eMLR - model fitting

workflowr

• Summary
• Checks
• Past versions

Last updated: 2021-03-10

Checks: 7 0

Knit directory: emlr_mod_v_XXX/

This reproducible R Markdown analysis was created with workflowr (version 1.6.2). The Checks tab describes the reproducibility checks that were applied when the results were created. The Past versions tab lists the development history.

---

R Markdown file: up-to-date

Great! Since the R Markdown file has been committed to the Git repository, you know the exact version of the code that produced these results.

Environment: empty

Great job! The global environment was empty. Objects defined in the global environment can affect the analysis in your R Markdown file in unknown ways. For reproduciblity it’s best to always run the code in an empty environment.

Seed: set.seed(20200707)

The command set.seed(20200707) was run prior to running the code in the R Markdown file. Setting a seed ensures that any results that rely on randomness, e.g. subsampling or permutations, are reproducible.

Session information: recorded

Great job! Recording the operating system, R version, and package versions is critical for reproducibility.

Cache: none

Nice! There were no cached chunks for this analysis, so you can be confident that you successfully produced the results during this run.

File paths: relative

Great job! Using relative paths to the files within your workflowr project makes it easier to run your code on other machines.

Repository version: e255177

Great! You are using Git for version control. Tracking code development and connecting the code version to the results is critical for reproducibility.

The results in this page were generated with repository version e255177. See the Past versions tab to see a history of the changes made to the R Markdown and HTML files.

Note that you need to be careful to ensure that all relevant files for the analysis have been committed to Git prior to generating the results (you can use wflow_publish or wflow_git_commit). workflowr only checks the R Markdown file, but you know if there are other scripts or data files that it depends on. Below is the status of the Git repository when the results were generated:

Ignored files:
    Ignored:    .Rhistory
    Ignored:    .Rproj.user/

Unstaged changes:
    Deleted:    a.png
    Modified:   data/auxillary/params_local.rds

Note that any generated files, e.g. HTML, png, CSS, etc., are not included in this status report because it is ok for generated content to have uncommitted changes.

---

These are the previous versions of the repository in which changes were made to the R Markdown (analysis/eMLR_model_fitting.Rmd) and HTML (docs/eMLR_model_fitting.html) files. If you’ve configured a remote Git repository (see ?wflow_git_remote), click on the hyperlinks in the table below to view the files as they were in that past version.

File	Version	Author	Date	Message
Rmd	e255177	Donghe-Zhu	2021-03-10	local rebuild
html	f2a7146	Donghe-Zhu	2021-03-10	Build site.
html	fd528ed	Donghe-Zhu	2021-03-10	Build site.
html	9d5a62c	Donghe-Zhu	2021-03-10	Build site.
Rmd	09b27ef	Donghe-Zhu	2021-03-10	local rebuild
html	5d1e70b	Donghe-Zhu	2021-03-10	Build site.
Rmd	6125b2d	Donghe-Zhu	2021-03-10	local rebuild
html	2093979	Donghe-Zhu	2021-03-10	Build site.
Rmd	558d285	Donghe-Zhu	2021-03-10	local rebuild
html	b865899	Donghe-Zhu	2021-03-10	Build site.
html	cc2a956	Donghe-Zhu	2021-03-10	Build site.
Rmd	2a633bd	Donghe-Zhu	2021-03-10	local rebuild
html	60689fb	Donghe-Zhu	2021-03-10	Build site.
html	9230b52	Donghe-Zhu	2021-03-10	Build site.
html	dba33c8	Donghe-Zhu	2021-03-09	Build site.
Rmd	6a60e02	Donghe-Zhu	2021-03-09	local rebuild
html	17f1c4a	Donghe-Zhu	2021-03-09	Build site.
Rmd	4a4a400	Donghe-Zhu	2021-03-09	local rebuild
html	c024d1a	Donghe-Zhu	2021-03-09	Build site.
Rmd	34744ec	Donghe-Zhu	2021-03-09	local rebuild
html	02f7242	Donghe-Zhu	2021-03-09	Build site.
html	6f50bc6	Donghe-Zhu	2021-03-09	Build site.
Rmd	88f0729	Donghe-Zhu	2021-03-09	local rebuild
html	1691156	Donghe-Zhu	2021-03-08	Build site.
html	c0ceaf8	Donghe-Zhu	2021-03-08	Build site.
html	058e0a1	Donghe-Zhu	2021-03-08	Build site.
html	112dea0	Donghe-Zhu	2021-03-08	Build site.
html	1843412	Donghe-Zhu	2021-03-08	Build site.
Rmd	d709f6c	Donghe-Zhu	2021-03-08	local rebuild
html	65b0cef	Donghe-Zhu	2021-03-07	Build site.
html	4083a6c	Donghe-Zhu	2021-03-07	Build site.
html	3fbbfa4	Donghe-Zhu	2021-03-07	Build site.
html	627c8fb	Donghe-Zhu	2021-03-07	Build site.
html	3607f4d	Donghe-Zhu	2021-03-07	Build site.
html	9ef3222	Donghe-Zhu	2021-03-05	Build site.
Rmd	2be54f9	Donghe-Zhu	2021-03-05	local rebuild
html	8c1e978	Donghe-Zhu	2021-03-05	Build site.
html	865f68c	Donghe-Zhu	2021-03-05	Build site.
html	ee69bc1	Donghe-Zhu	2021-03-05	Build site.
html	a79291f	Donghe-Zhu	2021-03-05	Build site.
html	e8c6f30	Donghe-Zhu	2021-03-04	Build site.
html	59288fe	Donghe-Zhu	2021-03-04	Build site.
html	731abc8	Donghe-Zhu	2021-03-04	Build site.
html	e2a5a33	Donghe-Zhu	2021-03-04	Build site.
html	c7892c1	Donghe-Zhu	2021-03-04	Build site.
html	924430b	Donghe-Zhu	2021-03-03	Build site.
html	0d0bca1	Donghe-Zhu	2021-03-03	Build site.
html	cb63c16	Donghe-Zhu	2021-03-03	Build site.
html	ffda45a	Donghe-Zhu	2021-03-03	Build site.
html	691ba81	Donghe-Zhu	2021-03-03	Build site.
html	c5e45a2	Donghe-Zhu	2021-03-03	Build site.
html	89c3e58	Donghe-Zhu	2021-03-03	Build site.
html	c407a50	Donghe-Zhu	2021-03-03	Build site.
html	c911669	Donghe-Zhu	2021-03-03	Build site.
Rmd	e1f9d21	Donghe-Zhu	2021-03-03	local rebuild
html	b71c719	Donghe-Zhu	2021-03-01	Build site.
html	13666ca	Donghe-Zhu	2021-03-01	Build site.
Rmd	c3195f4	Donghe-Zhu	2021-03-01	local rebuild
html	c6e60fe	Donghe-Zhu	2021-03-01	Build site.
Rmd	8ef147d	Donghe-Zhu	2021-03-01	local rebuild
html	7a388f7	Donghe-Zhu	2021-03-01	Build site.
html	799e913	Donghe-Zhu	2021-03-01	Build site.
Rmd	aa780a7	Donghe-Zhu	2021-03-01	local rebuild
html	66ff99f	Donghe-Zhu	2021-03-01	Build site.
html	ac9bb7a	Donghe-Zhu	2021-02-28	Build site.
html	efdc047	Donghe-Zhu	2021-02-28	Build site.
html	e9a7418	Donghe-Zhu	2021-02-28	Build site.
Rmd	eac1b0e	Donghe-Zhu	2021-02-28	local rebuild
html	e152917	Donghe-Zhu	2021-02-28	Build site.
html	feb991c	Donghe-Zhu	2021-02-27	Build site.
Rmd	4563314	Donghe-Zhu	2021-02-27	local rebuild
html	287123c	Donghe-Zhu	2021-02-27	Build site.
Rmd	764a9c2	Donghe-Zhu	2021-02-27	local rebuild
html	54d5b5b	Donghe-Zhu	2021-02-27	Build site.
Rmd	2e836bf	Donghe-Zhu	2021-02-27	local rebuild
html	330f064	Donghe-Zhu	2021-02-27	Build site.
Rmd	f360282	Donghe-Zhu	2021-02-27	local rebuild
html	adbc9bc	Donghe-Zhu	2021-02-27	Build site.
Rmd	a8a8f9c	Donghe-Zhu	2021-02-27	local rebuild
html	5937141	Donghe-Zhu	2021-02-27	Build site.
Rmd	5f0bfca	Donghe-Zhu	2021-02-27	local rebuild
html	4414bbf	Donghe-Zhu	2021-02-27	Build site.
html	a265efb	Donghe-Zhu	2021-02-27	Build site.
html	19edd1e	Donghe-Zhu	2021-02-27	Build site.
Rmd	1ae5bb4	Donghe-Zhu	2021-02-27	local rebuild
html	f20483f	Donghe-Zhu	2021-02-26	Build site.
html	6a2c7b3	Donghe-Zhu	2021-02-25	Build site.
html	02b976d	Donghe-Zhu	2021-02-24	Build site.
html	354c224	Donghe-Zhu	2021-02-24	Build site.
Rmd	d910d39	Donghe-Zhu	2021-02-24	local rebuild
html	1a0a88a	Donghe-Zhu	2021-02-24	Build site.
Rmd	663e891	Donghe-Zhu	2021-02-24	local rebuild
html	57f701e	Donghe-Zhu	2021-02-24	Build site.
html	06f3149	Donghe-Zhu	2021-02-16	Build site.
html	401eab3	Donghe-Zhu	2021-02-15	Build site.
html	e3bba84	Donghe-Zhu	2021-02-15	Build site.
html	5dce4b1	Donghe-Zhu	2021-02-15	Build site.
Rmd	35b0f2e	Donghe-Zhu	2021-02-15	local rebuild
html	4469a0c	Donghe-Zhu	2021-02-13	Build site.
Rmd	8186d57	Donghe-Zhu	2021-02-10	apply nr_obs
html	5ae6a69	Donghe-Zhu	2021-02-10	Build site.
Rmd	eeb6557	Donghe-Zhu	2021-02-10	local rebuild
html	05385dc	Donghe-Zhu	2021-02-10	Build site.
html	f791ae4	Donghe-Zhu	2021-02-09	Build site.
html	f71ae34	Donghe-Zhu	2021-02-09	Build site.
html	c011832	Donghe-Zhu	2021-02-09	Build site.
html	a145fa7	Donghe-Zhu	2021-02-09	Build site.
Rmd	37a41c8	Donghe-Zhu	2021-02-09	local rebuild
html	c344e42	Donghe-Zhu	2021-02-08	Build site.
Rmd	8f5fa79	Donghe-Zhu	2021-02-08	local rebuild
html	2f095d7	Donghe-Zhu	2021-02-07	Build site.
html	2305044	Donghe-Zhu	2021-02-07	Build site.
Rmd	c3638c1	Donghe-Zhu	2021-02-07	local rebuild
html	1fad5f1	Donghe-Zhu	2021-02-07	Build site.
html	ca03c39	Donghe-Zhu	2021-02-07	Build site.
html	e2ffc14	Donghe-Zhu	2021-02-05	Build site.
html	cd7c52c	Donghe-Zhu	2021-02-04	Build site.
Rmd	bcf91a8	jens-daniel-mueller	2021-02-04	separate MLR tables, added plot residuals vs location
html	bcf84f4	Donghe-Zhu	2021-02-02	Build site.
html	a518739	Donghe-Zhu	2021-02-01	Build site.
html	61666de	Donghe-Zhu	2021-01-31	Build site.
html	865b582	Donghe-Zhu	2021-01-31	Build site.
html	3e68089	Donghe-Zhu	2021-01-31	Build site.
html	ecf335c	Donghe-Zhu	2021-01-31	Build site.
html	a618965	Donghe-Zhu	2021-01-31	Build site.
html	59e006e	Donghe-Zhu	2021-01-31	Build site.
html	a1c8f87	Donghe-Zhu	2021-01-31	Build site.
html	ae5c18f	Donghe-Zhu	2021-01-31	Build site.
html	b50fe52	Donghe-Zhu	2021-01-31	Build site.
Rmd	ac99ae5	jens-daniel-mueller	2021-01-29	code review
html	ac99ae5	jens-daniel-mueller	2021-01-29	code review
html	b5bdcaf	Donghe-Zhu	2021-01-29	Build site.
Rmd	b234505	Donghe-Zhu	2021-01-29	MLR approach across all depth
html	442010d	Donghe-Zhu	2021-01-29	Build site.
Rmd	e67e7dd	Donghe-Zhu	2021-01-29	surface equilibrium approach across all latitudes irrespective of gamma
html	372adf5	Donghe-Zhu	2021-01-29	Build site.
html	af8788e	Donghe-Zhu	2021-01-29	Build site.
html	21c91c9	Donghe-Zhu	2021-01-29	Build site.
html	eded038	Donghe-Zhu	2021-01-29	Build site.
html	541d4dd	Donghe-Zhu	2021-01-29	Build site.
html	6a75576	Donghe-Zhu	2021-01-28	Build site.
html	16fba40	Donghe-Zhu	2021-01-28	Build site.
Rmd	aecf0c6	Donghe-Zhu	2021-01-28	diagnostic ploting
Rmd	a02684e	Donghe-Zhu	2021-01-28	error
Rmd	4584be9	Donghe-Zhu	2021-01-28	latest
html	12bc567	Donghe-Zhu	2021-01-27	Build site.
html	ceed31b	Donghe-Zhu	2021-01-27	Build site.
html	342402d	Donghe-Zhu	2021-01-27	Build site.
html	5bad5c2	Donghe-Zhu	2021-01-27	Build site.
Rmd	c2c9529	Donghe-Zhu	2021-01-27	random subsetting based on lat
html	61efb56	Donghe-Zhu	2021-01-25	Build site.
html	48f638e	Donghe-Zhu	2021-01-25	Build site.
html	c1cec47	Donghe-Zhu	2021-01-25	Build site.
html	05ffb0c	Donghe-Zhu	2021-01-25	Build site.
html	8b97165	Donghe-Zhu	2021-01-25	Build site.
html	c569946	Donghe-Zhu	2021-01-24	Build site.
html	a2f0d56	Donghe-Zhu	2021-01-23	Build site.
html	28509fc	Donghe-Zhu	2021-01-23	Build site.
html	4c28e4a	Donghe-Zhu	2021-01-22	Build site.
html	24cc264	jens-daniel-mueller	2021-01-22	cleaned /docs before creating copies
html	88eb28f	Donghe-Zhu	2021-01-21	Build site.
html	2679490	Donghe-Zhu	2021-01-21	Build site.
html	7891955	Donghe-Zhu	2021-01-21	Build site.
html	d4cf1cb	Donghe-Zhu	2021-01-21	Build site.
Rmd	167eeec	Donghe-Zhu	2021-01-21	surface DIC calculation with atmospheric equilibrium option
html	1f3e5b6	jens-daniel-mueller	2021-01-20	Build site.
html	0e7bdf1	jens-daniel-mueller	2021-01-15	cleaning template repository
html	73cbef3	jens-daniel-mueller	2021-01-15	Build site.
html	4571843	jens-daniel-mueller	2021-01-14	revision and html deleted for template copying
html	23151cd	jens-daniel-mueller	2021-01-14	Build site.
html	b3564aa	jens-daniel-mueller	2021-01-14	Build site.
html	8d032c3	jens-daniel-mueller	2021-01-14	Build site.
html	022871c	Donghe-Zhu	2021-01-13	Build site.
Rmd	d44f36f	Donghe-Zhu	2021-01-13	reorder analysis final
html	17dee1d	jens-daniel-mueller	2021-01-13	Build site.
Rmd	9e04fd7	jens-daniel-mueller	2021-01-13	local rebuild after revision
html	a076226	Donghe-Zhu	2021-01-11	Build site.
Rmd	52eff18	Donghe-Zhu	2021-01-09	Implemet model_run and subsetting
html	7cdea0c	jens-daniel-mueller	2021-01-06	Build site.
Rmd	b5934dd	jens-daniel-mueller	2021-01-06	local rebuild after revision
html	fa85b93	jens-daniel-mueller	2021-01-06	Build site.
html	e5cb81a	Donghe-Zhu	2021-01-05	Build site.
Rmd	608cc45	Donghe-Zhu	2021-01-05	modification of analysis
html	a499f10	Donghe-Zhu	2021-01-05	Build site.
Rmd	715bdb4	Donghe-Zhu	2021-01-02	model modification
html	fb8a752	Donghe-Zhu	2020-12-23	Build site.
Rmd	82e3c9c	Donghe-Zhu	2020-12-23	first build after creating model template
html	8fae0b2	Donghe-Zhu	2020-12-21	Build site.
Rmd	00a1322	Donghe-Zhu	2020-12-21	first build after creating model template
Rmd	d73ae35	Donghe-Zhu	2020-12-21	first version with lm error
html	c8b76b3	jens-daniel-mueller	2020-12-19	Build site.
Rmd	b5fedce	jens-daniel-mueller	2020-12-19	first build after creating model template
Rmd	8e8abf5	Jens Müller	2020-12-18	Initial commit

---

1 Required data

Required are:

• cleaned and prepared GLODAP-based synthetic model subsetting file

GLODAP <-
  read_csv(paste(path_version_data,
                 "GLODAPv2.2020_MLR_fitting_ready.csv",
                 sep = ""))

2 Predictor combinations

Find all possible combinations of following considered predictor variables:

• sal, temp, aou, nitrate, silicate, phosphate, phosphate_star

# the following code is a workaround to find all predictor combinations
# using the olsrr package and fit all models for one era, slab, and basin

i_basin <- unique(GLODAP$basin)[1]
i_era   <- unique(GLODAP$era)[1]

# subset one basin and era for fitting
GLODAP_basin_era <- GLODAP %>%
  filter(basin == i_basin, era == i_era)

i_gamma_slab <- unique(GLODAP_basin_era$gamma_slab)[1]
print(i_gamma_slab)

# subset one gamma slab
GLODAP_basin_era_slab <- GLODAP_basin_era %>%
  filter(gamma_slab == i_gamma_slab)

# fit the full linear model, i.e. all predictor combinations
lm_full <- lm(paste(
  params_local$MLR_target,
  paste(params_local$MLR_predictors, collapse = " + "),
  sep = " ~ "
),
data = GLODAP_basin_era_slab)

# fit linear models for all possible predictor combinations
# unfortunately, this functions does not provide model coefficients (yet)
lm_all <- ols_step_all_possible(lm_full)

# convert to tibble
lm_all <- as_tibble(lm_all)

# extract relevant columns and format model formula
lm_all <- lm_all %>% 
  select(n, predictors) %>%
  mutate(lm_coeff = str_replace_all(predictors, " ", " + "),
         lm_coeff = paste(params_local$MLR_target, "~", lm_coeff))

# remove certain predictor combinations
# lm_rm_ph <- lm_all %>%
#   filter(str_detect(lm_coeff, "phosphate_star")) %>%
#   mutate(lm_coeff_filter = str_remove(lm_coeff, "phosphate_star")) %>%
#   filter(
#     str_detect(lm_coeff_filter, "oxygen") &
#       str_detect(lm_coeff_filter, "phosphate")
#   )

# lm_rm_si <- lm_all %>%
#   filter(str_detect(lm_coeff, "silicate_star")) %>%
#   mutate(lm_coeff_filter = str_remove(lm_coeff, "silicate_star")) %>%
#   filter(str_detect(lm_coeff_filter, "silicate"))

# lm_rm_o2 <- lm_all %>%
#   filter(str_detect(lm_coeff, "phosphate_star")) %>%
#   mutate(lm_coeff_filter = str_remove(lm_coeff, "phosphate_star")) %>%
#   filter(
#     str_detect(lm_coeff_filter, "phosphate") &
#       str_detect(lm_coeff_filter, "oxygen")
#   )

# lm_rm <- bind_rows(lm_rm_ph, lm_rm_o2) %>%
#   select(-lm_coeff_filter) %>%
#   unique()

# lm_rm <- lm_rm_ph %>%
#   select(-lm_coeff_filter) %>%
#   unique()
# 
# lm_all <- anti_join(lm_all, lm_rm)

# remove temp sal predictor combination
lm_all <- lm_all %>%
# filter(!(
#   str_detect(lm_coeff, "temp") &
#     str_detect(lm_coeff, "phosphate_star")
# )) %>%
mutate(lm_coeff_filter = str_remove(lm_coeff, "phosphate_star")) %>%
filter(!(str_detect(lm_coeff_filter, "nitrate") &
           str_detect(lm_coeff_filter, "phosphate")
)) %>%
filter(!(
  str_detect(lm_coeff_filter, "temp") &
    str_detect(lm_coeff_filter, "sal")
)) %>%
# filter(!(
#   str_detect(lm_coeff_filter, "oxygen") &
#     str_detect(lm_coeff_filter, "aou")
# )) %>%
select(-lm_coeff_filter)

# remove helper objects
rm(
  i_gamma_slab,
  i_era,
  i_basin,
  GLODAP_basin_era,
  GLODAP_basin_era_slab,
  lm_full,
  lm_rm_ph,
  lm_rm_si,
  lm_rm_o2,
  lm_rm
)

# lm_full <- lm(paste(
#   params_local$MLR_target,
#   paste(params_local$MLR_predictors, collapse = " + "),
#   sep = " ~ "
# ),
# data = GLODAP_basin_era_slab)
# 
# lm_full <-
#   loess(
#     cstar_tref ~ sal + temp + aou + phosphate,
#     span = 0.1,
#     degree = 1,
#     data = GLODAP_basin_era_slab
#   )

3 Apply predictor threshold

Select combinations with a total number of predictors in the range:

• Minimum: 2
  
• Maximum: 9

lm_all <- lm_all %>% 
  filter(n >= params_local$MLR_predictors_min,
         n <= params_local$MLR_predictors_max)

This results in a total number of MLR models of:

• 64

4 Fit all models

Individual linear regression models were fitted for the chosen target variable:

• cstar_tref

as a function of each predictor combination. Fitting was performed separately within each basin, era, and slab. Model diagnostics, such as the root mean squared error (RMSE), were calculated for each fitted model.

# loop across all basins, era, gamma slabs, and MLRs
# fit all MLR models
for (i_basin in unique(GLODAP$basin)) {
  for (i_era in unique(GLODAP$era)) {
    #i_basin <- unique(GLODAP$basin)[1]
    #i_era   <- unique(GLODAP$era)[1]
    print(i_basin)
    print(i_era)
    
    GLODAP_basin_era <- GLODAP %>%
      filter(basin == i_basin, era == i_era)
    
    for (i_gamma_slab in unique(GLODAP_basin_era$gamma_slab)) {
      #i_gamma_slab <- unique(GLODAP_basin_era$gamma_slab)[1]
      print(i_gamma_slab)
      
      GLODAP_basin_era_slab <- GLODAP_basin_era %>%
        filter(gamma_slab == i_gamma_slab)
      
      # number of observations used for each fitting model
      i_nr_obs = nrow(GLODAP_basin_era_slab)
      
      for (i_predictors in unique(lm_all$predictors)) {
        #i_predictors <- unique(lm_all$predictors)[1]
        
        # extract one model definition
        i_lm <- lm_all %>%
          filter(predictors == i_predictors) %>%
          select(lm_coeff) %>%
          pull()
        
        # extract number of predictors
        i_n_predictors <- lm_all %>%
          filter(predictors == i_predictors) %>%
          select(n) %>%
          pull()
        
        if (i_nr_obs > i_n_predictors) {
          # fit model
          if (params_local$MLR_type == "rlm") {
            i_lm_fit <- MASS::rlm(as.formula(i_lm),
                                  data = GLODAP_basin_era_slab)
          }
          
          if (params_local$MLR_type == "lm") {
            i_lm_fit <- lm(as.formula(i_lm),
                           data = GLODAP_basin_era_slab)
          }
          
          # find max predictor correlation
          i_cor_max <- GLODAP_basin_era_slab %>%
            select(!!!syms(str_split(i_predictors, " ",
                                     simplify = TRUE))) %>%
            correlate(quiet = TRUE) %>%
            select(-term) %>%
            abs() %>%
            max(na.rm = TRUE)
          
          # calculate root mean squared error
          i_rmse <- sqrt(c(crossprod(i_lm_fit$residuals)) /
                           length(i_lm_fit$residuals))
          
          # calculate maximum residual
          i_resid_max <- max(abs(i_lm_fit$residuals))
          
          # calculate Akaike information criterion aic
          i_aic <- AIC(i_lm_fit)
          
          # collect model coefficients and diagnostics
          coefficients <- tidy(i_lm_fit)
          
          coefficients <- coefficients %>%
            mutate(
              basin = i_basin,
              era = i_era,
              gamma_slab = i_gamma_slab,
              model = i_lm,
              nr_obs = i_nr_obs,
              rmse = i_rmse,
              aic = i_aic,
              resid_max = i_resid_max,
              n_predictors = i_n_predictors,
              na_predictor = anyNA(coefficients$estimate),
              cor_max = i_cor_max
            )
          
          if (exists("lm_all_fitted")) {
            lm_all_fitted <- bind_rows(lm_all_fitted, coefficients)
          }
          
          if (!exists("lm_all_fitted")) {
            lm_all_fitted <- coefficients
          }
        }
      }
    }
  }
}

rm(
  i_lm_fit,
  coefficients,
  i_rmse,
  GLODAP_basin_era,
  GLODAP_basin_era_slab,
  i_lm,
  i_basin,
  i_era,
  i_gamma_slab,
  i_nr_obs,
  i_predictors,
  i_aic,
  i_n_predictors,
  i_resid_max
)

5 Prepare coeffcients

Coefficients are prepared for the mapping of Cant and the chosen target variable.

5.1 Formatting

# select relevant columns
lm_all_fitted <- lm_all_fitted %>%
  select(
    basin,
    gamma_slab,
    era,
    model,
    nr_obs,
    n_predictors,
    term,
    estimate,
    rmse,
    aic,
    resid_max,
    na_predictor,
    cor_max
  )

# set coefficient to zero if not fitted (=NA)
lm_all_fitted <- lm_all_fitted %>%
  mutate(estimate = if_else(is.na(estimate), 0, estimate))

# Prepare model coefficients for mapping of target variable
lm_all_fitted_wide <- lm_all_fitted %>%
  pivot_wider(
    values_from = estimate,
    names_from = term,
    names_prefix = "coeff_",
    values_fill = 0
  )

5.2 Predictor selection

Within each basin and slab, the following number of best linear regression models was selected:

• 5

The criterion used to select the best models was:

• rmse

The criterion was summed up for two adjacent eras, and the models with lowest summed values were selected.

Please note, that currently the lm() function produces NAs for some predictors. It is not yet entirely clear when this happens, but presumably it is caused by some form of collinearity between predictors, such that including another predictor does not help to explain the target variable any better. The issues also expresses as exactly identical rmse values of different models. As an interim solution, models with fitted NA predictors were not included.

# remove models with predictors fitted as NA
lm_all_fitted_wide <- lm_all_fitted_wide %>%
  filter(na_predictor == FALSE)

# calculate RMSE sum for adjacent eras
lm_all_fitted_wide_eras <- lm_all_fitted_wide %>%
  select(basin, gamma_slab, n_predictors, model, era, nr_obs, rmse, aic, resid_max) %>%
  arrange(era) %>%
  group_by(basin, gamma_slab, model) %>%
  mutate(
    eras = paste(lag(era), era, sep = " --> "),
    rmse_sum = rmse + lag(rmse),
    aic_sum = aic + lag(aic)
  ) %>%
  ungroup() %>%
  select(-c(era)) %>%
  drop_na()

# subset models with lowest summed criterion
# chose which criterion is applied

if (params_local$MLR_criterion == "aic") {
  lm_best <- lm_all_fitted_wide_eras %>%
    group_by(basin, gamma_slab, eras) %>%
    slice_min(order_by = aic_sum,
              with_ties = FALSE,
              n = params_local$MLR_number) %>%
    ungroup() %>%
    arrange(basin, gamma_slab, eras, model)
} else {
  lm_best <- lm_all_fitted_wide_eras %>%
    group_by(basin, gamma_slab, eras) %>%
    slice_min(order_by = rmse_sum,
              with_ties = FALSE,
              n = params_local$MLR_number) %>%
    ungroup() %>%
    arrange(basin, gamma_slab, eras, model)
}

5.3 RMSE tables

5.3.1 per model

lm_best %>%
  kable() %>%
  add_header_above() %>%
  kable_styling() %>%
  scroll_box(width = "100%", height = "400px")

basin	gamma_slab	n_predictors	model	nr_obs	rmse	aic	resid_max	eras	rmse_sum	aic_sum
Atlantic	(-Inf,26]	5	cstar_tref ~ sal + aou + nitrate + silicate + phosphate_star	158	1.5921923	609.3599	6.118408	1982-1999 –> 2000-2012	3.2779521	1430.8804
Atlantic	(-Inf,26]	4	cstar_tref ~ sal + aou + phosphate + phosphate_star	158	1.0492038	475.5626	4.357844	1982-1999 –> 2000-2012	2.3855522	1198.4564
Atlantic	(-Inf,26]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	158	1.0480832	477.2249	4.299021	1982-1999 –> 2000-2012	2.3837757	1201.9145
Atlantic	(-Inf,26]	4	cstar_tref ~ temp + aou + phosphate + phosphate_star	158	1.4654213	581.1417	7.417048	1982-1999 –> 2000-2012	3.1276914	1394.8248
Atlantic	(-Inf,26]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	158	1.4545749	580.7941	7.074044	1982-1999 –> 2000-2012	3.1160634	1396.2815
Atlantic	(-Inf,26]	5	cstar_tref ~ sal + aou + nitrate + silicate + phosphate_star	72	1.6825475	293.2516	3.600013	2000-2012 –> 2013-2019	3.2747398	902.6116
Atlantic	(-Inf,26]	4	cstar_tref ~ sal + aou + phosphate + phosphate_star	72	1.2725075	251.0296	3.658367	2000-2012 –> 2013-2019	2.3217113	726.5922
Atlantic	(-Inf,26]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	72	1.1936365	243.8158	3.237974	2000-2012 –> 2013-2019	2.2417197	721.0407
Atlantic	(-Inf,26]	4	cstar_tref ~ temp + aou + phosphate + phosphate_star	72	1.5761474	281.8448	5.713265	2000-2012 –> 2013-2019	3.0415687	862.9865
Atlantic	(-Inf,26]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	72	1.5044066	277.1365	5.003414	2000-2012 –> 2013-2019	2.9589816	857.9306
Atlantic	(26,26.5]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	1046	3.5518213	5633.9468	13.477555	1982-1999 –> 2000-2012	6.9985663	13749.8718
Atlantic	(26,26.5]	4	cstar_tref ~ temp + aou + nitrate + phosphate_star	1046	4.1960266	5980.6362	10.665564	1982-1999 –> 2000-2012	8.3544396	14667.0559
Atlantic	(26,26.5]	4	cstar_tref ~ temp + aou + nitrate + silicate	1046	4.0405761	5901.6616	14.579174	1982-1999 –> 2000-2012	8.1249524	14533.2897
Atlantic	(26,26.5]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	1046	4.0338370	5900.1695	15.685804	1982-1999 –> 2000-2012	8.1154929	14531.7655
Atlantic	(26,26.5]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	1046	4.2948916	6031.3553	13.012884	1982-1999 –> 2000-2012	8.5299909	14775.5085
Atlantic	(26,26.5]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	567	3.6070302	3077.8676	10.902628	2000-2012 –> 2013-2019	7.1588515	8711.8144
Atlantic	(26,26.5]	4	cstar_tref ~ temp + aou + nitrate + phosphate_star	567	4.1023698	3221.7908	12.065595	2000-2012 –> 2013-2019	8.2983964	9202.4270
Atlantic	(26,26.5]	4	cstar_tref ~ temp + aou + nitrate + silicate	567	3.8959809	3163.2545	13.662757	2000-2012 –> 2013-2019	7.9365570	9064.9161
Atlantic	(26,26.5]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	567	3.8631919	3155.6702	14.511046	2000-2012 –> 2013-2019	7.8970289	9055.8397
Atlantic	(26,26.5]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	567	4.2189568	3255.5690	10.763473	2000-2012 –> 2013-2019	8.5138484	9286.9243
Atlantic	(26.5,27.25]	4	cstar_tref ~ aou + silicate + phosphate + phosphate_star	5826	3.2048632	30116.1996	13.883989	1982-1999 –> 2000-2012	5.8566114	66749.2353
Atlantic	(26.5,27.25]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	5826	3.0564406	29565.6808	11.606855	1982-1999 –> 2000-2012	5.6534731	65881.7998
Atlantic	(26.5,27.25]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	5826	3.3320007	30571.5035	22.586631	1982-1999 –> 2000-2012	6.2196175	68509.9481
Atlantic	(26.5,27.25]	4	cstar_tref ~ temp + aou + silicate + phosphate	5826	3.4482264	30969.0165	22.457033	1982-1999 –> 2000-2012	6.3351546	68901.8131
Atlantic	(26.5,27.25]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	5826	2.9085483	28987.7771	53.677420	1982-1999 –> 2000-2012	5.4636468	65054.8974
Atlantic	(26.5,27.25]	4	cstar_tref ~ aou + silicate + phosphate + phosphate_star	3061	3.7866672	16850.1007	26.056626	2000-2012 –> 2013-2019	6.9915304	46966.3003
Atlantic	(26.5,27.25]	4	cstar_tref ~ sal + aou + silicate + phosphate	3061	3.6106563	16558.7135	19.167648	2000-2012 –> 2013-2019	6.9485986	47148.9767
Atlantic	(26.5,27.25]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	3061	3.5323227	16426.4342	21.773645	2000-2012 –> 2013-2019	6.5887633	45992.1150
Atlantic	(26.5,27.25]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	3061	3.7730192	16829.9956	17.919627	2000-2012 –> 2013-2019	7.1050198	47401.4991
Atlantic	(26.5,27.25]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	3061	3.2108913	15842.3519	25.125644	2000-2012 –> 2013-2019	6.1194395	44830.1290
Atlantic	(27.25,27.5]	4	cstar_tref ~ sal + aou + nitrate + silicate	2025	2.5285742	9515.7061	13.358360	1982-1999 –> 2000-2012	5.1450783	23231.4624
Atlantic	(27.25,27.5]	5	cstar_tref ~ sal + aou + nitrate + silicate + phosphate_star	2025	2.4514644	9392.2776	12.813379	1982-1999 –> 2000-2012	4.9864330	22927.8111
Atlantic	(27.25,27.5]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	2025	2.6905754	9769.2091	21.422922	1982-1999 –> 2000-2012	4.8576234	22402.1133
Atlantic	(27.25,27.5]	4	cstar_tref ~ temp + aou + nitrate + silicate	2025	2.4063497	9315.0504	11.614926	1982-1999 –> 2000-2012	4.1264292	20616.3452
Atlantic	(27.25,27.5]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	2025	2.2547324	9053.4778	15.509020	1982-1999 –> 2000-2012	3.9706310	20342.7650
Atlantic	(27.25,27.5]	4	cstar_tref ~ aou + nitrate + silicate + phosphate_star	1109	3.0051254	5599.7139	21.412798	2000-2012 –> 2013-2019	5.7555576	15456.0350
Atlantic	(27.25,27.5]	4	cstar_tref ~ sal + aou + nitrate + silicate	1109	3.0025580	5597.8181	16.245244	2000-2012 –> 2013-2019	5.5311321	15113.5242
Atlantic	(27.25,27.5]	5	cstar_tref ~ sal + aou + nitrate + silicate + phosphate_star	1109	2.7952620	5441.1451	16.992150	2000-2012 –> 2013-2019	5.2467264	14833.4228
Atlantic	(27.25,27.5]	4	cstar_tref ~ temp + aou + nitrate + silicate	1109	3.1081847	5674.5038	12.222568	2000-2012 –> 2013-2019	5.5145344	14989.5543
Atlantic	(27.25,27.5]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	1109	2.7923328	5438.8197	16.610907	2000-2012 –> 2013-2019	5.0470652	14492.2975
Atlantic	(27.5,27.75]	3	cstar_tref ~ sal + aou + phosphate	2804	2.7836924	13708.7557	13.816311	1982-1999 –> 2000-2012	5.2587422	31083.3422
Atlantic	(27.5,27.75]	4	cstar_tref ~ sal + aou + phosphate + phosphate_star	2804	2.7656318	13674.2524	14.269310	1982-1999 –> 2000-2012	5.0314996	30391.3946
Atlantic	(27.5,27.75]	4	cstar_tref ~ sal + aou + silicate + phosphate	2804	2.4538915	13003.5694	13.901382	1982-1999 –> 2000-2012	4.8210764	30047.3887
Atlantic	(27.5,27.75]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	2804	2.3944064	12867.9502	14.685866	1982-1999 –> 2000-2012	4.4949743	29021.3907
Atlantic	(27.5,27.75]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	2804	3.1165165	14346.1100	16.244315	1982-1999 –> 2000-2012	5.5026775	31451.5564
Atlantic	(27.5,27.75]	4	cstar_tref ~ sal + aou + nitrate + silicate	1515	3.2789491	7909.5783	16.534959	2000-2012 –> 2013-2019	6.1058258	21706.6649
Atlantic	(27.5,27.75]	5	cstar_tref ~ sal + aou + nitrate + silicate + phosphate_star	1515	3.2267256	7862.9314	14.600864	2000-2012 –> 2013-2019	6.0506408	21656.1398
Atlantic	(27.5,27.75]	4	cstar_tref ~ sal + aou + phosphate + phosphate_star	1515	3.4234258	8040.2283	14.171915	2000-2012 –> 2013-2019	6.1890576	21714.4806
Atlantic	(27.5,27.75]	4	cstar_tref ~ sal + aou + silicate + phosphate	1515	2.8745087	7510.7055	15.545879	2000-2012 –> 2013-2019	5.3284002	20514.2749
Atlantic	(27.5,27.75]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	1515	2.8711798	7509.1946	15.461950	2000-2012 –> 2013-2019	5.2655862	20377.1448
Atlantic	(27.75,27.85]	4	cstar_tref ~ sal + aou + nitrate + silicate	1036	1.9259602	4310.0805	13.267819	1982-1999 –> 2000-2012	3.9306085	9904.1154
Atlantic	(27.75,27.85]	5	cstar_tref ~ sal + aou + nitrate + silicate + phosphate_star	1036	1.8800580	4262.0997	14.057027	1982-1999 –> 2000-2012	3.8317057	9787.3967
Atlantic	(27.75,27.85]	4	cstar_tref ~ sal + aou + phosphate + phosphate_star	1036	1.9943230	4382.3519	12.367472	1982-1999 –> 2000-2012	3.6776199	9515.1410
Atlantic	(27.75,27.85]	4	cstar_tref ~ sal + aou + silicate + phosphate	1036	1.7389083	4098.3902	12.226980	1982-1999 –> 2000-2012	3.5475856	9420.8408
Atlantic	(27.75,27.85]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	1036	1.5641536	3880.9392	12.798383	1982-1999 –> 2000-2012	3.1611985	8876.8661
Atlantic	(27.75,27.85]	4	cstar_tref ~ sal + aou + nitrate + silicate	513	2.0314562	2195.0114	12.644220	2000-2012 –> 2013-2019	3.9574164	6505.0919
Atlantic	(27.75,27.85]	5	cstar_tref ~ sal + aou + nitrate + silicate + phosphate_star	513	2.0209724	2191.7028	12.956555	2000-2012 –> 2013-2019	3.9010304	6453.8025
Atlantic	(27.75,27.85]	4	cstar_tref ~ sal + aou + phosphate + phosphate_star	513	2.4147179	2372.3345	11.388027	2000-2012 –> 2013-2019	4.4090409	6754.6864
Atlantic	(27.75,27.85]	4	cstar_tref ~ sal + aou + silicate + phosphate	513	1.8570079	2102.8906	11.721525	2000-2012 –> 2013-2019	3.5959162	6201.2808
Atlantic	(27.75,27.85]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	513	1.7475521	2042.5606	12.039326	2000-2012 –> 2013-2019	3.3117057	5923.4997
Atlantic	(27.85,27.95]	4	cstar_tref ~ aou + silicate + phosphate + phosphate_star	983	3.4332878	5226.7302	38.381356	1982-1999 –> 2000-2012	6.3108859	11854.3203
Atlantic	(27.85,27.95]	4	cstar_tref ~ sal + aou + phosphate + phosphate_star	983	3.4396213	5230.3536	36.781212	1982-1999 –> 2000-2012	6.1696286	11717.2584
Atlantic	(27.85,27.95]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	983	3.4272905	5225.2930	34.214054	1982-1999 –> 2000-2012	6.1571686	11714.0714
Atlantic	(27.85,27.95]	4	cstar_tref ~ temp + aou + phosphate + phosphate_star	983	3.0946626	5022.5819	23.332862	1982-1999 –> 2000-2012	6.0114682	11686.3324
Atlantic	(27.85,27.95]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	983	3.0757549	5012.5332	23.130965	1982-1999 –> 2000-2012	5.9400103	11629.7050
Atlantic	(27.85,27.95]	4	cstar_tref ~ aou + silicate + phosphate + phosphate_star	569	3.7372699	3127.0405	23.268863	2000-2012 –> 2013-2019	7.1705577	8353.7707
Atlantic	(27.85,27.95]	4	cstar_tref ~ sal + aou + phosphate + phosphate_star	569	3.4103854	3022.8793	30.447244	2000-2012 –> 2013-2019	6.8500067	8253.2329
Atlantic	(27.85,27.95]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	569	3.3215129	2994.8304	29.207068	2000-2012 –> 2013-2019	6.7488034	8220.1234
Atlantic	(27.85,27.95]	4	cstar_tref ~ temp + aou + phosphate + phosphate_star	569	3.6730463	3107.3144	22.693963	2000-2012 –> 2013-2019	6.7677089	8129.8962
Atlantic	(27.85,27.95]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	569	3.6600265	3105.2733	23.151675	2000-2012 –> 2013-2019	6.7357814	8117.8065
Atlantic	(27.95,28.05]	4	cstar_tref ~ sal + aou + phosphate + phosphate_star	1204	4.6143746	7111.0606	26.067945	1982-1999 –> 2000-2012	9.4462340	17159.5181
Atlantic	(27.95,28.05]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	1204	4.5430532	7075.5511	25.262696	1982-1999 –> 2000-2012	9.2883301	17065.3992
Atlantic	(27.95,28.05]	4	cstar_tref ~ temp + aou + nitrate + phosphate_star	1204	4.0815088	6815.5758	22.528945	1982-1999 –> 2000-2012	8.1122385	16256.3696
Atlantic	(27.95,28.05]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	1204	3.8590720	6682.6316	25.099675	1982-1999 –> 2000-2012	7.3908813	15682.5017
Atlantic	(27.95,28.05]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	1204	4.5224648	7064.6136	21.845213	1982-1999 –> 2000-2012	9.3768338	17130.6504
Atlantic	(27.95,28.05]	4	cstar_tref ~ sal + aou + phosphate + phosphate_star	666	4.3483289	3859.7886	24.917815	2000-2012 –> 2013-2019	8.9627036	10970.8492
Atlantic	(27.95,28.05]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	666	4.2792874	3840.4697	24.913097	2000-2012 –> 2013-2019	8.8223406	10916.0208
Atlantic	(27.95,28.05]	4	cstar_tref ~ temp + aou + nitrate + phosphate_star	666	3.8465745	3696.4739	22.933854	2000-2012 –> 2013-2019	7.9280833	10512.0498
Atlantic	(27.95,28.05]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	666	3.5060655	3575.0128	26.986021	2000-2012 –> 2013-2019	7.3651375	10257.6443
Atlantic	(27.95,28.05]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	666	4.4290548	3886.2901	23.783433	2000-2012 –> 2013-2019	8.9515196	10950.9038
Atlantic	(28.05,28.1]	4	cstar_tref ~ aou + silicate + phosphate + phosphate_star	804	1.1604167	2532.8901	10.979649	1982-1999 –> 2000-2012	2.1134849	5495.0017
Atlantic	(28.05,28.1]	4	cstar_tref ~ sal + aou + phosphate + phosphate_star	804	1.0598757	2387.1610	7.838670	1982-1999 –> 2000-2012	1.9527650	5208.9110
Atlantic	(28.05,28.1]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	804	1.0324411	2346.9902	6.945256	1982-1999 –> 2000-2012	1.9247967	5169.4535
Atlantic	(28.05,28.1]	4	cstar_tref ~ temp + aou + phosphate + phosphate_star	804	1.1065403	2456.4443	11.331523	1982-1999 –> 2000-2012	2.0473492	5390.6954
Atlantic	(28.05,28.1]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	804	1.0436142	2364.2985	12.188672	1982-1999 –> 2000-2012	1.8828911	5054.7923
Atlantic	(28.05,28.1]	5	cstar_tref ~ sal + aou + nitrate + silicate + phosphate_star	434	1.1676572	1380.1780	6.819178	2000-2012 –> 2013-2019	2.3011906	3877.3774
Atlantic	(28.05,28.1]	4	cstar_tref ~ sal + aou + phosphate + phosphate_star	434	1.1212849	1343.0032	8.929761	2000-2012 –> 2013-2019	2.1811606	3730.1642
Atlantic	(28.05,28.1]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	434	1.0586072	1295.0748	7.429722	2000-2012 –> 2013-2019	2.0910483	3642.0650
Atlantic	(28.05,28.1]	4	cstar_tref ~ temp + aou + phosphate + phosphate_star	434	1.1480057	1363.4454	12.833810	2000-2012 –> 2013-2019	2.2545460	3819.8898
Atlantic	(28.05,28.1]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	434	1.1075442	1334.3006	13.578379	2000-2012 –> 2013-2019	2.1511584	3698.5991
Atlantic	(28.1,28.15]	4	cstar_tref ~ aou + silicate + phosphate + phosphate_star	936	0.8652007	2397.1990	9.973159	1982-1999 –> 2000-2012	1.5501093	5104.0130
Atlantic	(28.1,28.15]	5	cstar_tref ~ sal + aou + nitrate + silicate + phosphate_star	936	0.8394339	2342.6013	6.649159	1982-1999 –> 2000-2012	1.5477300	5138.3794
Atlantic	(28.1,28.15]	4	cstar_tref ~ sal + aou + phosphate + phosphate_star	936	0.7732900	2186.9596	6.039973	1982-1999 –> 2000-2012	1.4451653	4844.0128
Atlantic	(28.1,28.15]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	936	0.7598609	2156.1646	5.927820	1982-1999 –> 2000-2012	1.3893138	4646.2932
Atlantic	(28.1,28.15]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	936	0.7856962	2218.7544	10.025704	1982-1999 –> 2000-2012	1.3744859	4535.9182
Atlantic	(28.1,28.15]	5	cstar_tref ~ sal + aou + nitrate + silicate + phosphate_star	497	0.9633503	1387.3108	6.933462	2000-2012 –> 2013-2019	1.8027842	3729.9121
Atlantic	(28.1,28.15]	4	cstar_tref ~ sal + aou + phosphate + phosphate_star	497	0.8714406	1285.6430	6.181914	2000-2012 –> 2013-2019	1.6447306	3472.6026
Atlantic	(28.1,28.15]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	497	0.8712585	1287.4353	6.182326	2000-2012 –> 2013-2019	1.6311195	3443.5998
Atlantic	(28.1,28.15]	4	cstar_tref ~ temp + aou + phosphate + phosphate_star	497	0.9653756	1387.3983	11.632299	2000-2012 –> 2013-2019	1.8224628	3766.9596
Atlantic	(28.1,28.15]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	497	0.8791505	1296.3985	11.933687	2000-2012 –> 2013-2019	1.6648467	3515.1529
Atlantic	(28.15,28.2]	4	cstar_tref ~ aou + nitrate + silicate + phosphate_star	1540	0.5623454	2609.3623	2.430575	1982-1999 –> 2000-2012	1.1578520	6627.2122
Atlantic	(28.15,28.2]	4	cstar_tref ~ sal + aou + nitrate + phosphate_star	1540	0.5939756	2777.9061	2.353787	1982-1999 –> 2000-2012	1.1267120	6300.3123
Atlantic	(28.15,28.2]	5	cstar_tref ~ sal + aou + nitrate + silicate + phosphate_star	1540	0.5471615	2527.0561	2.040783	1982-1999 –> 2000-2012	1.0648603	5924.1022
Atlantic	(28.15,28.2]	4	cstar_tref ~ temp + aou + nitrate + silicate	1540	0.5718023	2660.7281	2.192349	1982-1999 –> 2000-2012	1.1224532	6330.2485
Atlantic	(28.15,28.2]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	1540	0.5576121	2585.3284	2.314250	1982-1999 –> 2000-2012	1.1076613	6251.9858
Atlantic	(28.15,28.2]	4	cstar_tref ~ sal + aou + nitrate + phosphate_star	819	0.7431790	1850.0329	4.262643	2000-2012 –> 2013-2019	1.3371546	4627.9389
Atlantic	(28.15,28.2]	4	cstar_tref ~ sal + aou + nitrate + silicate	819	0.8257916	2022.6871	4.712442	2000-2012 –> 2013-2019	1.4632956	5018.4180
Atlantic	(28.15,28.2]	5	cstar_tref ~ sal + aou + nitrate + silicate + phosphate_star	819	0.7372762	1838.9708	4.731734	2000-2012 –> 2013-2019	1.2844377	4366.0269
Atlantic	(28.15,28.2]	4	cstar_tref ~ temp + aou + nitrate + silicate	819	0.8619250	2092.8357	8.363302	2000-2012 –> 2013-2019	1.4337273	4753.5638
Atlantic	(28.15,28.2]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	819	0.8613203	2093.6861	8.208278	2000-2012 –> 2013-2019	1.4189324	4679.0145
Atlantic	(28.2, Inf]	3	cstar_tref ~ sal + aou + nitrate	2693	0.3593168	2139.5581	1.966552	1982-1999 –> 2000-2012	0.6655852	3898.5165
Atlantic	(28.2, Inf]	4	cstar_tref ~ sal + aou + nitrate + phosphate_star	2693	0.3540505	2062.0339	1.937681	1982-1999 –> 2000-2012	0.6560011	3717.6111
Atlantic	(28.2, Inf]	4	cstar_tref ~ sal + aou + nitrate + silicate	2693	0.3588037	2133.8610	1.963165	1982-1999 –> 2000-2012	0.6635911	3858.8422
Atlantic	(28.2, Inf]	5	cstar_tref ~ sal + aou + nitrate + silicate + phosphate_star	2693	0.3463114	1944.9979	1.900529	1982-1999 –> 2000-2012	0.6453988	3531.8596
Atlantic	(28.2, Inf]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	2693	0.5306498	4243.5482	3.091584	1982-1999 –> 2000-2012	0.9896559	9009.4595
Atlantic	(28.2, Inf]	3	cstar_tref ~ sal + aou + nitrate	1557	0.4186021	1716.7958	2.479100	2000-2012 –> 2013-2019	0.7779188	3856.3538
Atlantic	(28.2, Inf]	4	cstar_tref ~ sal + aou + nitrate + phosphate_star	1557	0.3991609	1570.7062	2.411345	2000-2012 –> 2013-2019	0.7532114	3632.7401
Atlantic	(28.2, Inf]	4	cstar_tref ~ sal + aou + nitrate + silicate	1557	0.4110188	1661.8663	2.465092	2000-2012 –> 2013-2019	0.7698225	3795.7273
Atlantic	(28.2, Inf]	5	cstar_tref ~ sal + aou + nitrate + silicate + phosphate_star	1557	0.3901368	1501.4981	2.457959	2000-2012 –> 2013-2019	0.7364483	3446.4960
Atlantic	(28.2, Inf]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	1557	0.7057457	3347.3447	8.527267	2000-2012 –> 2013-2019	1.2363955	7590.8929
Indo-Pacific	(-Inf,26]	4	cstar_tref ~ sal + aou + phosphate + phosphate_star	5288	6.2360939	34376.5179	29.968567	1982-1999 –> 2000-2012	12.7656352	81794.3473
Indo-Pacific	(-Inf,26]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	5288	6.1928478	34304.9200	29.527354	1982-1999 –> 2000-2012	12.6716991	81612.6324
Indo-Pacific	(-Inf,26]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	5288	7.1987438	35896.7294	31.371808	1982-1999 –> 2000-2012	14.7271008	85364.2640
Indo-Pacific	(-Inf,26]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	5288	7.2933052	36034.7494	29.166512	1982-1999 –> 2000-2012	14.8774849	85608.5624
Indo-Pacific	(-Inf,26]	4	cstar_tref ~ temp + silicate + phosphate + phosphate_star	5288	7.3907730	36173.1511	28.492599	1982-1999 –> 2000-2012	15.1050761	85989.6943
Indo-Pacific	(-Inf,26]	4	cstar_tref ~ sal + aou + phosphate + phosphate_star	2816	5.9520247	18049.4373	24.894024	2000-2012 –> 2013-2019	12.1881186	52425.9552
Indo-Pacific	(-Inf,26]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	2816	5.8778725	17980.8313	24.128023	2000-2012 –> 2013-2019	12.0707203	52285.7513
Indo-Pacific	(-Inf,26]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	2816	6.9521542	18926.2002	25.907885	2000-2012 –> 2013-2019	14.1508980	54822.9297
Indo-Pacific	(-Inf,26]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	2816	7.0001768	18964.9700	25.465195	2000-2012 –> 2013-2019	14.2934820	54999.7194
Indo-Pacific	(-Inf,26]	4	cstar_tref ~ temp + silicate + phosphate + phosphate_star	2816	7.1344030	19069.9395	24.441528	2000-2012 –> 2013-2019	14.5251760	55243.0906
Indo-Pacific	(26,26.5]	4	cstar_tref ~ aou + silicate + phosphate + phosphate_star	5525	4.8905258	33230.9339	41.688307	1982-1999 –> 2000-2012	9.5377100	78823.9388
Indo-Pacific	(26,26.5]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	5525	4.5360650	32401.5327	43.772780	1982-1999 –> 2000-2012	8.7824377	76605.3494
Indo-Pacific	(26,26.5]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	5525	4.7555301	32923.6260	49.041150	1982-1999 –> 2000-2012	9.1671720	77716.3587
Indo-Pacific	(26,26.5]	4	cstar_tref ~ temp + aou + silicate + phosphate	5525	4.8893893	33228.3657	40.409229	1982-1999 –> 2000-2012	9.5091497	78730.0815
Indo-Pacific	(26,26.5]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	5525	4.8803203	33209.8508	41.154556	1982-1999 –> 2000-2012	9.4999894	78713.2617
Indo-Pacific	(26,26.5]	4	cstar_tref ~ aou + silicate + phosphate + phosphate_star	2918	4.8175903	17468.7156	40.382988	2000-2012 –> 2013-2019	9.7081161	50699.6495
Indo-Pacific	(26,26.5]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	2918	4.4724496	17036.8813	46.310491	2000-2012 –> 2013-2019	9.0085146	49438.4140
Indo-Pacific	(26,26.5]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	2918	4.5715543	17164.7889	45.715284	2000-2012 –> 2013-2019	9.3270844	50088.4149
Indo-Pacific	(26,26.5]	4	cstar_tref ~ temp + aou + silicate + phosphate	2918	4.8142859	17464.7112	37.043514	2000-2012 –> 2013-2019	9.7036752	50693.0769
Indo-Pacific	(26,26.5]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	2918	4.8065118	17457.2797	38.739984	2000-2012 –> 2013-2019	9.6868321	50667.1305
Indo-Pacific	(26.5,26.75]	4	cstar_tref ~ aou + silicate + phosphate + phosphate_star	4544	4.0473152	25612.8259	22.127132	1982-1999 –> 2000-2012	7.9963826	60742.2745
Indo-Pacific	(26.5,26.75]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	4544	3.9265162	25339.4488	20.226531	1982-1999 –> 2000-2012	7.6839109	59845.1956
Indo-Pacific	(26.5,26.75]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	4544	4.0218289	25557.4171	33.030413	1982-1999 –> 2000-2012	8.0127086	60821.3190
Indo-Pacific	(26.5,26.75]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	4544	3.9477481	25388.4579	23.151958	1982-1999 –> 2000-2012	7.8249401	60288.9073
Indo-Pacific	(26.5,26.75]	4	cstar_tref ~ temp + nitrate + silicate + phosphate_star	4544	4.0218809	25555.5345	32.963712	1982-1999 –> 2000-2012	8.0834114	61038.1226
Indo-Pacific	(26.5,26.75]	4	cstar_tref ~ aou + silicate + phosphate + phosphate_star	2447	4.4033896	14211.0265	24.538450	2000-2012 –> 2013-2019	8.4507048	39823.8524
Indo-Pacific	(26.5,26.75]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	2447	4.2938981	14089.7973	24.434470	2000-2012 –> 2013-2019	8.2204143	39429.2462
Indo-Pacific	(26.5,26.75]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	2447	4.3225383	14122.3318	31.664753	2000-2012 –> 2013-2019	8.3443672	39679.7489
Indo-Pacific	(26.5,26.75]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	2447	4.2923135	14087.9909	22.815590	2000-2012 –> 2013-2019	8.2400615	39476.4489
Indo-Pacific	(26.5,26.75]	4	cstar_tref ~ temp + nitrate + silicate + phosphate_star	2447	4.3388127	14138.7232	34.446250	2000-2012 –> 2013-2019	8.3606936	39694.2577
Indo-Pacific	(26.75,27]	4	cstar_tref ~ aou + silicate + phosphate + phosphate_star	5354	4.5232238	31366.7748	18.928405	1982-1999 –> 2000-2012	8.5202080	73619.8323
Indo-Pacific	(26.75,27]	4	cstar_tref ~ sal + aou + phosphate + phosphate_star	5354	4.3077986	30844.2463	21.980567	1982-1999 –> 2000-2012	7.9956057	71884.6902
Indo-Pacific	(26.75,27]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	5354	4.2906105	30803.4359	21.052395	1982-1999 –> 2000-2012	7.9645082	71788.9629
Indo-Pacific	(26.75,27]	4	cstar_tref ~ temp + aou + phosphate + phosphate_star	5354	4.2057274	30587.4712	23.104196	1982-1999 –> 2000-2012	7.8859232	71596.7963
Indo-Pacific	(26.75,27]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	5354	4.1702723	30498.8181	21.453131	1982-1999 –> 2000-2012	7.8227361	71396.2141
Indo-Pacific	(26.75,27]	4	cstar_tref ~ aou + silicate + phosphate + phosphate_star	2868	4.9018613	17269.0630	18.494849	2000-2012 –> 2013-2019	9.4250851	48635.8378
Indo-Pacific	(26.75,27]	4	cstar_tref ~ sal + aou + phosphate + phosphate_star	2868	4.6612052	16980.3073	20.095371	2000-2012 –> 2013-2019	8.9690038	47824.5536
Indo-Pacific	(26.75,27]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	2868	4.6499950	16968.4956	19.282213	2000-2012 –> 2013-2019	8.9406055	47771.9315
Indo-Pacific	(26.75,27]	4	cstar_tref ~ temp + aou + phosphate + phosphate_star	2868	4.5774010	16876.2410	16.522089	2000-2012 –> 2013-2019	8.7831284	47463.7121
Indo-Pacific	(26.75,27]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	2868	4.5537010	16848.4650	17.066955	2000-2012 –> 2013-2019	8.7239733	47347.2831
Indo-Pacific	(27,27.25]	4	cstar_tref ~ aou + silicate + phosphate + phosphate_star	6466	4.4389355	37635.7547	39.385070	1982-1999 –> 2000-2012	8.0900559	85614.5068
Indo-Pacific	(27,27.25]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	6466	4.3929768	37503.1646	41.945012	1982-1999 –> 2000-2012	7.9587117	85065.6810
Indo-Pacific	(27,27.25]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	6466	4.1535561	36778.4265	49.359080	1982-1999 –> 2000-2012	7.5202091	83325.5519
Indo-Pacific	(27,27.25]	4	cstar_tref ~ temp + aou + phosphate + phosphate_star	6466	4.3599345	37403.5276	46.003290	1982-1999 –> 2000-2012	7.9680032	85172.6402
Indo-Pacific	(27,27.25]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	6466	3.9500266	36128.6900	31.512269	1982-1999 –> 2000-2012	7.2528573	82337.5496
Indo-Pacific	(27,27.25]	4	cstar_tref ~ aou + silicate + phosphate + phosphate_star	3470	5.1328308	21210.8952	31.173698	2000-2012 –> 2013-2019	9.5717663	58846.6499
Indo-Pacific	(27,27.25]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	3470	5.0789520	21139.6617	33.597697	2000-2012 –> 2013-2019	9.4719288	58642.8263
Indo-Pacific	(27,27.25]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	3470	4.9716940	20991.5322	35.708885	2000-2012 –> 2013-2019	9.1252501	57769.9588
Indo-Pacific	(27,27.25]	4	cstar_tref ~ temp + aou + phosphate + phosphate_star	3470	5.1322261	21210.0776	39.784583	2000-2012 –> 2013-2019	9.4921606	58613.6052
Indo-Pacific	(27,27.25]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	3470	4.4723380	20256.9380	25.616236	2000-2012 –> 2013-2019	8.4223646	56385.6280
Indo-Pacific	(27.25,27.5]	5	cstar_tref ~ sal + aou + nitrate + silicate + phosphate_star	5847	3.4261572	31007.5182	32.305003	1982-1999 –> 2000-2012	6.3475428	70339.4077
Indo-Pacific	(27.25,27.5]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	5847	3.6920890	31881.6814	32.521736	1982-1999 –> 2000-2012	6.7625645	71999.2104
Indo-Pacific	(27.25,27.5]	4	cstar_tref ~ sal + aou + silicate + phosphate_star	5847	3.7105782	31938.0962	31.726047	1982-1999 –> 2000-2012	6.7817085	72056.9912
Indo-Pacific	(27.25,27.5]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	5847	3.6356816	31701.6427	32.976030	1982-1999 –> 2000-2012	6.7191704	71885.9262
Indo-Pacific	(27.25,27.5]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	5847	3.3461863	30731.3292	33.390589	1982-1999 –> 2000-2012	6.2704796	70078.9213
Indo-Pacific	(27.25,27.5]	5	cstar_tref ~ sal + aou + nitrate + silicate + phosphate_star	3127	3.9776245	17522.8442	31.036835	2000-2012 –> 2013-2019	7.4037817	48530.3624
Indo-Pacific	(27.25,27.5]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	3127	4.3037583	18015.6837	32.127293	2000-2012 –> 2013-2019	7.9958473	49897.3651
Indo-Pacific	(27.25,27.5]	4	cstar_tref ~ sal + aou + silicate + phosphate_star	3127	4.3425043	18069.7354	30.551097	2000-2012 –> 2013-2019	8.0530824	50007.8316
Indo-Pacific	(27.25,27.5]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	3127	4.2454019	17930.3030	31.035584	2000-2012 –> 2013-2019	7.8810835	49631.9457
Indo-Pacific	(27.25,27.5]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	3127	3.8437243	17308.6883	33.232474	2000-2012 –> 2013-2019	7.1899105	48040.0175
Indo-Pacific	(27.5,27.75]	5	cstar_tref ~ sal + aou + nitrate + silicate + phosphate_star	5836	3.2683124	30398.6938	24.119856	1982-1999 –> 2000-2012	5.5822735	67013.2424
Indo-Pacific	(27.5,27.75]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	5836	3.2280103	30253.8699	9.417658	1982-1999 –> 2000-2012	5.5715676	67074.4342
Indo-Pacific	(27.5,27.75]	4	cstar_tref ~ sal + aou + silicate + phosphate_star	5836	3.3807244	30791.3972	22.456992	1982-1999 –> 2000-2012	5.7423173	67734.2326
Indo-Pacific	(27.5,27.75]	4	cstar_tref ~ sal + nitrate + silicate + phosphate_star	5836	3.3957705	30843.2286	29.089521	1982-1999 –> 2000-2012	5.7808728	67946.6354
Indo-Pacific	(27.5,27.75]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	5836	3.3691828	30753.4813	15.287781	1982-1999 –> 2000-2012	5.8121319	68247.3438
Indo-Pacific	(27.5,27.75]	5	cstar_tref ~ sal + aou + nitrate + silicate + phosphate_star	3104	3.9417327	17337.7899	25.386634	2000-2012 –> 2013-2019	7.2100451	47736.4837
Indo-Pacific	(27.5,27.75]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	3104	3.7804110	17078.3721	11.020697	2000-2012 –> 2013-2019	7.0084214	47332.2420
Indo-Pacific	(27.5,27.75]	4	cstar_tref ~ sal + aou + silicate + phosphate_star	3104	4.0989818	17578.6356	23.944569	2000-2012 –> 2013-2019	7.4797062	48370.0328
Indo-Pacific	(27.5,27.75]	4	cstar_tref ~ sal + nitrate + silicate + phosphate_star	3104	4.1948886	17722.2154	32.318244	2000-2012 –> 2013-2019	7.5906591	48565.4440
Indo-Pacific	(27.5,27.75]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	3104	4.0127640	17448.6640	19.751773	2000-2012 –> 2013-2019	7.3819468	48202.1453
Indo-Pacific	(27.75,27.85]	4	cstar_tref ~ aou + silicate + phosphate + phosphate_star	2317	2.7304690	11242.0909	21.046900	1982-1999 –> 2000-2012	4.6623579	24262.9999
Indo-Pacific	(27.75,27.85]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	2317	2.7290365	11241.6591	21.325228	1982-1999 –> 2000-2012	4.6507603	24231.5321
Indo-Pacific	(27.75,27.85]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	2317	2.7271269	11238.4154	21.453348	1982-1999 –> 2000-2012	4.6635446	24275.9866
Indo-Pacific	(27.75,27.85]	4	cstar_tref ~ temp + aou + silicate + phosphate	2317	2.7417874	11261.2601	20.642191	1982-1999 –> 2000-2012	4.6870749	24325.4494
Indo-Pacific	(27.75,27.85]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	2317	2.6406178	11089.0349	20.968772	1982-1999 –> 2000-2012	4.5482001	24032.6569
Indo-Pacific	(27.75,27.85]	5	cstar_tref ~ sal + aou + nitrate + silicate + phosphate_star	1264	3.1358059	6490.2930	31.989646	2000-2012 –> 2013-2019	5.8629052	17728.6613
Indo-Pacific	(27.75,27.85]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	1264	3.1693826	6517.2176	30.950746	2000-2012 –> 2013-2019	5.8984191	17758.8767
Indo-Pacific	(27.75,27.85]	4	cstar_tref ~ sal + nitrate + silicate + phosphate_star	1264	3.1488202	6498.7630	29.448400	2000-2012 –> 2013-2019	5.8762396	17735.6753
Indo-Pacific	(27.75,27.85]	4	cstar_tref ~ temp + aou + phosphate + phosphate_star	1264	3.1128492	6469.7178	31.766441	2000-2012 –> 2013-2019	5.8536894	17729.3767
Indo-Pacific	(27.75,27.85]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	1264	3.0665742	6433.8549	28.861392	2000-2012 –> 2013-2019	5.7071919	17522.8898
Indo-Pacific	(27.85,27.95]	4	cstar_tref ~ temp + aou + nitrate + phosphate_star	2907	2.7487099	14140.4282	28.492785	1982-1999 –> 2000-2012	4.8701028	31563.9400
Indo-Pacific	(27.85,27.95]	4	cstar_tref ~ temp + aou + nitrate + silicate	2907	2.7484328	14139.8421	28.396374	1982-1999 –> 2000-2012	4.9240749	31765.8662
Indo-Pacific	(27.85,27.95]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	2907	2.7457460	14136.1557	28.208152	1982-1999 –> 2000-2012	4.8664196	31558.9474
Indo-Pacific	(27.85,27.95]	3	cstar_tref ~ temp + nitrate + phosphate_star	2907	2.7674113	14177.8510	31.750508	1982-1999 –> 2000-2012	4.8898936	31603.4801
Indo-Pacific	(27.85,27.95]	4	cstar_tref ~ temp + nitrate + silicate + phosphate_star	2907	2.7621671	14168.8231	31.138313	1982-1999 –> 2000-2012	4.8840444	31594.1657
Indo-Pacific	(27.85,27.95]	4	cstar_tref ~ temp + aou + nitrate + silicate	1542	3.3046795	8074.4335	31.424170	2000-2012 –> 2013-2019	6.0531124	22214.2756
Indo-Pacific	(27.85,27.95]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	1542	3.2946985	8067.1049	31.554855	2000-2012 –> 2013-2019	6.0404446	22203.2606
Indo-Pacific	(27.85,27.95]	4	cstar_tref ~ temp + aou + phosphate + phosphate_star	1542	3.2669990	8039.0671	37.333823	2000-2012 –> 2013-2019	6.0608699	22274.2424
Indo-Pacific	(27.85,27.95]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	1542	3.2637446	8037.9935	37.426960	2000-2012 –> 2013-2019	6.0494318	22258.1136
Indo-Pacific	(27.85,27.95]	4	cstar_tref ~ temp + nitrate + silicate + phosphate_star	1542	3.2965108	8066.8008	32.540164	2000-2012 –> 2013-2019	6.0586779	22235.6239
Indo-Pacific	(27.95,28.05]	4	cstar_tref ~ aou + silicate + phosphate + phosphate_star	2467	2.2624239	11041.3418	8.237248	1982-1999 –> 2000-2012	4.1845877	25738.2975
Indo-Pacific	(27.95,28.05]	5	cstar_tref ~ sal + aou + nitrate + silicate + phosphate_star	2467	2.1936153	10890.9515	8.036190	1982-1999 –> 2000-2012	4.1649943	25769.0539
Indo-Pacific	(27.95,28.05]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	2467	2.2115502	10931.1275	8.468880	1982-1999 –> 2000-2012	4.1022689	25513.2034
Indo-Pacific	(27.95,28.05]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	2467	2.2668883	11053.0683	8.062293	1982-1999 –> 2000-2012	4.2018862	25799.1794
Indo-Pacific	(27.95,28.05]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	2467	2.1886299	10879.7253	7.878228	1982-1999 –> 2000-2012	4.0642895	25405.1370
Indo-Pacific	(27.95,28.05]	4	cstar_tref ~ sal + aou + nitrate + phosphate_star	1354	2.4060015	6232.0181	8.104133	2000-2012 –> 2013-2019	4.6173063	17160.5981
Indo-Pacific	(27.95,28.05]	5	cstar_tref ~ sal + aou + nitrate + silicate + phosphate_star	1354	2.4007452	6228.0956	8.259744	2000-2012 –> 2013-2019	4.5943605	17119.0470
Indo-Pacific	(27.95,28.05]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	1354	2.4779038	6313.7598	8.329809	2000-2012 –> 2013-2019	4.6894540	17244.8873
Indo-Pacific	(27.95,28.05]	4	cstar_tref ~ temp + aou + phosphate + phosphate_star	1354	2.4648617	6297.4690	8.721893	2000-2012 –> 2013-2019	4.7165003	17315.2334
Indo-Pacific	(27.95,28.05]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	1354	2.4266912	6257.2052	8.523746	2000-2012 –> 2013-2019	4.6153211	17136.9304
Indo-Pacific	(28.05,28.1]	4	cstar_tref ~ aou + silicate + phosphate + phosphate_star	1718	1.8848420	7065.3607	9.810959	1982-1999 –> 2000-2012	3.5844089	17034.4465
Indo-Pacific	(28.05,28.1]	4	cstar_tref ~ sal + aou + silicate + phosphate	1718	1.9503440	7182.7407	8.816710	1982-1999 –> 2000-2012	3.5709134	16908.7065
Indo-Pacific	(28.05,28.1]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	1718	1.8450332	6994.0133	9.467590	1982-1999 –> 2000-2012	3.4414783	16645.3685
Indo-Pacific	(28.05,28.1]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	1718	1.8612616	7024.1034	10.244079	1982-1999 –> 2000-2012	3.4707315	16716.9636
Indo-Pacific	(28.05,28.1]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	1718	1.8032691	6915.3424	9.697645	1982-1999 –> 2000-2012	3.4298781	16662.3098
Indo-Pacific	(28.05,28.1]	4	cstar_tref ~ aou + silicate + phosphate + phosphate_star	966	2.1066397	4192.9110	9.987464	2000-2012 –> 2013-2019	3.9914816	11258.2717
Indo-Pacific	(28.05,28.1]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	966	2.0390556	4131.9137	9.747515	2000-2012 –> 2013-2019	3.8840888	11125.9270
Indo-Pacific	(28.05,28.1]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	966	2.0868098	4176.6389	10.548800	2000-2012 –> 2013-2019	3.9480714	11200.7423
Indo-Pacific	(28.05,28.1]	4	cstar_tref ~ temp + aou + silicate + phosphate	966	2.1188554	4204.0818	10.037184	2000-2012 –> 2013-2019	4.0138656	11287.9289
Indo-Pacific	(28.05,28.1]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	966	2.0001288	4094.6740	9.111786	2000-2012 –> 2013-2019	3.8033978	11010.0164
Indo-Pacific	(28.1, Inf]	4	cstar_tref ~ sal + aou + silicate + phosphate	14627	1.4320006	52025.9353	13.806990	1982-1999 –> 2000-2012	2.7088012	119684.1812
Indo-Pacific	(28.1, Inf]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	14627	1.3378772	50039.0036	16.225048	1982-1999 –> 2000-2012	2.5090135	114186.0580
Indo-Pacific	(28.1, Inf]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	14627	1.3692488	50717.0570	13.004762	1982-1999 –> 2000-2012	2.4951048	113260.4541
Indo-Pacific	(28.1, Inf]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	14627	1.3940533	51242.2624	17.034744	1982-1999 –> 2000-2012	2.6340769	117713.8450
Indo-Pacific	(28.1, Inf]	4	cstar_tref ~ temp + nitrate + silicate + phosphate_star	14627	1.5669226	54659.9964	17.476131	1982-1999 –> 2000-2012	2.8961915	123956.0907
Indo-Pacific	(28.1, Inf]	5	cstar_tref ~ sal + aou + nitrate + silicate + phosphate_star	7804	1.6305548	29791.8606	9.567306	2000-2012 –> 2013-2019	3.1514890	83582.4147
Indo-Pacific	(28.1, Inf]	4	cstar_tref ~ sal + aou + silicate + phosphate	7804	1.5693631	29192.8476	10.689506	2000-2012 –> 2013-2019	3.0013637	81218.7829
Indo-Pacific	(28.1, Inf]	5	cstar_tref ~ sal + aou + silicate + phosphate + phosphate_star	7804	1.4923380	28409.3615	12.644005	2000-2012 –> 2013-2019	2.8302151	78448.3652
Indo-Pacific	(28.1, Inf]	5	cstar_tref ~ temp + aou + nitrate + silicate + phosphate_star	7804	1.5858456	29357.9189	10.996188	2000-2012 –> 2013-2019	2.9550945	80074.9759
Indo-Pacific	(28.1, Inf]	5	cstar_tref ~ temp + aou + silicate + phosphate + phosphate_star	7804	1.5521124	29022.3323	13.774789	2000-2012 –> 2013-2019	2.9461657	80264.5947

5.3.2 per fitting unit

lm_best %>%
  select(-n_predictors) %>%
  group_by(basin, gamma_slab, eras) %>% 
  summarise(rmse_sum_mean = mean(rmse_sum),
            ais_sum_mean = mean(aic_sum)) %>% 
  ungroup() %>% 
  kable() %>%
  add_header_above() %>%
  kable_styling() %>%
  scroll_box(width = "100%", height = "400px")

basin	gamma_slab	eras	rmse_sum_mean	ais_sum_mean
Atlantic	(-Inf,26]	1982-1999 –> 2000-2012	2.8582070	1324.4715
Atlantic	(-Inf,26]	2000-2012 –> 2013-2019	2.7677442	814.2323
Atlantic	(26,26.5]	1982-1999 –> 2000-2012	8.0246884	14451.4983
Atlantic	(26,26.5]	2000-2012 –> 2013-2019	7.9609365	9064.3843
Atlantic	(26.5,27.25]	1982-1999 –> 2000-2012	5.9057007	67019.5388
Atlantic	(26.5,27.25]	2000-2012 –> 2013-2019	6.7506703	46467.8040
Atlantic	(27.25,27.5]	1982-1999 –> 2000-2012	4.6172390	21904.0994
Atlantic	(27.25,27.5]	2000-2012 –> 2013-2019	5.4190031	14976.9668
Atlantic	(27.5,27.75]	1982-1999 –> 2000-2012	5.0217940	30399.0145
Atlantic	(27.5,27.75]	2000-2012 –> 2013-2019	5.7879021	21193.7410
Atlantic	(27.75,27.85]	1982-1999 –> 2000-2012	3.6297437	9500.8720
Atlantic	(27.75,27.85]	2000-2012 –> 2013-2019	3.8350219	6367.6723
Atlantic	(27.85,27.95]	1982-1999 –> 2000-2012	6.1178323	11720.3375
Atlantic	(27.85,27.95]	2000-2012 –> 2013-2019	6.8545716	8214.9660
Atlantic	(27.95,28.05]	1982-1999 –> 2000-2012	8.7229036	16658.8878
Atlantic	(27.95,28.05]	2000-2012 –> 2013-2019	8.4059569	10721.4936
Atlantic	(28.05,28.1]	1982-1999 –> 2000-2012	1.9842574	5263.7708
Atlantic	(28.05,28.1]	2000-2012 –> 2013-2019	2.1958208	3753.6191
Atlantic	(28.1,28.15]	1982-1999 –> 2000-2012	1.4613609	4853.7233
Atlantic	(28.1,28.15]	2000-2012 –> 2013-2019	1.7131888	3585.6454
Atlantic	(28.15,28.2]	1982-1999 –> 2000-2012	1.1159078	6286.7722
Atlantic	(28.15,28.2]	2000-2012 –> 2013-2019	1.3875095	4688.9924
Atlantic	(28.2, Inf]	1982-1999 –> 2000-2012	0.7240464	4803.2578
Atlantic	(28.2, Inf]	2000-2012 –> 2013-2019	0.8547593	4464.4420
Indo-Pacific	(-Inf,26]	1982-1999 –> 2000-2012	14.0293992	84073.9001
Indo-Pacific	(-Inf,26]	2000-2012 –> 2013-2019	13.4456790	53955.4892
Indo-Pacific	(26,26.5]	1982-1999 –> 2000-2012	9.2992918	78117.7980
Indo-Pacific	(26,26.5]	2000-2012 –> 2013-2019	9.4868445	50317.3372
Indo-Pacific	(26.5,26.75]	1982-1999 –> 2000-2012	7.9202707	60547.1638
Indo-Pacific	(26.5,26.75]	2000-2012 –> 2013-2019	8.3232483	39620.7108
Indo-Pacific	(26.75,27]	1982-1999 –> 2000-2012	8.0377962	72057.2992
Indo-Pacific	(26.75,27]	2000-2012 –> 2013-2019	8.9683592	47808.6636
Indo-Pacific	(27,27.25]	1982-1999 –> 2000-2012	7.7579674	84303.1859
Indo-Pacific	(27,27.25]	2000-2012 –> 2013-2019	9.2166941	58051.7336
Indo-Pacific	(27.25,27.5]	1982-1999 –> 2000-2012	6.5762932	71272.0914
Indo-Pacific	(27.25,27.5]	2000-2012 –> 2013-2019	7.7047411	49221.5045
Indo-Pacific	(27.5,27.75]	1982-1999 –> 2000-2012	5.6978326	67603.1777
Indo-Pacific	(27.5,27.75]	2000-2012 –> 2013-2019	7.3341557	48041.2696
Indo-Pacific	(27.75,27.85]	1982-1999 –> 2000-2012	4.6423876	24225.7250
Indo-Pacific	(27.75,27.85]	2000-2012 –> 2013-2019	5.8396890	17695.0960
Indo-Pacific	(27.85,27.95]	1982-1999 –> 2000-2012	4.8869071	31617.2799
Indo-Pacific	(27.85,27.95]	2000-2012 –> 2013-2019	6.0525073	22237.1032
Indo-Pacific	(27.95,28.05]	1982-1999 –> 2000-2012	4.1436053	25644.9742
Indo-Pacific	(27.95,28.05]	2000-2012 –> 2013-2019	4.6465884	17195.3393
Indo-Pacific	(28.05,28.1]	1982-1999 –> 2000-2012	3.4994821	16793.5590
Indo-Pacific	(28.05,28.1]	2000-2012 –> 2013-2019	3.9281810	11176.5773
Indo-Pacific	(28.1, Inf]	1982-1999 –> 2000-2012	2.6486376	117760.1258
Indo-Pacific	(28.1, Inf]	2000-2012 –> 2013-2019	2.9768656	80717.8267

5.4 Target variable coefficients

A data frame to map the target variable is prepared.

# create table with two era belonging to one eras
eras_forward <- lm_all_fitted_wide %>%
  arrange(era) %>% 
  group_by(basin, gamma_slab, model) %>% 
  mutate(eras = paste(era, lead(era), sep = " --> ")) %>% 
  ungroup() %>% 
  select(era, eras) %>% 
  unique()

eras_backward <- lm_all_fitted_wide %>%
  arrange(era) %>% 
  group_by(basin, gamma_slab, model) %>% 
  mutate(eras = paste(lag(era), era, sep = " --> ")) %>% 
  ungroup() %>% 
  select(era, eras) %>% 
  unique()

eras_era <- full_join(eras_backward, eras_forward) %>% 
  filter(str_detect(eras, "NA") == FALSE)

# extend best model selection from eras to era
lm_best_target <- full_join(
  lm_best %>% select(basin, gamma_slab, model, eras),
  eras_era)

lm_best_target <- left_join(lm_best_target, lm_all_fitted_wide)

rm(eras_era, eras_forward, eras_backward,
   lm_all_fitted)

5.5 Plot selected model residuals

# plot model diagnostics, if activated
if (params_local$plot_all_figures == "y") {
  # mutate predictors column
  lm_best_plot <- lm_best_target %>%
    select(basin, gamma_slab, model, eras, era) %>%
    mutate(
      predictors = str_remove(model, paste(params_local$MLR_target, "~ ")),
      predictors = str_replace_all(predictors, "\\+ ", "")
    )
  
  # loop across all basins, era, gamma slabs, and MLRs
  # fit all MLR models
  for (i_basin in unique(GLODAP$basin)) {
    for (i_era in unique(GLODAP$era)) {
      #i_basin <- unique(GLODAP$basin)[1]
      #i_era   <- unique(GLODAP$era)[2]
      print(i_basin)
      print(i_era)
      
      GLODAP_basin_era <- GLODAP %>%
        filter(basin == i_basin, era == i_era)
      
      for (i_gamma_slab in unique(GLODAP_basin_era$gamma_slab)) {
        #i_gamma_slab <- unique(GLODAP_basin_era$gamma_slab)[1]
        print(i_gamma_slab)
        
        GLODAP_basin_era_slab <- GLODAP_basin_era %>%
          filter(gamma_slab == i_gamma_slab)
        
        lm_best_basin_era_slab <- lm_best_plot %>%
          filter(basin == i_basin, era == i_era, gamma_slab == i_gamma_slab)
        
        for (i_eras in unique(lm_best_basin_era_slab$eras)) {
          #i_eras <- unique(lm_best_basin_era_slab$eras)[1]
          print(i_eras)
          
          lm_best_basin_era_slab_eras <- lm_best_basin_era_slab %>%
            filter(eras == i_eras)
          
          for (i_predictors in unique(lm_best_basin_era_slab_eras$predictors)) {
            #i_predictors <- unique(lm_best_basin_era_slab$predictors)[1]
            print(i_predictors)
            # extract one model definition
            i_lm <- lm_all %>%
              filter(predictors == i_predictors) %>%
              select(lm_coeff) %>%
              pull()
            
             # fit model
          if (params_local$MLR_type == "rlm") {
            i_lm_fit <- MASS::rlm(as.formula(i_lm),
                                  data = GLODAP_basin_era_slab)
          }
          
          if (params_local$MLR_type == "lm") {
            i_lm_fit <- lm(as.formula(i_lm),
                           data = GLODAP_basin_era_slab)
          }
            
            # plot model diagnostics vs predictors
            
            p_model_predictors <- ggnostic(
              i_lm_fit,
              columnsY = c(params_local$MLR_target, ".fitted", ".resid"),
              title = paste(
                "era:",
                i_era,
                "| eras:",
                i_eras,
                "| basin:",
                i_basin,
                "| gamma slab:",
                i_gamma_slab,
                "| predictors:",
                i_predictors
              )
            )
            
            ggsave(
              plot = p_model_predictors,
              path = paste(path_version_figures, "eMLR_diagnostics/", sep = ""),
              filename = paste(
                "MLR_residuals",
                i_era,
                i_eras,
                i_basin,
                i_gamma_slab,
                i_predictors,
                "predictors.png",
                sep = "_"
              ),
              width = 14,
              height = 8
            )

            rm(p_model_predictors)
            
            
            # plot model diagnostics vs location
            
            GLODAP_basin_era_slab <- GLODAP_basin_era_slab %>%
              mutate(fitted = i_lm_fit$fitted.values,
                     residuals = i_lm_fit$residuals)
            
            GLODAP_basin_era_slab_long <- GLODAP_basin_era_slab %>% 
              pivot_longer(cols = c(params_local$MLR_target , fitted, residuals),
                           names_to = "estimate",
                           values_to = "value"
              ) %>% 
              pivot_longer(cols = c(lat, lon, depth),
                           names_to = "coordinate_type",
                           values_to = "coordinate_value"
              )

             p_model_coordinate <- GLODAP_basin_era_slab_long %>%
              ggplot(aes(coordinate_value, value)) +
              geom_bin2d() +
              scale_fill_viridis_c() +
              labs(
                title = paste(
                  "era:",
                  i_era,
                  "| eras:",
                  i_eras,
                  "| basin:",
                  i_basin,
                  "| gamma slab:",
                  i_gamma_slab,
                  "| predictors:",
                  i_predictors
                )
              ) +
              facet_grid(estimate~coordinate_type,
                         scales = "free")

            ggsave(
              plot = p_model_coordinate,
              path = paste(path_version_figures, "eMLR_diagnostics", sep = ""),
              filename = paste(
                "Location_MLR_residuals",
                i_era,
                i_eras,
                i_basin,
                i_gamma_slab,
                i_predictors,
                "predictors.png",
                sep = "_"
              ),
              width = 14,
              height = 8
            )

            rm(p_model_coordinate)
            
          }
          
        }
        
      }
    }
  }
  
  rm(
    lm_best_plot,
    lm_best_basin_era_slab,
    i_rmse,
    GLODAP_basin_era,
    GLODAP_basin_era_slab,
    i_lm,
    lm_all_fitted,
    i_basin,
    i_era,
    i_gamma_slab,
    i_predictors,
    lm_all,
    i_aic,
    i_n_predictors,
    i_resid_max
  )
  
}

Individual residual plots of the MLR models for each basin, era, eras and neutral density (gamma) slab are available at:

/nfs/kryo/work/jenmueller/emlr_cant/model/v_XXX/figures/eMLR_diagnostics/

5.6 Cant coeffcients

A data frame of coefficient offsets is prepared to facilitate the direct mapping of Cant.

# pivot long format
lm_best_long <- lm_best_target %>%
  pivot_longer(cols = starts_with("coeff_"),
               names_to = "term",
               values_to = "estimate",
               names_prefix = "coeff_")

# subtract coefficients of adjacent era
lm_best_long <- lm_best_long %>%
  arrange(era) %>%
  group_by(basin, gamma_slab, eras, model, term) %>%
  mutate(delta_coeff = estimate - lag(estimate)) %>%
  ungroup() %>%
  arrange(basin, gamma_slab, model, term, eras) %>%
  drop_na() %>%
  select(-c(era,estimate))

# pivot back to wide format
lm_best_cant <- lm_best_long %>%
  pivot_wider(values_from = delta_coeff,
              names_from = term,
              names_prefix = "delta_coeff_",
              values_fill = 0)

5.7 Write files

lm_best_target %>%
  select(
    basin,
    gamma_slab,
    model,
    eras,
    era,
    starts_with("coeff_")
  ) %>%
  write_csv(paste(path_version_data,
                  "lm_best_target.csv",
                  sep = ""))

lm_best_cant %>%
  select(
    basin,
    gamma_slab,
    model,
    eras,
    starts_with("delta_coeff_")
  ) %>%
  write_csv(paste(path_version_data,
                  "lm_best_cant.csv",
                  sep = ""))

lm_best %>%
  write_csv(paste(path_version_data,
                  "lm_best.csv",
                  sep = ""))

6 Model diagnotics

6.1 Selection criterion vs predictors

The selection criterion (rmse) was plotted against the number of predictors (limited to 2 - 9).

6.1.1 All models

lm_all_fitted_wide %>%
  ggplot(aes(as.factor(n_predictors),
             !!sym(params_local$MLR_criterion),
             col = basin)) +
  geom_hline(yintercept = 10) +
  geom_boxplot() +
  facet_grid(gamma_slab~era) +
  scale_color_brewer(palette = "Set1") +
  labs(x="Number of predictors")

Past versions of eMLR_predictor_model_quality_all-1.png

Version	Author	Date
9d5a62c	Donghe-Zhu	2021-03-10
5d1e70b	Donghe-Zhu	2021-03-10
2093979	Donghe-Zhu	2021-03-10
b865899	Donghe-Zhu	2021-03-10
cc2a956	Donghe-Zhu	2021-03-10
60689fb	Donghe-Zhu	2021-03-10
dba33c8	Donghe-Zhu	2021-03-09
17f1c4a	Donghe-Zhu	2021-03-09
c024d1a	Donghe-Zhu	2021-03-09
02f7242	Donghe-Zhu	2021-03-09
6f50bc6	Donghe-Zhu	2021-03-09
1691156	Donghe-Zhu	2021-03-08
c0ceaf8	Donghe-Zhu	2021-03-08
058e0a1	Donghe-Zhu	2021-03-08
112dea0	Donghe-Zhu	2021-03-08
1843412	Donghe-Zhu	2021-03-08
3fbbfa4	Donghe-Zhu	2021-03-07
627c8fb	Donghe-Zhu	2021-03-07
9ef3222	Donghe-Zhu	2021-03-05
8c1e978	Donghe-Zhu	2021-03-05
865f68c	Donghe-Zhu	2021-03-05
ee69bc1	Donghe-Zhu	2021-03-05
a79291f	Donghe-Zhu	2021-03-05
e8c6f30	Donghe-Zhu	2021-03-04
59288fe	Donghe-Zhu	2021-03-04
731abc8	Donghe-Zhu	2021-03-04
e2a5a33	Donghe-Zhu	2021-03-04
c7892c1	Donghe-Zhu	2021-03-04
924430b	Donghe-Zhu	2021-03-03
0d0bca1	Donghe-Zhu	2021-03-03
cb63c16	Donghe-Zhu	2021-03-03
ffda45a	Donghe-Zhu	2021-03-03
691ba81	Donghe-Zhu	2021-03-03
c5e45a2	Donghe-Zhu	2021-03-03
89c3e58	Donghe-Zhu	2021-03-03
c911669	Donghe-Zhu	2021-03-03
b71c719	Donghe-Zhu	2021-03-01
13666ca	Donghe-Zhu	2021-03-01
c6e60fe	Donghe-Zhu	2021-03-01
7a388f7	Donghe-Zhu	2021-03-01
799e913	Donghe-Zhu	2021-03-01
66ff99f	Donghe-Zhu	2021-03-01
ac9bb7a	Donghe-Zhu	2021-02-28
efdc047	Donghe-Zhu	2021-02-28
e9a7418	Donghe-Zhu	2021-02-28
e152917	Donghe-Zhu	2021-02-28
287123c	Donghe-Zhu	2021-02-27
54d5b5b	Donghe-Zhu	2021-02-27
330f064	Donghe-Zhu	2021-02-27
adbc9bc	Donghe-Zhu	2021-02-27
5937141	Donghe-Zhu	2021-02-27
4414bbf	Donghe-Zhu	2021-02-27
a265efb	Donghe-Zhu	2021-02-27
19edd1e	Donghe-Zhu	2021-02-27
f20483f	Donghe-Zhu	2021-02-26
6a2c7b3	Donghe-Zhu	2021-02-25
02b976d	Donghe-Zhu	2021-02-24
354c224	Donghe-Zhu	2021-02-24
1a0a88a	Donghe-Zhu	2021-02-24
57f701e	Donghe-Zhu	2021-02-24
06f3149	Donghe-Zhu	2021-02-16
401eab3	Donghe-Zhu	2021-02-15
e3bba84	Donghe-Zhu	2021-02-15
5dce4b1	Donghe-Zhu	2021-02-15
4469a0c	Donghe-Zhu	2021-02-13
5ae6a69	Donghe-Zhu	2021-02-10
05385dc	Donghe-Zhu	2021-02-10
f791ae4	Donghe-Zhu	2021-02-09
f71ae34	Donghe-Zhu	2021-02-09
c011832	Donghe-Zhu	2021-02-09
a145fa7	Donghe-Zhu	2021-02-09
c344e42	Donghe-Zhu	2021-02-08
2f095d7	Donghe-Zhu	2021-02-07
1fad5f1	Donghe-Zhu	2021-02-07
ca03c39	Donghe-Zhu	2021-02-07
cd7c52c	Donghe-Zhu	2021-02-04
bcf84f4	Donghe-Zhu	2021-02-02
a518739	Donghe-Zhu	2021-02-01
61666de	Donghe-Zhu	2021-01-31
865b582	Donghe-Zhu	2021-01-31
3e68089	Donghe-Zhu	2021-01-31
ecf335c	Donghe-Zhu	2021-01-31
a618965	Donghe-Zhu	2021-01-31
59e006e	Donghe-Zhu	2021-01-31
a1c8f87	Donghe-Zhu	2021-01-31
ae5c18f	Donghe-Zhu	2021-01-31
b50fe52	Donghe-Zhu	2021-01-31
ac99ae5	jens-daniel-mueller	2021-01-29
b5bdcaf	Donghe-Zhu	2021-01-29
442010d	Donghe-Zhu	2021-01-29
372adf5	Donghe-Zhu	2021-01-29
af8788e	Donghe-Zhu	2021-01-29
21c91c9	Donghe-Zhu	2021-01-29
eded038	Donghe-Zhu	2021-01-29
541d4dd	Donghe-Zhu	2021-01-29
6a75576	Donghe-Zhu	2021-01-28
16fba40	Donghe-Zhu	2021-01-28
12bc567	Donghe-Zhu	2021-01-27
ceed31b	Donghe-Zhu	2021-01-27
342402d	Donghe-Zhu	2021-01-27
5bad5c2	Donghe-Zhu	2021-01-27
61efb56	Donghe-Zhu	2021-01-25
48f638e	Donghe-Zhu	2021-01-25
c1cec47	Donghe-Zhu	2021-01-25
05ffb0c	Donghe-Zhu	2021-01-25
8b97165	Donghe-Zhu	2021-01-25
c569946	Donghe-Zhu	2021-01-24
a2f0d56	Donghe-Zhu	2021-01-23
28509fc	Donghe-Zhu	2021-01-23
4c28e4a	Donghe-Zhu	2021-01-22
24cc264	jens-daniel-mueller	2021-01-22
7891955	Donghe-Zhu	2021-01-21
d4cf1cb	Donghe-Zhu	2021-01-21
1f3e5b6	jens-daniel-mueller	2021-01-20
0e7bdf1	jens-daniel-mueller	2021-01-15
4571843	jens-daniel-mueller	2021-01-14
b3564aa	jens-daniel-mueller	2021-01-14
8d032c3	jens-daniel-mueller	2021-01-14
17dee1d	jens-daniel-mueller	2021-01-13
7cdea0c	jens-daniel-mueller	2021-01-06
fa85b93	jens-daniel-mueller	2021-01-06
e5cb81a	Donghe-Zhu	2021-01-05
a499f10	Donghe-Zhu	2021-01-05
fb8a752	Donghe-Zhu	2020-12-23
8fae0b2	Donghe-Zhu	2020-12-21
c8b76b3	jens-daniel-mueller	2020-12-19

6.1.2 Best models

lm_best_target %>%
  ggplot(aes("",
             !!sym(params_local$MLR_criterion),
             col = basin)) +
  geom_hline(yintercept = 10) +
  geom_boxplot() +
  facet_grid(gamma_slab~era) +
  scale_color_brewer(palette = "Set1") +
  labs(x="Number of predictors pooled")

Past versions of eMLR_predictor_model_quality_best-1.png

Version	Author	Date
fd528ed	Donghe-Zhu	2021-03-10
9d5a62c	Donghe-Zhu	2021-03-10
5d1e70b	Donghe-Zhu	2021-03-10
2093979	Donghe-Zhu	2021-03-10
b865899	Donghe-Zhu	2021-03-10
cc2a956	Donghe-Zhu	2021-03-10
60689fb	Donghe-Zhu	2021-03-10
dba33c8	Donghe-Zhu	2021-03-09
17f1c4a	Donghe-Zhu	2021-03-09
c024d1a	Donghe-Zhu	2021-03-09
02f7242	Donghe-Zhu	2021-03-09
6f50bc6	Donghe-Zhu	2021-03-09
1691156	Donghe-Zhu	2021-03-08
c0ceaf8	Donghe-Zhu	2021-03-08
058e0a1	Donghe-Zhu	2021-03-08
112dea0	Donghe-Zhu	2021-03-08
1843412	Donghe-Zhu	2021-03-08
3fbbfa4	Donghe-Zhu	2021-03-07
627c8fb	Donghe-Zhu	2021-03-07
9ef3222	Donghe-Zhu	2021-03-05
8c1e978	Donghe-Zhu	2021-03-05
865f68c	Donghe-Zhu	2021-03-05
ee69bc1	Donghe-Zhu	2021-03-05
a79291f	Donghe-Zhu	2021-03-05
e8c6f30	Donghe-Zhu	2021-03-04
59288fe	Donghe-Zhu	2021-03-04
731abc8	Donghe-Zhu	2021-03-04
e2a5a33	Donghe-Zhu	2021-03-04
c7892c1	Donghe-Zhu	2021-03-04
924430b	Donghe-Zhu	2021-03-03
0d0bca1	Donghe-Zhu	2021-03-03
cb63c16	Donghe-Zhu	2021-03-03
ffda45a	Donghe-Zhu	2021-03-03
691ba81	Donghe-Zhu	2021-03-03
c5e45a2	Donghe-Zhu	2021-03-03
89c3e58	Donghe-Zhu	2021-03-03
c407a50	Donghe-Zhu	2021-03-03
c911669	Donghe-Zhu	2021-03-03
b71c719	Donghe-Zhu	2021-03-01
13666ca	Donghe-Zhu	2021-03-01
c6e60fe	Donghe-Zhu	2021-03-01
7a388f7	Donghe-Zhu	2021-03-01
799e913	Donghe-Zhu	2021-03-01
66ff99f	Donghe-Zhu	2021-03-01
ac9bb7a	Donghe-Zhu	2021-02-28
efdc047	Donghe-Zhu	2021-02-28
e9a7418	Donghe-Zhu	2021-02-28
e152917	Donghe-Zhu	2021-02-28
287123c	Donghe-Zhu	2021-02-27
54d5b5b	Donghe-Zhu	2021-02-27
330f064	Donghe-Zhu	2021-02-27
adbc9bc	Donghe-Zhu	2021-02-27
5937141	Donghe-Zhu	2021-02-27
4414bbf	Donghe-Zhu	2021-02-27
a265efb	Donghe-Zhu	2021-02-27
19edd1e	Donghe-Zhu	2021-02-27
f20483f	Donghe-Zhu	2021-02-26
6a2c7b3	Donghe-Zhu	2021-02-25
354c224	Donghe-Zhu	2021-02-24
1a0a88a	Donghe-Zhu	2021-02-24
57f701e	Donghe-Zhu	2021-02-24
06f3149	Donghe-Zhu	2021-02-16
401eab3	Donghe-Zhu	2021-02-15
e3bba84	Donghe-Zhu	2021-02-15
5dce4b1	Donghe-Zhu	2021-02-15
4469a0c	Donghe-Zhu	2021-02-13
5ae6a69	Donghe-Zhu	2021-02-10
05385dc	Donghe-Zhu	2021-02-10
f791ae4	Donghe-Zhu	2021-02-09
f71ae34	Donghe-Zhu	2021-02-09
c011832	Donghe-Zhu	2021-02-09
a145fa7	Donghe-Zhu	2021-02-09
c344e42	Donghe-Zhu	2021-02-08
2f095d7	Donghe-Zhu	2021-02-07
1fad5f1	Donghe-Zhu	2021-02-07
ca03c39	Donghe-Zhu	2021-02-07
e2ffc14	Donghe-Zhu	2021-02-05
cd7c52c	Donghe-Zhu	2021-02-04
bcf84f4	Donghe-Zhu	2021-02-02
a518739	Donghe-Zhu	2021-02-01
61666de	Donghe-Zhu	2021-01-31
865b582	Donghe-Zhu	2021-01-31
3e68089	Donghe-Zhu	2021-01-31
ecf335c	Donghe-Zhu	2021-01-31
a618965	Donghe-Zhu	2021-01-31
59e006e	Donghe-Zhu	2021-01-31
a1c8f87	Donghe-Zhu	2021-01-31
ae5c18f	Donghe-Zhu	2021-01-31
b50fe52	Donghe-Zhu	2021-01-31
ac99ae5	jens-daniel-mueller	2021-01-29
b5bdcaf	Donghe-Zhu	2021-01-29
442010d	Donghe-Zhu	2021-01-29
372adf5	Donghe-Zhu	2021-01-29
af8788e	Donghe-Zhu	2021-01-29
21c91c9	Donghe-Zhu	2021-01-29
eded038	Donghe-Zhu	2021-01-29
541d4dd	Donghe-Zhu	2021-01-29
6a75576	Donghe-Zhu	2021-01-28
16fba40	Donghe-Zhu	2021-01-28
12bc567	Donghe-Zhu	2021-01-27
ceed31b	Donghe-Zhu	2021-01-27
342402d	Donghe-Zhu	2021-01-27
5bad5c2	Donghe-Zhu	2021-01-27
61efb56	Donghe-Zhu	2021-01-25
48f638e	Donghe-Zhu	2021-01-25
c1cec47	Donghe-Zhu	2021-01-25
05ffb0c	Donghe-Zhu	2021-01-25
8b97165	Donghe-Zhu	2021-01-25
c569946	Donghe-Zhu	2021-01-24
a2f0d56	Donghe-Zhu	2021-01-23
28509fc	Donghe-Zhu	2021-01-23
4c28e4a	Donghe-Zhu	2021-01-22
24cc264	jens-daniel-mueller	2021-01-22
7891955	Donghe-Zhu	2021-01-21
d4cf1cb	Donghe-Zhu	2021-01-21
1f3e5b6	jens-daniel-mueller	2021-01-20
0e7bdf1	jens-daniel-mueller	2021-01-15
4571843	jens-daniel-mueller	2021-01-14
b3564aa	jens-daniel-mueller	2021-01-14
8d032c3	jens-daniel-mueller	2021-01-14
17dee1d	jens-daniel-mueller	2021-01-13
7cdea0c	jens-daniel-mueller	2021-01-06
fa85b93	jens-daniel-mueller	2021-01-06
e5cb81a	Donghe-Zhu	2021-01-05
a499f10	Donghe-Zhu	2021-01-05
fb8a752	Donghe-Zhu	2020-12-23
8fae0b2	Donghe-Zhu	2020-12-21
c8b76b3	jens-daniel-mueller	2020-12-19

6.2 RMSE correlation between eras

RMSE was plotted to compare the agreement for one model applied to two adjacent eras (ie check whether the same predictor combination performs equal in both eras).

6.2.1 All models

# find max rmse to scale axis
max_rmse <-
  max(c(lm_all_fitted_wide_eras$rmse,
        lm_all_fitted_wide_eras$rmse_sum - lm_all_fitted_wide_eras$rmse))

lm_all_fitted_wide_eras %>%
  ggplot(aes(rmse, rmse_sum - rmse, col = gamma_slab)) +
  geom_point() +
  scale_color_viridis_d() +
  coord_equal(xlim = c(0,max_rmse),
              ylim = c(0,max_rmse)) +
  facet_grid(eras ~ basin)

Past versions of rmse_correlation_across_eras_all_models-1.png

Version	Author	Date
9d5a62c	Donghe-Zhu	2021-03-10
5d1e70b	Donghe-Zhu	2021-03-10
2093979	Donghe-Zhu	2021-03-10
b865899	Donghe-Zhu	2021-03-10
cc2a956	Donghe-Zhu	2021-03-10
dba33c8	Donghe-Zhu	2021-03-09
17f1c4a	Donghe-Zhu	2021-03-09
c024d1a	Donghe-Zhu	2021-03-09
02f7242	Donghe-Zhu	2021-03-09
1691156	Donghe-Zhu	2021-03-08
c0ceaf8	Donghe-Zhu	2021-03-08
058e0a1	Donghe-Zhu	2021-03-08
112dea0	Donghe-Zhu	2021-03-08
1843412	Donghe-Zhu	2021-03-08
3fbbfa4	Donghe-Zhu	2021-03-07
627c8fb	Donghe-Zhu	2021-03-07
9ef3222	Donghe-Zhu	2021-03-05
8c1e978	Donghe-Zhu	2021-03-05
865f68c	Donghe-Zhu	2021-03-05
ee69bc1	Donghe-Zhu	2021-03-05
a79291f	Donghe-Zhu	2021-03-05
e8c6f30	Donghe-Zhu	2021-03-04
59288fe	Donghe-Zhu	2021-03-04
731abc8	Donghe-Zhu	2021-03-04
e2a5a33	Donghe-Zhu	2021-03-04
c7892c1	Donghe-Zhu	2021-03-04
924430b	Donghe-Zhu	2021-03-03
0d0bca1	Donghe-Zhu	2021-03-03
cb63c16	Donghe-Zhu	2021-03-03
ffda45a	Donghe-Zhu	2021-03-03
691ba81	Donghe-Zhu	2021-03-03
c5e45a2	Donghe-Zhu	2021-03-03
89c3e58	Donghe-Zhu	2021-03-03
c911669	Donghe-Zhu	2021-03-03
13666ca	Donghe-Zhu	2021-03-01
c6e60fe	Donghe-Zhu	2021-03-01
7a388f7	Donghe-Zhu	2021-03-01
799e913	Donghe-Zhu	2021-03-01
66ff99f	Donghe-Zhu	2021-03-01
ac9bb7a	Donghe-Zhu	2021-02-28
efdc047	Donghe-Zhu	2021-02-28
e9a7418	Donghe-Zhu	2021-02-28
287123c	Donghe-Zhu	2021-02-27
54d5b5b	Donghe-Zhu	2021-02-27
330f064	Donghe-Zhu	2021-02-27
adbc9bc	Donghe-Zhu	2021-02-27
5937141	Donghe-Zhu	2021-02-27
4414bbf	Donghe-Zhu	2021-02-27
a265efb	Donghe-Zhu	2021-02-27
19edd1e	Donghe-Zhu	2021-02-27
f20483f	Donghe-Zhu	2021-02-26
6a2c7b3	Donghe-Zhu	2021-02-25
02b976d	Donghe-Zhu	2021-02-24
354c224	Donghe-Zhu	2021-02-24
1a0a88a	Donghe-Zhu	2021-02-24
57f701e	Donghe-Zhu	2021-02-24
06f3149	Donghe-Zhu	2021-02-16
e3bba84	Donghe-Zhu	2021-02-15
5dce4b1	Donghe-Zhu	2021-02-15
4469a0c	Donghe-Zhu	2021-02-13
5ae6a69	Donghe-Zhu	2021-02-10
05385dc	Donghe-Zhu	2021-02-10
f791ae4	Donghe-Zhu	2021-02-09
f71ae34	Donghe-Zhu	2021-02-09
c011832	Donghe-Zhu	2021-02-09
a145fa7	Donghe-Zhu	2021-02-09
c344e42	Donghe-Zhu	2021-02-08
2f095d7	Donghe-Zhu	2021-02-07
1fad5f1	Donghe-Zhu	2021-02-07
ca03c39	Donghe-Zhu	2021-02-07
cd7c52c	Donghe-Zhu	2021-02-04
bcf84f4	Donghe-Zhu	2021-02-02
61666de	Donghe-Zhu	2021-01-31
865b582	Donghe-Zhu	2021-01-31
3e68089	Donghe-Zhu	2021-01-31
ecf335c	Donghe-Zhu	2021-01-31
a618965	Donghe-Zhu	2021-01-31
59e006e	Donghe-Zhu	2021-01-31
a1c8f87	Donghe-Zhu	2021-01-31
ae5c18f	Donghe-Zhu	2021-01-31
b50fe52	Donghe-Zhu	2021-01-31
ac99ae5	jens-daniel-mueller	2021-01-29
b5bdcaf	Donghe-Zhu	2021-01-29
442010d	Donghe-Zhu	2021-01-29
372adf5	Donghe-Zhu	2021-01-29
af8788e	Donghe-Zhu	2021-01-29
21c91c9	Donghe-Zhu	2021-01-29
eded038	Donghe-Zhu	2021-01-29
541d4dd	Donghe-Zhu	2021-01-29
6a75576	Donghe-Zhu	2021-01-28
16fba40	Donghe-Zhu	2021-01-28
12bc567	Donghe-Zhu	2021-01-27
ceed31b	Donghe-Zhu	2021-01-27
342402d	Donghe-Zhu	2021-01-27
5bad5c2	Donghe-Zhu	2021-01-27
61efb56	Donghe-Zhu	2021-01-25
48f638e	Donghe-Zhu	2021-01-25
c1cec47	Donghe-Zhu	2021-01-25
05ffb0c	Donghe-Zhu	2021-01-25
8b97165	Donghe-Zhu	2021-01-25
c569946	Donghe-Zhu	2021-01-24
a2f0d56	Donghe-Zhu	2021-01-23
28509fc	Donghe-Zhu	2021-01-23
4c28e4a	Donghe-Zhu	2021-01-22
24cc264	jens-daniel-mueller	2021-01-22
7891955	Donghe-Zhu	2021-01-21
d4cf1cb	Donghe-Zhu	2021-01-21
1f3e5b6	jens-daniel-mueller	2021-01-20
0e7bdf1	jens-daniel-mueller	2021-01-15
4571843	jens-daniel-mueller	2021-01-14
b3564aa	jens-daniel-mueller	2021-01-14
8d032c3	jens-daniel-mueller	2021-01-14
17dee1d	jens-daniel-mueller	2021-01-13
7cdea0c	jens-daniel-mueller	2021-01-06
fa85b93	jens-daniel-mueller	2021-01-06
e5cb81a	Donghe-Zhu	2021-01-05
a499f10	Donghe-Zhu	2021-01-05
fb8a752	Donghe-Zhu	2020-12-23
8fae0b2	Donghe-Zhu	2020-12-21
c8b76b3	jens-daniel-mueller	2020-12-19

rm(max_rmse)

6.2.2 Best models

# find max rmse to scale axis
max_rmse <-
  max(c(lm_best$rmse,
        lm_best$rmse_sum - lm_best$rmse))

lm_best %>%
  ggplot(aes(rmse, rmse_sum - rmse, col = gamma_slab)) +
  geom_point() +
  scale_color_viridis_d() +
  coord_equal(xlim = c(0,max_rmse),
              ylim = c(0,max_rmse)) +
  facet_grid(eras ~ basin)

Past versions of rmse_correlation_across_eras_best_models-1.png

Version	Author	Date
fd528ed	Donghe-Zhu	2021-03-10
9d5a62c	Donghe-Zhu	2021-03-10
5d1e70b	Donghe-Zhu	2021-03-10
2093979	Donghe-Zhu	2021-03-10
b865899	Donghe-Zhu	2021-03-10
cc2a956	Donghe-Zhu	2021-03-10
60689fb	Donghe-Zhu	2021-03-10
dba33c8	Donghe-Zhu	2021-03-09
17f1c4a	Donghe-Zhu	2021-03-09
c024d1a	Donghe-Zhu	2021-03-09
02f7242	Donghe-Zhu	2021-03-09
6f50bc6	Donghe-Zhu	2021-03-09
1691156	Donghe-Zhu	2021-03-08
c0ceaf8	Donghe-Zhu	2021-03-08
058e0a1	Donghe-Zhu	2021-03-08
112dea0	Donghe-Zhu	2021-03-08
1843412	Donghe-Zhu	2021-03-08
3fbbfa4	Donghe-Zhu	2021-03-07
627c8fb	Donghe-Zhu	2021-03-07
9ef3222	Donghe-Zhu	2021-03-05
8c1e978	Donghe-Zhu	2021-03-05
865f68c	Donghe-Zhu	2021-03-05
ee69bc1	Donghe-Zhu	2021-03-05
a79291f	Donghe-Zhu	2021-03-05
e8c6f30	Donghe-Zhu	2021-03-04
59288fe	Donghe-Zhu	2021-03-04
731abc8	Donghe-Zhu	2021-03-04
e2a5a33	Donghe-Zhu	2021-03-04
c7892c1	Donghe-Zhu	2021-03-04
924430b	Donghe-Zhu	2021-03-03
0d0bca1	Donghe-Zhu	2021-03-03
cb63c16	Donghe-Zhu	2021-03-03
ffda45a	Donghe-Zhu	2021-03-03
691ba81	Donghe-Zhu	2021-03-03
c5e45a2	Donghe-Zhu	2021-03-03
89c3e58	Donghe-Zhu	2021-03-03
c407a50	Donghe-Zhu	2021-03-03
c911669	Donghe-Zhu	2021-03-03
b71c719	Donghe-Zhu	2021-03-01
13666ca	Donghe-Zhu	2021-03-01
c6e60fe	Donghe-Zhu	2021-03-01
7a388f7	Donghe-Zhu	2021-03-01
799e913	Donghe-Zhu	2021-03-01
66ff99f	Donghe-Zhu	2021-03-01
ac9bb7a	Donghe-Zhu	2021-02-28
efdc047	Donghe-Zhu	2021-02-28
e9a7418	Donghe-Zhu	2021-02-28
e152917	Donghe-Zhu	2021-02-28
287123c	Donghe-Zhu	2021-02-27
54d5b5b	Donghe-Zhu	2021-02-27
330f064	Donghe-Zhu	2021-02-27
adbc9bc	Donghe-Zhu	2021-02-27
5937141	Donghe-Zhu	2021-02-27
4414bbf	Donghe-Zhu	2021-02-27
a265efb	Donghe-Zhu	2021-02-27
19edd1e	Donghe-Zhu	2021-02-27
f20483f	Donghe-Zhu	2021-02-26
6a2c7b3	Donghe-Zhu	2021-02-25
354c224	Donghe-Zhu	2021-02-24
1a0a88a	Donghe-Zhu	2021-02-24
57f701e	Donghe-Zhu	2021-02-24
06f3149	Donghe-Zhu	2021-02-16
401eab3	Donghe-Zhu	2021-02-15
e3bba84	Donghe-Zhu	2021-02-15
5dce4b1	Donghe-Zhu	2021-02-15
4469a0c	Donghe-Zhu	2021-02-13
5ae6a69	Donghe-Zhu	2021-02-10
05385dc	Donghe-Zhu	2021-02-10
f791ae4	Donghe-Zhu	2021-02-09
f71ae34	Donghe-Zhu	2021-02-09
c011832	Donghe-Zhu	2021-02-09
a145fa7	Donghe-Zhu	2021-02-09
c344e42	Donghe-Zhu	2021-02-08
2f095d7	Donghe-Zhu	2021-02-07
1fad5f1	Donghe-Zhu	2021-02-07
ca03c39	Donghe-Zhu	2021-02-07
e2ffc14	Donghe-Zhu	2021-02-05
cd7c52c	Donghe-Zhu	2021-02-04
bcf84f4	Donghe-Zhu	2021-02-02
a518739	Donghe-Zhu	2021-02-01
61666de	Donghe-Zhu	2021-01-31
865b582	Donghe-Zhu	2021-01-31
3e68089	Donghe-Zhu	2021-01-31
ecf335c	Donghe-Zhu	2021-01-31
a618965	Donghe-Zhu	2021-01-31
59e006e	Donghe-Zhu	2021-01-31
a1c8f87	Donghe-Zhu	2021-01-31
ae5c18f	Donghe-Zhu	2021-01-31
b50fe52	Donghe-Zhu	2021-01-31
ac99ae5	jens-daniel-mueller	2021-01-29
b5bdcaf	Donghe-Zhu	2021-01-29
442010d	Donghe-Zhu	2021-01-29
372adf5	Donghe-Zhu	2021-01-29
af8788e	Donghe-Zhu	2021-01-29
21c91c9	Donghe-Zhu	2021-01-29
eded038	Donghe-Zhu	2021-01-29
541d4dd	Donghe-Zhu	2021-01-29
6a75576	Donghe-Zhu	2021-01-28
16fba40	Donghe-Zhu	2021-01-28
12bc567	Donghe-Zhu	2021-01-27
ceed31b	Donghe-Zhu	2021-01-27
342402d	Donghe-Zhu	2021-01-27
5bad5c2	Donghe-Zhu	2021-01-27
61efb56	Donghe-Zhu	2021-01-25
48f638e	Donghe-Zhu	2021-01-25
c1cec47	Donghe-Zhu	2021-01-25
05ffb0c	Donghe-Zhu	2021-01-25
8b97165	Donghe-Zhu	2021-01-25
c569946	Donghe-Zhu	2021-01-24
a2f0d56	Donghe-Zhu	2021-01-23
28509fc	Donghe-Zhu	2021-01-23
4c28e4a	Donghe-Zhu	2021-01-22
24cc264	jens-daniel-mueller	2021-01-22
7891955	Donghe-Zhu	2021-01-21
d4cf1cb	Donghe-Zhu	2021-01-21
1f3e5b6	jens-daniel-mueller	2021-01-20
0e7bdf1	jens-daniel-mueller	2021-01-15
4571843	jens-daniel-mueller	2021-01-14
b3564aa	jens-daniel-mueller	2021-01-14
8d032c3	jens-daniel-mueller	2021-01-14
17dee1d	jens-daniel-mueller	2021-01-13
7cdea0c	jens-daniel-mueller	2021-01-06
fa85b93	jens-daniel-mueller	2021-01-06
e5cb81a	Donghe-Zhu	2021-01-05
a499f10	Donghe-Zhu	2021-01-05
fb8a752	Donghe-Zhu	2020-12-23
8fae0b2	Donghe-Zhu	2020-12-21
c8b76b3	jens-daniel-mueller	2020-12-19

rm(max_rmse)

6.3 Predictor counts

The number of models where a particular predictor was included were counted for each basin, density slab and compared eras

# calculate cases of predictor used
lm_all_stats <- lm_best_long %>% 
  filter(term != "(Intercept)",
         delta_coeff != 0) %>% 
  group_by(basin, eras, gamma_slab) %>% 
  count(term) %>% 
  ungroup() %>% 
  pivot_wider(values_from = n,
              names_from = term,
              values_fill = 0)

# print table
lm_all_stats %>%
  gt(rowname_col = "gamma_slab",
     groupname_col = c("basin", "eras")) %>% 
  summary_rows(
    groups = TRUE,
    fns = list(total = "sum")
  )

	aou	nitrate	phosphate	phosphate_star	sal	silicate	temp
Atlantic - 1982-1999 --> 2000-2012
(-Inf,26]	5	1	4	5	3	3	2
(26,26.5]	5	3	2	4	1	4	4
(26.5,27.25]	5	1	4	4	1	5	3
(27.25,27.5]	5	4	1	3	3	5	2
(27.5,27.75]	5	1	4	3	4	3	1
(27.75,27.85]	5	2	3	3	5	4	0
(27.85,27.95]	5	0	5	5	2	3	2
(27.95,28.05]	5	2	3	5	2	3	3
(28.05,28.1]	5	0	5	5	2	3	2
(28.1,28.15]	5	1	4	5	3	4	1
(28.15,28.2]	5	5	0	4	2	4	2
(28.2, Inf]	5	5	0	3	4	3	1
total	60.00	25.00	35.00	49.00	32.00	44.00	23.00
Atlantic - 2000-2012 --> 2013-2019
(-Inf,26]	5	1	4	5	3	3	2
(26,26.5]	5	3	2	4	1	4	4
(26.5,27.25]	5	1	4	4	2	5	2
(27.25,27.5]	5	5	0	3	2	5	2
(27.5,27.75]	5	2	3	3	5	4	0
(27.75,27.85]	5	2	3	3	5	4	0
(27.85,27.95]	5	0	5	5	2	3	2
(27.95,28.05]	5	2	3	5	2	3	3
(28.05,28.1]	5	1	4	5	3	3	2
(28.1,28.15]	5	1	4	5	3	3	2
(28.15,28.2]	5	5	0	3	3	4	2
(28.2, Inf]	5	5	0	3	4	3	1
total	60.00	28.00	32.00	48.00	35.00	44.00	22.00
Indo-Pacific - 1982-1999 --> 2000-2012
(-Inf,26]	4	1	4	5	2	4	3
(26,26.5]	5	1	4	4	1	5	3
(26.5,26.75]	4	2	3	5	1	5	3
(26.75,27]	5	0	5	5	2	3	2
(27,27.25]	5	1	4	5	1	4	3
(27.25,27.5]	5	2	2	5	3	5	2
(27.5,27.75]	4	2	2	5	4	5	1
(27.75,27.85]	5	1	4	4	1	5	3
(27.85,27.95]	3	5	0	4	0	3	5
(27.95,28.05]	5	2	3	5	2	5	2
(28.05,28.1]	5	1	4	4	2	5	2
(28.1, Inf]	4	2	3	4	2	5	3
total	54.00	20.00	38.00	55.00	21.00	54.00	32.00
Indo-Pacific - 2000-2012 --> 2013-2019
(-Inf,26]	4	1	4	5	2	4	3
(26,26.5]	5	1	4	4	1	5	3
(26.5,26.75]	4	2	3	5	1	5	3
(26.75,27]	5	0	5	5	2	3	2
(27,27.25]	5	1	4	5	1	4	3
(27.25,27.5]	5	2	2	5	3	5	2
(27.5,27.75]	4	2	2	5	4	5	1
(27.75,27.85]	4	2	3	5	3	4	2
(27.85,27.95]	4	3	2	4	0	4	5
(27.95,28.05]	5	2	3	5	3	3	2
(28.05,28.1]	5	1	4	4	1	5	3
(28.1, Inf]	5	2	3	4	3	5	2
total	55.00	19.00	39.00	56.00	24.00	52.00	31.00

6.4 RMSE alternatives

AIC is an alternative criterion to RMSE to judge model quality, but not (yet) taken into account.

lm_all_fitted_wide_eras %>% 
  ggplot(aes(rmse, aic, col = gamma_slab)) +
  geom_point() +
  scale_color_viridis_d() +
  facet_grid(eras~basin)

Past versions of aic_vs_rmse_all_models-1.png

Version	Author	Date
9d5a62c	Donghe-Zhu	2021-03-10
5d1e70b	Donghe-Zhu	2021-03-10
2093979	Donghe-Zhu	2021-03-10
b865899	Donghe-Zhu	2021-03-10
cc2a956	Donghe-Zhu	2021-03-10
dba33c8	Donghe-Zhu	2021-03-09
17f1c4a	Donghe-Zhu	2021-03-09
c024d1a	Donghe-Zhu	2021-03-09
02f7242	Donghe-Zhu	2021-03-09
1691156	Donghe-Zhu	2021-03-08
c0ceaf8	Donghe-Zhu	2021-03-08
058e0a1	Donghe-Zhu	2021-03-08
112dea0	Donghe-Zhu	2021-03-08
1843412	Donghe-Zhu	2021-03-08
3fbbfa4	Donghe-Zhu	2021-03-07
627c8fb	Donghe-Zhu	2021-03-07
9ef3222	Donghe-Zhu	2021-03-05
8c1e978	Donghe-Zhu	2021-03-05
865f68c	Donghe-Zhu	2021-03-05
ee69bc1	Donghe-Zhu	2021-03-05
a79291f	Donghe-Zhu	2021-03-05
e8c6f30	Donghe-Zhu	2021-03-04
59288fe	Donghe-Zhu	2021-03-04
731abc8	Donghe-Zhu	2021-03-04
e2a5a33	Donghe-Zhu	2021-03-04
c7892c1	Donghe-Zhu	2021-03-04
924430b	Donghe-Zhu	2021-03-03
0d0bca1	Donghe-Zhu	2021-03-03
cb63c16	Donghe-Zhu	2021-03-03
ffda45a	Donghe-Zhu	2021-03-03
691ba81	Donghe-Zhu	2021-03-03
c5e45a2	Donghe-Zhu	2021-03-03
89c3e58	Donghe-Zhu	2021-03-03
c911669	Donghe-Zhu	2021-03-03
13666ca	Donghe-Zhu	2021-03-01
c6e60fe	Donghe-Zhu	2021-03-01
7a388f7	Donghe-Zhu	2021-03-01
799e913	Donghe-Zhu	2021-03-01
66ff99f	Donghe-Zhu	2021-03-01
ac9bb7a	Donghe-Zhu	2021-02-28
efdc047	Donghe-Zhu	2021-02-28
e9a7418	Donghe-Zhu	2021-02-28
287123c	Donghe-Zhu	2021-02-27
54d5b5b	Donghe-Zhu	2021-02-27
330f064	Donghe-Zhu	2021-02-27
adbc9bc	Donghe-Zhu	2021-02-27
5937141	Donghe-Zhu	2021-02-27
4414bbf	Donghe-Zhu	2021-02-27
a265efb	Donghe-Zhu	2021-02-27
19edd1e	Donghe-Zhu	2021-02-27
f20483f	Donghe-Zhu	2021-02-26
6a2c7b3	Donghe-Zhu	2021-02-25
02b976d	Donghe-Zhu	2021-02-24
354c224	Donghe-Zhu	2021-02-24
1a0a88a	Donghe-Zhu	2021-02-24
57f701e	Donghe-Zhu	2021-02-24
06f3149	Donghe-Zhu	2021-02-16
e3bba84	Donghe-Zhu	2021-02-15
5dce4b1	Donghe-Zhu	2021-02-15
4469a0c	Donghe-Zhu	2021-02-13
5ae6a69	Donghe-Zhu	2021-02-10
05385dc	Donghe-Zhu	2021-02-10
f791ae4	Donghe-Zhu	2021-02-09
f71ae34	Donghe-Zhu	2021-02-09
c011832	Donghe-Zhu	2021-02-09
a145fa7	Donghe-Zhu	2021-02-09
c344e42	Donghe-Zhu	2021-02-08
2f095d7	Donghe-Zhu	2021-02-07
1fad5f1	Donghe-Zhu	2021-02-07
ca03c39	Donghe-Zhu	2021-02-07
cd7c52c	Donghe-Zhu	2021-02-04
bcf84f4	Donghe-Zhu	2021-02-02
61666de	Donghe-Zhu	2021-01-31
865b582	Donghe-Zhu	2021-01-31
3e68089	Donghe-Zhu	2021-01-31
ecf335c	Donghe-Zhu	2021-01-31
a618965	Donghe-Zhu	2021-01-31
59e006e	Donghe-Zhu	2021-01-31
a1c8f87	Donghe-Zhu	2021-01-31
ae5c18f	Donghe-Zhu	2021-01-31
b50fe52	Donghe-Zhu	2021-01-31
ac99ae5	jens-daniel-mueller	2021-01-29
b5bdcaf	Donghe-Zhu	2021-01-29
442010d	Donghe-Zhu	2021-01-29
372adf5	Donghe-Zhu	2021-01-29
af8788e	Donghe-Zhu	2021-01-29
21c91c9	Donghe-Zhu	2021-01-29
eded038	Donghe-Zhu	2021-01-29
541d4dd	Donghe-Zhu	2021-01-29
6a75576	Donghe-Zhu	2021-01-28
16fba40	Donghe-Zhu	2021-01-28
12bc567	Donghe-Zhu	2021-01-27
ceed31b	Donghe-Zhu	2021-01-27
342402d	Donghe-Zhu	2021-01-27
5bad5c2	Donghe-Zhu	2021-01-27
61efb56	Donghe-Zhu	2021-01-25
48f638e	Donghe-Zhu	2021-01-25
c1cec47	Donghe-Zhu	2021-01-25
05ffb0c	Donghe-Zhu	2021-01-25
8b97165	Donghe-Zhu	2021-01-25
c569946	Donghe-Zhu	2021-01-24
a2f0d56	Donghe-Zhu	2021-01-23
28509fc	Donghe-Zhu	2021-01-23
4c28e4a	Donghe-Zhu	2021-01-22
24cc264	jens-daniel-mueller	2021-01-22
7891955	Donghe-Zhu	2021-01-21
d4cf1cb	Donghe-Zhu	2021-01-21
1f3e5b6	jens-daniel-mueller	2021-01-20
0e7bdf1	jens-daniel-mueller	2021-01-15
4571843	jens-daniel-mueller	2021-01-14
b3564aa	jens-daniel-mueller	2021-01-14
8d032c3	jens-daniel-mueller	2021-01-14
17dee1d	jens-daniel-mueller	2021-01-13
7cdea0c	jens-daniel-mueller	2021-01-06
fa85b93	jens-daniel-mueller	2021-01-06
e5cb81a	Donghe-Zhu	2021-01-05
a499f10	Donghe-Zhu	2021-01-05
fb8a752	Donghe-Zhu	2020-12-23
8fae0b2	Donghe-Zhu	2020-12-21
c8b76b3	jens-daniel-mueller	2020-12-19

lm_best %>% 
  ggplot(aes(rmse, aic, col = gamma_slab)) +
  geom_point() +
  scale_color_viridis_d() +
  facet_grid(eras~basin)

Past versions of aic_vs_rmse_selected_models-1.png

Version	Author	Date
fd528ed	Donghe-Zhu	2021-03-10
9d5a62c	Donghe-Zhu	2021-03-10
5d1e70b	Donghe-Zhu	2021-03-10
2093979	Donghe-Zhu	2021-03-10
b865899	Donghe-Zhu	2021-03-10
cc2a956	Donghe-Zhu	2021-03-10
60689fb	Donghe-Zhu	2021-03-10
dba33c8	Donghe-Zhu	2021-03-09
17f1c4a	Donghe-Zhu	2021-03-09
c024d1a	Donghe-Zhu	2021-03-09
02f7242	Donghe-Zhu	2021-03-09
6f50bc6	Donghe-Zhu	2021-03-09
1691156	Donghe-Zhu	2021-03-08
c0ceaf8	Donghe-Zhu	2021-03-08
058e0a1	Donghe-Zhu	2021-03-08
112dea0	Donghe-Zhu	2021-03-08
1843412	Donghe-Zhu	2021-03-08
3fbbfa4	Donghe-Zhu	2021-03-07
627c8fb	Donghe-Zhu	2021-03-07
9ef3222	Donghe-Zhu	2021-03-05
8c1e978	Donghe-Zhu	2021-03-05
865f68c	Donghe-Zhu	2021-03-05
ee69bc1	Donghe-Zhu	2021-03-05
a79291f	Donghe-Zhu	2021-03-05
e8c6f30	Donghe-Zhu	2021-03-04
59288fe	Donghe-Zhu	2021-03-04
731abc8	Donghe-Zhu	2021-03-04
e2a5a33	Donghe-Zhu	2021-03-04
c7892c1	Donghe-Zhu	2021-03-04
924430b	Donghe-Zhu	2021-03-03
0d0bca1	Donghe-Zhu	2021-03-03
cb63c16	Donghe-Zhu	2021-03-03
ffda45a	Donghe-Zhu	2021-03-03
691ba81	Donghe-Zhu	2021-03-03
c5e45a2	Donghe-Zhu	2021-03-03
89c3e58	Donghe-Zhu	2021-03-03
c407a50	Donghe-Zhu	2021-03-03
c911669	Donghe-Zhu	2021-03-03
b71c719	Donghe-Zhu	2021-03-01
13666ca	Donghe-Zhu	2021-03-01
c6e60fe	Donghe-Zhu	2021-03-01
7a388f7	Donghe-Zhu	2021-03-01
799e913	Donghe-Zhu	2021-03-01
66ff99f	Donghe-Zhu	2021-03-01
ac9bb7a	Donghe-Zhu	2021-02-28
efdc047	Donghe-Zhu	2021-02-28
e9a7418	Donghe-Zhu	2021-02-28
e152917	Donghe-Zhu	2021-02-28
287123c	Donghe-Zhu	2021-02-27
54d5b5b	Donghe-Zhu	2021-02-27
330f064	Donghe-Zhu	2021-02-27
adbc9bc	Donghe-Zhu	2021-02-27
5937141	Donghe-Zhu	2021-02-27
4414bbf	Donghe-Zhu	2021-02-27
a265efb	Donghe-Zhu	2021-02-27
19edd1e	Donghe-Zhu	2021-02-27
f20483f	Donghe-Zhu	2021-02-26
6a2c7b3	Donghe-Zhu	2021-02-25
354c224	Donghe-Zhu	2021-02-24
1a0a88a	Donghe-Zhu	2021-02-24
57f701e	Donghe-Zhu	2021-02-24
06f3149	Donghe-Zhu	2021-02-16
401eab3	Donghe-Zhu	2021-02-15
e3bba84	Donghe-Zhu	2021-02-15
5dce4b1	Donghe-Zhu	2021-02-15
4469a0c	Donghe-Zhu	2021-02-13
5ae6a69	Donghe-Zhu	2021-02-10
05385dc	Donghe-Zhu	2021-02-10
f791ae4	Donghe-Zhu	2021-02-09
f71ae34	Donghe-Zhu	2021-02-09
c011832	Donghe-Zhu	2021-02-09
a145fa7	Donghe-Zhu	2021-02-09
c344e42	Donghe-Zhu	2021-02-08
2f095d7	Donghe-Zhu	2021-02-07
1fad5f1	Donghe-Zhu	2021-02-07
ca03c39	Donghe-Zhu	2021-02-07
e2ffc14	Donghe-Zhu	2021-02-05
cd7c52c	Donghe-Zhu	2021-02-04
bcf84f4	Donghe-Zhu	2021-02-02
a518739	Donghe-Zhu	2021-02-01
61666de	Donghe-Zhu	2021-01-31
865b582	Donghe-Zhu	2021-01-31
3e68089	Donghe-Zhu	2021-01-31
ecf335c	Donghe-Zhu	2021-01-31
a618965	Donghe-Zhu	2021-01-31
59e006e	Donghe-Zhu	2021-01-31
a1c8f87	Donghe-Zhu	2021-01-31
ae5c18f	Donghe-Zhu	2021-01-31
b50fe52	Donghe-Zhu	2021-01-31
ac99ae5	jens-daniel-mueller	2021-01-29
b5bdcaf	Donghe-Zhu	2021-01-29
442010d	Donghe-Zhu	2021-01-29
372adf5	Donghe-Zhu	2021-01-29
af8788e	Donghe-Zhu	2021-01-29
21c91c9	Donghe-Zhu	2021-01-29
eded038	Donghe-Zhu	2021-01-29
541d4dd	Donghe-Zhu	2021-01-29
6a75576	Donghe-Zhu	2021-01-28
16fba40	Donghe-Zhu	2021-01-28
12bc567	Donghe-Zhu	2021-01-27
ceed31b	Donghe-Zhu	2021-01-27
342402d	Donghe-Zhu	2021-01-27
5bad5c2	Donghe-Zhu	2021-01-27
61efb56	Donghe-Zhu	2021-01-25
48f638e	Donghe-Zhu	2021-01-25
c1cec47	Donghe-Zhu	2021-01-25
05ffb0c	Donghe-Zhu	2021-01-25
8b97165	Donghe-Zhu	2021-01-25
c569946	Donghe-Zhu	2021-01-24
a2f0d56	Donghe-Zhu	2021-01-23
28509fc	Donghe-Zhu	2021-01-23
4c28e4a	Donghe-Zhu	2021-01-22
24cc264	jens-daniel-mueller	2021-01-22
7891955	Donghe-Zhu	2021-01-21
d4cf1cb	Donghe-Zhu	2021-01-21
1f3e5b6	jens-daniel-mueller	2021-01-20
0e7bdf1	jens-daniel-mueller	2021-01-15
4571843	jens-daniel-mueller	2021-01-14
b3564aa	jens-daniel-mueller	2021-01-14
8d032c3	jens-daniel-mueller	2021-01-14
17dee1d	jens-daniel-mueller	2021-01-13
7cdea0c	jens-daniel-mueller	2021-01-06
fa85b93	jens-daniel-mueller	2021-01-06
e5cb81a	Donghe-Zhu	2021-01-05
a499f10	Donghe-Zhu	2021-01-05
fb8a752	Donghe-Zhu	2020-12-23
8fae0b2	Donghe-Zhu	2020-12-21
c8b76b3	jens-daniel-mueller	2020-12-19

Session information

sessionInfo()

R version 4.0.3 (2020-10-10)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: openSUSE Leap 15.2

Matrix products: default
BLAS:   /usr/local/R-4.0.3/lib64/R/lib/libRblas.so
LAPACK: /usr/local/R-4.0.3/lib64/R/lib/libRlapack.so

locale:
 [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C              
 [3] LC_TIME=en_US.UTF-8        LC_COLLATE=en_US.UTF-8    
 [5] LC_MONETARY=en_US.UTF-8    LC_MESSAGES=en_US.UTF-8   
 [7] LC_PAPER=en_US.UTF-8       LC_NAME=C                 
 [9] LC_ADDRESS=C               LC_TELEPHONE=C            
[11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
 [1] gt_0.2.2         corrr_0.4.3      broom_0.7.5      kableExtra_1.3.1
 [5] knitr_1.30       olsrr_0.5.3      GGally_2.0.0     lubridate_1.7.9 
 [9] metR_0.9.0       scico_1.2.0      patchwork_1.1.1  collapse_1.5.0  
[13] forcats_0.5.0    stringr_1.4.0    dplyr_1.0.2      purrr_0.3.4     
[17] readr_1.4.0      tidyr_1.1.2      tibble_3.0.4     ggplot2_3.3.3   
[21] tidyverse_1.3.0  workflowr_1.6.2 

loaded via a namespace (and not attached):
 [1] fs_1.5.0                 webshot_0.5.2            RColorBrewer_1.1-2      
 [4] httr_1.4.2               rprojroot_2.0.2          tools_4.0.3             
 [7] backports_1.1.10         R6_2.5.0                 nortest_1.0-4           
[10] DBI_1.1.0                colorspace_2.0-0         withr_2.3.0             
[13] gridExtra_2.3            tidyselect_1.1.0         curl_4.3                
[16] compiler_4.0.3           git2r_0.27.1             cli_2.2.0               
[19] rvest_0.3.6              xml2_1.3.2               sass_0.2.0              
[22] labeling_0.4.2           scales_1.1.1             checkmate_2.0.0         
[25] goftest_1.2-2            digest_0.6.27            foreign_0.8-80          
[28] rmarkdown_2.5            rio_0.5.16               pkgconfig_2.0.3         
[31] htmltools_0.5.0          highr_0.8                dbplyr_1.4.4            
[34] rlang_0.4.10             readxl_1.3.1             rstudioapi_0.13         
[37] farver_2.0.3             generics_0.1.0           jsonlite_1.7.2          
[40] zip_2.1.1                car_3.0-10               magrittr_2.0.1          
[43] Matrix_1.2-18            Rcpp_1.0.5               munsell_0.5.0           
[46] fansi_0.4.1              abind_1.4-5              lifecycle_0.2.0         
[49] stringi_1.5.3            whisker_0.4              yaml_2.2.1              
[52] carData_3.0-4            plyr_1.8.6               grid_4.0.3              
[55] blob_1.2.1               parallel_4.0.3           promises_1.1.1          
[58] crayon_1.3.4             lattice_0.20-41          haven_2.3.1             
[61] hms_0.5.3                pillar_1.4.7             reprex_0.3.0            
[64] glue_1.4.2               evaluate_0.14            RcppArmadillo_0.10.1.2.2
[67] data.table_1.13.6        modelr_0.1.8             vctrs_0.3.6             
[70] httpuv_1.5.4             cellranger_1.1.0         gtable_0.3.0            
[73] reshape_0.8.8            assertthat_0.2.1         xfun_0.20               
[76] openxlsx_4.2.3           RcppEigen_0.3.3.9.1      later_1.1.0.1           
[79] viridisLite_0.3.0        ellipsis_0.3.1           here_1.0.1