Last updated: 2019-05-06
Checks: 6 0
Knit directory: dsc-susie-z/
This reproducible R Markdown analysis was created with workflowr (version 1.3.0). The Checks tab describes the reproducibility checks that were applied when the results were created. The Past versions tab lists the development history.
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.
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.
The command set.seed(20190115) 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.
Great job! Recording the operating system, R version, and package versions is critical for reproducibility.
Nice! There were no cached chunks for this analysis, so you can be confident that you successfully produced the results during this run.
Great! You are using Git for version control. Tracking code development and connecting the code version to the results is critical for reproducibility. The version displayed above was the version of the Git repository at the time these results were generated.
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: .DS_Store
Ignored: .Rhistory
Ignored: .Rproj.user/
Ignored: .sos/
Ignored: analysis/.DS_Store
Ignored: data/.DS_Store
Ignored: output/.DS_Store
Untracked files:
Untracked: data/random_data_31.rds
Untracked: data/random_data_31_sim_gaussian_35.rds
Untracked: data/random_data_31_sim_gaussian_35_get_sumstats_1.rds
Untracked: data/small_data_1.ld_in_file.in.ld
Untracked: data/small_data_1.ld_out_file.out.ld
Untracked: data/small_data_132.ld_in_file.in.ld
Untracked: data/small_data_132.ld_out_file.out.ld
Untracked: data/small_data_132_sim_gaussian_12.rds
Untracked: data/small_data_132_sim_gaussian_12_get_sumstats_1.rds
Untracked: data/small_data_1_sim_gaussian_2.rds
Untracked: data/small_data_1_sim_gaussian_2_get_sumstats_1.rds
Untracked: data/small_data_46.rds
Untracked: data/small_data_46_sim_gaussian_10.rds
Untracked: data/small_data_46_sim_gaussian_10_get_sumstats_2.rds
Untracked: data/small_data_69.ld_in_file.in.ld
Untracked: data/small_data_69.ld_out_file.out.ld
Untracked: data/small_data_69.rds
Untracked: data/small_data_69_sim_gaussian_3.rds
Untracked: data/small_data_69_sim_gaussian_3_get_sumstats_1.rds
Untracked: data/small_data_69_sim_gaussian_3_get_sumstats_1_susie_z_1.rds
Untracked: data/small_data_69_sim_gaussian_3_get_sumstats_1_susie_z_2.rds
Untracked: figure/
Untracked: output/dscoutProblem475.rds
Untracked: output/dscoutProblem75.rds
Untracked: output/finemap_compare_random_data_null_dscout.rds
Untracked: output/finemap_compare_random_data_signal_dscout.rds
Untracked: output/finemap_compare_small_data_signal_dscout.rds
Untracked: output/finemap_compare_small_data_signal_dscout_RE8.rds
Untracked: output/r_compare_FINEMAP_PIP_ROC.rds
Untracked: output/r_compare_add_z_FINEMAP_PIP_ROC.rds
Untracked: output/r_compare_add_z_FINEMAP_ROC.rds
Untracked: output/r_compare_add_z_SuSiEb_ROC.rds
Untracked: output/r_compare_add_z_SuSiErss_ROC.rds
Untracked: output/r_compare_add_z_dscout_susie_finemap_tibble.rds
Untracked: output/r_compare_add_z_lambda_FINEMAP_ROC.rds
Untracked: output/r_compare_add_z_lambda_SuSiEb_ROC.rds
Untracked: output/r_compare_add_z_lambda_SuSiErss_ROC.rds
Untracked: output/r_compare_add_z_lambda_caviar_CAVIAR_ROC.rds
Untracked: output/r_compare_add_z_lambda_caviar_FINEMAP_ROC.rds
Untracked: output/r_compare_add_z_lambda_caviar_dscout_caviar_tibble.rds
Untracked: output/r_compare_add_z_lambda_caviar_dscout_finemap_tibble.rds
Untracked: output/r_compare_add_z_lambda_caviar_dscout_susiebhat_tibble.rds
Untracked: output/r_compare_add_z_lambda_caviar_dscout_susierss_tibble.rds
Untracked: output/r_compare_add_z_lambda_dscout_susie_finemap_tibble.rds
Untracked: output/r_compare_dscout_susie_finemappip_tibble.rds
Untracked: output/r_compare_dscout_susie_finemappip_truth_tibble.rds
Untracked: output/r_compare_susieb_PIP_ROC.rds
Untracked: output/r_compare_susiepip_tibble.rds
Untracked: output/r_compare_susierss_PIP_ROC.rds
Untracked: output/random_data_100_sim_gaussian_null_1_get_sumstats_1_finemap_1.rds
Untracked: output/random_data_31_35_fit_em.rds
Untracked: output/random_data_76.rds
Untracked: output/random_data_76_sim_gaussian_8.rds
Untracked: output/random_data_76_sim_gaussian_8_get_sumstats_1.rds
Untracked: output/small_data_42_sim_gaussian_36_get_sumstats_2_susie_z_2.rds
Untracked: output/small_data_92_sim_gaussian_30_get_sumstats_2_susie_z_2.rds
Unstaged changes:
Modified: analysis/SuSiErssNotConverge.Rmd
Modified: analysis/SusieZPerformance.Rmd
Modified: analysis/SusieZPerformanceRE3.Rmd
Modified: analysis/index.Rmd
Modified: output/dsc_susie_z_v_output.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 R Markdown and HTML files. If you’ve configured a remote Git repository (see ?wflow_git_remote), click on the hyperlinks in the table below to view them.
| File | Version | Author | Date | Message |
|---|---|---|---|---|
| Rmd | 34e4e13 | zouyuxin | 2019-05-06 | wflow_publish(“analysis/r_compare_add_z_lambda_caviar_susie_finemap.Rmd”) |
The design matrix X are real human genotype data from GTEx project, the 150 data in dsc-finemap repo. We simulate under various number of causal variables (1,2) and total percentage of variance explained (0.1, 0.2). We set effect size of each causal variable to be equal. Using the summary statistics from univariate regression, we fit SuSiE model using in-sample/out-sample correlation matrix, and compare their results.
library(dscrutils)
library(tibble)Warning: package 'tibble' was built under R version 3.5.2library(kableExtra)
library(dplyr)
Attaching package: 'dplyr'The following objects are masked from 'package:stats':
filter, lagThe following objects are masked from 'package:base':
intersect, setdiff, setequal, uniondscout.finemap = dscquery('r_compare_add_z_lambda_caviar', targets = 'sim_gaussian sim_gaussian.pve sim_gaussian.n_signal sim_gaussian.meta data.N_in method.ld_method method.add_z score.total score.valid score.size score.pip', conditions = c("$(method) == 'finemap'"), groups = c("method_susie:", "method: susie_bhat, susie_rss, finemap, caviar", "score: score_susie score_finemap score_caviar"))
dscout.caviar = dscquery('r_compare_add_z_lambda_caviar', targets = 'sim_gaussian sim_gaussian.pve sim_gaussian.n_signal sim_gaussian.meta data.N_in method.ld_method method.add_z score.pip', conditions = c("$(method) == 'caviar'"), groups = c("method_susie:", "method: susie_bhat, susie_rss, finemap, caviar", "score: score_susie score_finemap score_caviar"))
dscout.susiebhat = dscquery('r_compare_add_z_lambda_caviar', targets = 'sim_gaussian sim_gaussian.pve sim_gaussian.n_signal sim_gaussian.meta data.N_in method.ld_method method.add_z method.L method.estimate_residual_variance score.total score.valid score.size score.purity score.top score.converged score.pip', conditions = c("$(method) == 'susie_bhat'"), groups = c("method_susie:", "method: susie_bhat, susie_rss, finemap, caviar", "score: score_susie"))
dscout.susierss = dscquery('r_compare_add_z_lambda_caviar', targets = 'sim_gaussian sim_gaussian.pve sim_gaussian.n_signal sim_gaussian.meta data.N_in method.ld_method method.add_z method.L method.estimate_residual_variance method.lamb score.total score.valid score.size score.purity score.top score.converged score.pip', conditions = c("$(method) == 'susie_rss'"), groups = c("method_susie:", "method: susie_bhat, susie_rss, finemap, caviar", "score: score_susie"))dscout.finemap = readRDS('output/r_compare_add_z_lambda_caviar_dscout_finemap_tibble.rds')
dscout.finemap = dscout.finemap[,-c(6, 8, 11, 15)]
colnames(dscout.finemap) = c('DSC', 'filename','pve', 'n_signal', 'meta','N_in', 'ld_method', 'addz', 'valid', 'total', 'size')
dscout.susiebhat = readRDS('output/r_compare_add_z_lambda_caviar_dscout_susiebhat_tibble.rds')
dscout.susiebhat = dscout.susiebhat[,-c(6, 8, 13, 19)]
colnames(dscout.susiebhat) = c('DSC', 'filename','pve', 'n_signal', 'meta','N_in', 'ld_method','estimate_residual_variance', 'addz', 'L', 'valid', 'total', 'top', 'size', 'purity', 'converged')
dscout.susierss = readRDS('output/r_compare_add_z_lambda_caviar_dscout_susierss_tibble.rds')
dscout.susierss = dscout.susierss[,-c(6, 8, 14, 20)]
colnames(dscout.susierss) = c('DSC', 'filename','pve', 'n_signal', 'meta','N_in', 'ld_method','lambda','estimate_residual_variance', 'addz', 'L', 'valid', 'total', 'top', 'size', 'purity', 'converged')dscout.finemap.in_sample = dscout.finemap %>% filter(ld_method == 'in_sample' & addz == FALSE)
dscout.finemap.in_sample.addz = dscout.finemap %>% filter(ld_method == 'in_sample' & addz == TRUE)
dscout.finemap.out_sample = dscout.finemap %>% filter(ld_method == 'out_sample' & addz == FALSE)
dscout.finemap.out_sample.addz = dscout.finemap %>% filter(ld_method == 'out_sample' & addz == TRUE)valid.in = aggregate(valid ~ pve+n_signal, dscout.finemap.in_sample, sum)
total.in = aggregate(DSC~ pve+n_signal, dscout.finemap.in_sample, length)
total.in$total_true = total.in$DSC * total.in$n_signal
power.finemap.in = merge(valid.in, total.in)
power.finemap.in$in_sample = round(power.finemap.in$valid/(power.finemap.in$total_true), 3)
power.finemap.in = power.finemap.in[,-c(3,4,5)]
valid.in.addz = aggregate(valid ~ pve+n_signal, dscout.finemap.in_sample.addz, sum)
total.in.addz = aggregate(DSC~ pve+n_signal, dscout.finemap.in_sample.addz, length)
total.in.addz$total_true = total.in.addz$DSC * total.in.addz$n_signal
power.finemap.in.addz = merge(valid.in.addz, total.in.addz)
power.finemap.in.addz$in_sample.addz = round(power.finemap.in.addz$valid/(power.finemap.in.addz$total_true), 3)
power.finemap.in.addz = power.finemap.in.addz[,-c(3,4,5)]
valid.out = aggregate(valid ~ pve+n_signal, dscout.finemap.out_sample, sum)
total.out = aggregate(DSC~ pve+n_signal, dscout.finemap.out_sample, length)
total.out$total_true = total.out$DSC * total.out$n_signal
power.finemap.out = merge(valid.out, total.out)
power.finemap.out$out_sample = round(power.finemap.out$valid/(power.finemap.out$total_true), 3)
power.finemap.out = power.finemap.out[,-c(3,4,5)]
valid.out.addz = aggregate(valid ~ pve+n_signal, dscout.finemap.out_sample.addz, sum)
total.out.addz = aggregate(DSC~ pve+n_signal, dscout.finemap.out_sample.addz, length)
total.out.addz$total_true = total.out.addz$DSC * total.out.addz$n_signal
power.finemap.out.addz = merge(valid.out.addz, total.out.addz)
power.finemap.out.addz$out_sample.addz = round(power.finemap.out.addz$valid/(power.finemap.out.addz$total_true), 3)
power.finemap.out.addz = power.finemap.out.addz[,-c(3,4,5)]
power.finemap = cbind(power.finemap.in, power.finemap.in.addz, power.finemap.out, power.finemap.out.addz)
power.finemap = power.finemap[,-c(4,5,7,8,10,11)]
power.finemap %>% kable() %>% kable_styling(bootstrap_options = c("striped", "condensed", "responsive","bordered"), full_width = F, repeat_header_continued = T)| pve | n_signal | in_sample | in_sample.addz | out_sample | out_sample.addz |
|---|---|---|---|---|---|
| 0.1 | 1 | 1.007 | 0.980 | 0.873 | 0.887 |
| 0.1 | 2 | 0.540 | 0.480 | 0.420 | 0.420 |
| 0.2 | 1 | 0.987 | 0.980 | 0.873 | 0.887 |
| 0.2 | 2 | 0.747 | 0.707 | 0.560 | 0.573 |
valid.in = aggregate(valid ~ pve+n_signal, dscout.finemap.in_sample, sum)
total.in = aggregate(total~ pve+n_signal, dscout.finemap.in_sample, sum)
fdr.in = merge(valid.in, total.in)
fdr.in$in_sample = round((fdr.in$total - fdr.in$valid)/fdr.in$total, 4)
fdr.in = fdr.in[,-c(3,4)]
valid.in.addz = aggregate(valid ~ pve+n_signal, dscout.finemap.in_sample.addz, sum)
total.in.addz = aggregate(total~ pve+n_signal, dscout.finemap.in_sample.addz, sum)
fdr.in.addz = merge(valid.in.addz, total.in.addz)
fdr.in.addz$in_sample = round((fdr.in.addz$total - fdr.in.addz$valid)/fdr.in.addz$total, 4)
fdr.in.addz = fdr.in.addz[,-c(3,4)]
valid.out = aggregate(valid ~ pve+n_signal, dscout.finemap.out_sample, sum)
total.out = aggregate(total~ pve+n_signal, dscout.finemap.out_sample, sum)
fdr.out = merge(valid.out, total.out)
fdr.out$out_sample = round((fdr.out$total - fdr.out$valid)/fdr.out$total, 4)
fdr.out = fdr.out[,-c(3,4)]
valid.out.addz = aggregate(valid ~ pve+n_signal, dscout.finemap.out_sample.addz, sum)
total.out.addz = aggregate(total~ pve+n_signal, dscout.finemap.out_sample.addz, sum)
fdr.out.addz = merge(valid.out.addz, total.out.addz)
fdr.out.addz$out_sample.addz = round((fdr.out.addz$total - fdr.out.addz$valid)/fdr.out.addz$total, 4)
fdr.out.addz = fdr.out.addz[,-c(3,4)]
fdr.finemap = cbind(fdr.in, fdr.in.addz, fdr.out, fdr.out.addz)
fdr.finemap = fdr.finemap[,-c(4,5,7,8,10,11)]
fdr.finemap %>% kable() %>% kable_styling(bootstrap_options = c("striped", "condensed", "responsive","bordered"), full_width = F, repeat_header_continued = T)| pve | n_signal | in_sample | in_sample.1 | out_sample | out_sample.addz |
|---|---|---|---|---|---|
| 0.1 | 1 | 0.0131 | 0.0200 | 0.5305 | 0.3448 |
| 0.1 | 2 | 0.0471 | 0.0828 | 0.6147 | 0.4857 |
| 0.2 | 1 | 0.0513 | 0.0200 | 0.6650 | 0.4527 |
| 0.2 | 2 | 0.0931 | 0.0979 | 0.6129 | 0.4452 |
dscout.susieb.in_sample = dscout.susiebhat %>% filter(ld_method == 'in_sample' & addz == FALSE & converged == 1)
dscout.susieb.in_sample.addz = dscout.susiebhat %>% filter(ld_method == 'in_sample' & addz == TRUE & converged == 1)
dscout.susieb.out_sample = dscout.susiebhat %>% filter(ld_method == 'out_sample' & addz == FALSE & converged == 1)
dscout.susieb.out_sample.addz = dscout.susiebhat %>% filter(ld_method == 'out_sample' & addz == TRUE & converged == 1)There are 3 models from susie_bhat fail to converge. There are 16 cases with out-sample R failed (out of 600). The estimated residual variance becomes negative.
converge.summary = aggregate(converged ~ ld_method + addz + estimate_residual_variance + L, dscout.susiebhat, sum)
converge.summary$Fail = 600 - converge.summary$converged
Fail = converge.summary[converge.summary$Fail!=0,]
row.names(Fail) = NULL
Fail[,-5] %>% kable() %>% kable_styling(bootstrap_options = c("striped", "condensed", "responsive"), full_width = F) | ld_method | addz | estimate_residual_variance | L | Fail |
|---|---|---|---|---|
| out_sample | FALSE | TRUE | 2 | 2 |
| out_sample | FALSE | FALSE | 5 | 3 |
| out_sample | FALSE | TRUE | 5 | 15 |
| out_sample | TRUE | TRUE | 5 | 1 |
Estimate residual variance
purity.susieb.in_sample = aggregate(purity~pve+n_signal, dscout.susieb.in_sample %>% filter(estimate_residual_variance==TRUE & L==5), mean)
colnames(purity.susieb.in_sample)[colnames(purity.susieb.in_sample) == 'purity'] <- 'in_sample'
purity.susieb.in_sample.addz = aggregate(purity~pve+n_signal, dscout.susieb.in_sample.addz %>% filter(estimate_residual_variance==TRUE & L==5), mean)
colnames(purity.susieb.in_sample.addz)[colnames(purity.susieb.in_sample.addz) == 'purity'] <- 'in_sample.addz'
purity.susieb.out_sample = aggregate(purity~pve+n_signal, dscout.susieb.out_sample %>% filter(estimate_residual_variance==TRUE & L==5), mean)
colnames(purity.susieb.out_sample)[colnames(purity.susieb.out_sample) == 'purity'] <- 'out_sample'
purity.susieb.out_sample.addz = aggregate(purity~pve+n_signal, dscout.susieb.out_sample.addz %>% filter(estimate_residual_variance==TRUE & L==5), mean)
colnames(purity.susieb.out_sample.addz)[colnames(purity.susieb.out_sample.addz) == 'purity'] <- 'out_sample.addz'
purity.susieb = cbind(purity.susieb.in_sample, purity.susieb.in_sample.addz, purity.susieb.out_sample, purity.susieb.out_sample.addz)
purity.susieb = purity.susieb[,-c(4,5,7,8,10,11)]
round(purity.susieb, 3) %>% kable() %>% kable_styling(bootstrap_options = c("striped", "condensed", "responsive"), full_width = F) | pve | n_signal | in_sample | in_sample.addz | out_sample | out_sample.addz |
|---|---|---|---|---|---|
| 0.1 | 1 | 0.751 | 0.762 | 0.768 | 0.762 |
| 0.2 | 1 | 0.956 | 0.964 | 0.947 | 0.956 |
| 0.1 | 2 | 0.460 | 0.404 | 0.440 | 0.404 |
| 0.2 | 2 | 0.898 | 0.850 | 0.902 | 0.862 |
l=5
valid.in = aggregate(valid ~ pve+n_signal, dscout.susieb.in_sample %>% filter(estimate_residual_variance==TRUE & L==l), sum)
total.in = aggregate(DSC~ pve+n_signal, dscout.susieb.in_sample %>% filter(estimate_residual_variance==TRUE & L==l), length)
total.in$total_true = total.in$DSC * total.in$n_signal
power.susieb.in = merge(valid.in, total.in)
power.susieb.in$in_sample = round(power.susieb.in$valid/(power.susieb.in$total_true), 3)
power.susieb.in = power.susieb.in[,-c(3,4,5)]
valid.in.addz = aggregate(valid ~ pve+n_signal, dscout.susieb.in_sample.addz %>% filter(estimate_residual_variance==TRUE & L==l), sum)
total.in.addz = aggregate(DSC~ pve+n_signal, dscout.susieb.in_sample.addz %>% filter(estimate_residual_variance==TRUE & L==l), length)
total.in.addz$total_true = total.in.addz$DSC * total.in.addz$n_signal
power.susieb.in.addz = merge(valid.in.addz, total.in.addz)
power.susieb.in.addz$in_sample.addz = round(power.susieb.in.addz$valid/(power.susieb.in.addz$total_true), 3)
power.susieb.in.addz = power.susieb.in.addz[,-c(3,4,5)]
valid.out = aggregate(valid ~ pve+n_signal, dscout.susieb.out_sample %>% filter(estimate_residual_variance==TRUE & L==l), sum)
total.out = aggregate(DSC~ pve+n_signal, dscout.susieb.out_sample%>% filter(estimate_residual_variance==TRUE & L==l), length)
total.out$total_true = total.out$DSC * total.out$n_signal
power.susieb.out = merge(valid.out, total.out)
power.susieb.out$out_sample = round(power.susieb.out$valid/(power.susieb.out$total_true), 3)
power.susieb.out = power.susieb.out[,-c(3,4,5)]
valid.out.addz = aggregate(valid ~ pve+n_signal, dscout.susieb.out_sample.addz %>% filter(estimate_residual_variance==TRUE & L==l), sum)
total.out.addz = aggregate(DSC~ pve+n_signal, dscout.susieb.out_sample.addz %>% filter(estimate_residual_variance==TRUE & L==l), length)
total.out.addz$total_true = total.out.addz$DSC * total.out.addz$n_signal
power.susieb.out.addz = merge(valid.out.addz, total.out.addz)
power.susieb.out.addz$out_sample.addz = round(power.susieb.out.addz$valid/(power.susieb.out.addz$total_true), 3)
power.susieb.out.addz = power.susieb.out.addz[,-c(3,4,5)]
power.susieb = cbind(power.susieb.in, power.susieb.in.addz, power.susieb.out, power.susieb.out.addz)
power.susieb = power.susieb[,-c(4,5,7,8,10,11)]
power.susieb %>% kable() %>% kable_styling(bootstrap_options = c("striped", "condensed", "responsive","bordered"), full_width = F, repeat_header_continued = T)| pve | n_signal | in_sample | in_sample.addz | out_sample | out_sample.addz |
|---|---|---|---|---|---|
| 0.1 | 1 | 0.833 | 0.847 | 0.865 | 0.859 |
| 0.1 | 2 | 0.267 | 0.217 | 0.235 | 0.207 |
| 0.2 | 1 | 0.973 | 0.973 | 0.958 | 0.967 |
| 0.2 | 2 | 0.733 | 0.657 | 0.656 | 0.630 |
l=5
valid.in = aggregate(valid ~ pve+n_signal, dscout.susieb.in_sample%>% filter(estimate_residual_variance==TRUE & L==l), sum)
total.in = aggregate(total~ pve+n_signal, dscout.susieb.in_sample%>% filter(estimate_residual_variance==TRUE & L==l), sum)
fdr.in = merge(valid.in, total.in)
fdr.in$in_sample = round((fdr.in$total - fdr.in$valid)/fdr.in$total, 4)
fdr.in = fdr.in[,-c(3,4)]
valid.in.addz = aggregate(valid ~ pve+n_signal, dscout.susieb.in_sample.addz %>% filter(estimate_residual_variance==TRUE & L==l), sum)
total.in.addz = aggregate(total~ pve+n_signal, dscout.susieb.in_sample.addz %>% filter(estimate_residual_variance==TRUE & L==l), sum)
fdr.in.addz = merge(valid.in.addz, total.in.addz)
fdr.in.addz$in_sample.addz = round((fdr.in.addz$total - fdr.in.addz$valid)/fdr.in.addz$total, 4)
fdr.in.addz = fdr.in.addz[,-c(3,4)]
valid.out = aggregate(valid ~ pve+n_signal, dscout.susieb.out_sample%>% filter(estimate_residual_variance==TRUE & L==l), sum)
total.out = aggregate(total~ pve+n_signal, dscout.susieb.out_sample%>% filter(estimate_residual_variance==TRUE & L==l), sum)
fdr.out = merge(valid.out, total.out)
fdr.out$out_sample = round((fdr.out$total - fdr.out$valid)/fdr.out$total, 4)
fdr.out = fdr.out[,-c(3,4)]
valid.out.addz = aggregate(valid ~ pve+n_signal, dscout.susieb.out_sample.addz%>% filter(estimate_residual_variance==TRUE & L==l), sum)
total.out.addz = aggregate(total~ pve+n_signal, dscout.susieb.out_sample.addz%>% filter(estimate_residual_variance==TRUE & L==l), sum)
fdr.out.addz = merge(valid.out.addz, total.out.addz)
fdr.out.addz$out_sample.addz = round((fdr.out.addz$total - fdr.out.addz$valid)/fdr.out.addz$total, 4)
fdr.out.addz = fdr.out.addz[,-c(3,4)]
fdr.susieb = cbind(fdr.in, fdr.in.addz,fdr.out, fdr.out.addz)
fdr.susieb = fdr.susieb[,-c(4,5,7,8,10,11)]
fdr.susieb %>% kable() %>% kable_styling(bootstrap_options = c("striped", "condensed", "responsive","bordered"), full_width = F, repeat_header_continued = T)| pve | n_signal | in_sample | in_sample.addz | out_sample | out_sample.addz |
|---|---|---|---|---|---|
| 0.1 | 1 | 0.0234 | 0.0231 | 0.2050 | 0.0725 |
| 0.1 | 2 | 0.1753 | 0.2073 | 0.3429 | 0.2439 |
| 0.2 | 1 | 0.0331 | 0.0267 | 0.4385 | 0.1761 |
| 0.2 | 2 | 0.1200 | 0.1205 | 0.3754 | 0.2125 |
dscout.susierss.in_sample = dscout.susierss %>% filter(ld_method == 'in_sample' & addz == FALSE & converged == 1 & lambda == 0)
dscout.susierss.in_sample.addz = dscout.susierss %>% filter(ld_method == 'in_sample' & addz == TRUE & converged == 1 & lambda == 0)
dscout.susierss.out_sample = dscout.susierss %>% filter(ld_method == 'out_sample' & addz == FALSE & converged == 1 & lambda == 0)
dscout.susierss.out_sample.addz = dscout.susierss %>% filter(ld_method == 'out_sample' & addz == TRUE & converged == 1 & lambda == 0)
dscout.susierss.in_sample.l1 = dscout.susierss %>% filter(ld_method == 'in_sample' & addz == FALSE & converged == 1 & lambda == 1e-4)
dscout.susierss.in_sample.addz.l1 = dscout.susierss %>% filter(ld_method == 'in_sample' & addz == TRUE & converged == 1 & lambda == 1e-4)
dscout.susierss.out_sample.l1 = dscout.susierss %>% filter(ld_method == 'out_sample' & addz == FALSE & converged == 1 & lambda == 1e-4)
dscout.susierss.out_sample.addz.l1 = dscout.susierss %>% filter(ld_method == 'out_sample' & addz == TRUE & converged == 1 & lambda == 1e-4)
dscout.susierss.in_sample.l2 = dscout.susierss %>% filter(ld_method == 'in_sample' & addz == FALSE & converged == 1 & lambda == 0.1)
dscout.susierss.in_sample.addz.l2 = dscout.susierss %>% filter(ld_method == 'in_sample' & addz == TRUE & converged == 1 & lambda == 0.1)
dscout.susierss.out_sample.l2 = dscout.susierss %>% filter(ld_method == 'out_sample' & addz == FALSE & converged == 1 & lambda == 0.1)
dscout.susierss.out_sample.addz.l2 = dscout.susierss %>% filter(ld_method == 'out_sample' & addz == TRUE & converged == 1 & lambda == 0.1)
dscout.susierss.in_sample.l3 = dscout.susierss %>% filter(ld_method == 'in_sample' & addz == FALSE & converged == 1 & lambda == 1)
dscout.susierss.in_sample.addz.l3 = dscout.susierss %>% filter(ld_method == 'in_sample' & addz == TRUE & converged == 1 & lambda == 1)
dscout.susierss.out_sample.l3 = dscout.susierss %>% filter(ld_method == 'out_sample' & addz == FALSE & converged == 1 & lambda == 1)
dscout.susierss.out_sample.addz.l3 = dscout.susierss %>% filter(ld_method == 'out_sample' & addz == TRUE & converged == 1 & lambda == 1)There are cases fail to converge in susie_rss.
converge.summary = aggregate(converged ~ ld_method + addz + estimate_residual_variance + lambda + L, dscout.susierss, sum)
converge.summary$NotConverge = 600 - converge.summary$converged
NotConverge = converge.summary[converge.summary$NotConverge!=0,]
row.names(NotConverge) = NULL
NotConverge[,-5] %>% kable() %>% kable_styling(bootstrap_options = c("striped", "condensed", "responsive"), full_width = F) | ld_method | addz | estimate_residual_variance | lambda | converged | NotConverge |
|---|---|---|---|---|---|
| out_sample | FALSE | FALSE | 0 | 598 | 2 |
| out_sample | FALSE | TRUE | 0 | 598 | 2 |
l = 5
purity.susierss.in_sample = round(aggregate(purity~pve+n_signal, dscout.susierss.in_sample%>% filter(estimate_residual_variance==TRUE & L == l), mean), 3)
colnames(purity.susierss.in_sample)[colnames(purity.susierss.in_sample) == 'purity'] <- 'in_sample'
purity.susierss.in_sample.addz = round(aggregate(purity~pve+n_signal, dscout.susierss.in_sample.addz%>% filter(estimate_residual_variance==TRUE & L == l), mean), 3)
colnames(purity.susierss.in_sample.addz)[colnames(purity.susierss.in_sample.addz) == 'purity'] <- 'in_sample.addz'
purity.susierss.out_sample = round(aggregate(purity~pve+n_signal, dscout.susierss.out_sample%>% filter(estimate_residual_variance==TRUE & L == l), mean), 3)
colnames(purity.susierss.out_sample)[colnames(purity.susierss.out_sample) == 'purity'] <- 'out_sample'
purity.susierss.out_sample.addz = round(aggregate(purity~pve+n_signal, dscout.susierss.out_sample.addz%>% filter(estimate_residual_variance==TRUE & L == l), mean), 3)
colnames(purity.susierss.out_sample.addz)[colnames(purity.susierss.out_sample.addz) == 'purity'] <- 'out_sample.addz'
purity.susierss.in_sample.l1 = round(aggregate(purity~pve+n_signal, dscout.susierss.in_sample.l1%>% filter(estimate_residual_variance==TRUE & L == l), mean), 3)
colnames(purity.susierss.in_sample.l1)[colnames(purity.susierss.in_sample.l1) == 'purity'] <- 'in_sample.l1'
purity.susierss.in_sample.addz.l1 = round(aggregate(purity~pve+n_signal, dscout.susierss.in_sample.addz.l1%>% filter(estimate_residual_variance==TRUE & L == l), mean), 3)
colnames(purity.susierss.in_sample.addz.l1)[colnames(purity.susierss.in_sample.addz.l1) == 'purity'] <- 'in_sample.addz'
purity.susierss.out_sample.l1 = round(aggregate(purity~pve+n_signal, dscout.susierss.out_sample.l1%>% filter(estimate_residual_variance==TRUE & L == l), mean), 3)
colnames(purity.susierss.out_sample.l1)[colnames(purity.susierss.out_sample.l1) == 'purity'] <- 'out_sample'
purity.susierss.out_sample.addz.l1 = round(aggregate(purity~pve+n_signal, dscout.susierss.out_sample.addz.l1%>% filter(estimate_residual_variance==TRUE & L == l), mean), 3)
colnames(purity.susierss.out_sample.addz.l1)[colnames(purity.susierss.out_sample.addz.l1) == 'purity'] <- 'out_sample.addz'
purity.susierss.in_sample.l2 = round(aggregate(purity~pve+n_signal, dscout.susierss.in_sample.l2%>% filter(estimate_residual_variance==TRUE & L == l), mean), 3)
colnames(purity.susierss.in_sample.l2)[colnames(purity.susierss.in_sample.l2) == 'purity'] <- 'in_sample'
purity.susierss.in_sample.addz.l2 = round(aggregate(purity~pve+n_signal, dscout.susierss.in_sample.addz.l2%>% filter(estimate_residual_variance==TRUE & L == l), mean), 3)
colnames(purity.susierss.in_sample.addz)[colnames(purity.susierss.in_sample.addz) == 'purity'] <- 'in_sample.addz'
purity.susierss.out_sample.l2 = round(aggregate(purity~pve+n_signal, dscout.susierss.out_sample.l2%>% filter(estimate_residual_variance==TRUE & L == l), mean), 3)
colnames(purity.susierss.out_sample.l2)[colnames(purity.susierss.out_sample.l2) == 'purity'] <- 'out_sample'
purity.susierss.out_sample.addz.l2 = round(aggregate(purity~pve+n_signal, dscout.susierss.out_sample.addz.l2%>% filter(estimate_residual_variance==TRUE & L == l), mean), 3)
colnames(purity.susierss.out_sample.addz.l2)[colnames(purity.susierss.out_sample.addz.l2) == 'purity'] <- 'out_sample.addz'
purity.susierss.in_sample.l3 = round(aggregate(purity~pve+n_signal, dscout.susierss.in_sample.l3%>% filter(estimate_residual_variance==TRUE & L == l), mean), 3)
colnames(purity.susierss.in_sample.l3)[colnames(purity.susierss.in_sample.l3) == 'purity'] <- 'in_sample'
purity.susierss.in_sample.addz.l3 = round(aggregate(purity~pve+n_signal, dscout.susierss.in_sample.addz.l3%>% filter(estimate_residual_variance==TRUE & L == l), mean), 3)
colnames(purity.susierss.in_sample.addz.l3)[colnames(purity.susierss.in_sample.addz.l3) == 'purity'] <- 'in_sample.addz'
purity.susierss.out_sample.l3 = round(aggregate(purity~pve+n_signal, dscout.susierss.out_sample.l3%>% filter(estimate_residual_variance==TRUE & L == l), mean), 3)
colnames(purity.susierss.out_sample.l3)[colnames(purity.susierss.out_sample.l3) == 'purity'] <- 'out_sample'
purity.susierss.out_sample.addz.l3 = round(aggregate(purity~pve+n_signal, dscout.susierss.out_sample.addz.l3%>% filter(estimate_residual_variance==TRUE & L == l), mean), 3)
colnames(purity.susierss.out_sample.addz.l3)[colnames(purity.susierss.out_sample.addz.l3) == 'purity'] <- 'out_sample.addz'
purity.susierss = cbind(purity.susierss.in_sample, purity.susierss.in_sample.addz, purity.susierss.out_sample, purity.susierss.out_sample.addz)
purity.susierss = purity.susierss[,-c(4,5,7,8,10,11)]
purity.susierss %>% kable() %>% kable_styling(bootstrap_options = c("striped", "condensed", "responsive"), full_width = F, repeat_header_continued = T) %>%
footnote(general = "lambda = 0")| pve | n_signal | in_sample | in_sample.addz | out_sample | out_sample.addz |
|---|---|---|---|---|---|
| 0.1 | 1 | 0.758 | 0.782 | 0.724 | 0.771 |
| 0.2 | 1 | 0.961 | 0.972 | 0.937 | 0.958 |
| 0.1 | 2 | 0.465 | 0.396 | 0.382 | 0.412 |
| 0.2 | 2 | 0.892 | 0.808 | 0.829 | 0.841 |
| Note: | |||||
| lambda = 0 |
purity.susierss = cbind(purity.susierss.in_sample.l1, purity.susierss.in_sample.addz.l1, purity.susierss.out_sample.l1, purity.susierss.out_sample.addz.l1)
purity.susierss = purity.susierss[,-c(4,5,7,8,10,11)]
purity.susierss %>% kable() %>% kable_styling(bootstrap_options = c("striped", "condensed", "responsive"), full_width = F, repeat_header_continued = T) %>%
footnote(general = "lambda = 1e-4")| pve | n_signal | in_sample.l1 | in_sample.addz | out_sample | out_sample.addz |
|---|---|---|---|---|---|
| 0.1 | 1 | 0.771 | 0.804 | 0.724 | 0.769 |
| 0.2 | 1 | 0.961 | 0.971 | 0.936 | 0.958 |
| 0.1 | 2 | 0.483 | 0.562 | 0.382 | 0.406 |
| 0.2 | 2 | 0.894 | 0.808 | 0.829 | 0.832 |
| Note: | |||||
| lambda = 1e-4 |
purity.susierss = cbind(purity.susierss.in_sample.l2, purity.susierss.in_sample.addz.l2, purity.susierss.out_sample.l2, purity.susierss.out_sample.addz.l2)
purity.susierss = purity.susierss[,-c(4,5,7,8,10,11)]
purity.susierss %>% kable() %>% kable_styling(bootstrap_options = c("striped", "condensed", "responsive"), full_width = F, repeat_header_continued = T) %>%
footnote(general = "lambda = 0.1")| pve | n_signal | in_sample | purity | out_sample | out_sample.addz |
|---|---|---|---|---|---|
| 0.1 | 1 | 0.854 | 0.931 | 0.664 | 0.768 |
| 0.2 | 1 | 0.966 | 0.977 | 0.927 | 0.952 |
| 0.1 | 2 | 0.599 | 0.819 | 0.347 | 0.424 |
| 0.2 | 2 | 0.919 | 0.942 | 0.818 | 0.828 |
| Note: | |||||
| lambda = 0.1 |
purity.susierss = cbind(purity.susierss.in_sample.l3, purity.susierss.in_sample.addz.l3, purity.susierss.out_sample.l3, purity.susierss.out_sample.addz.l3)
purity.susierss = purity.susierss[,-c(4,5,7,8,10,11)]
purity.susierss %>% kable() %>% kable_styling(bootstrap_options = c("striped", "condensed", "responsive"), full_width = F, repeat_header_continued = T) %>% footnote(general = "lambda = 1")| pve | n_signal | in_sample | in_sample.addz | out_sample | out_sample.addz |
|---|---|---|---|---|---|
| 0.1 | 1 | 0.846 | 0.902 | 0.735 | 0.832 |
| 0.2 | 1 | 0.962 | 0.972 | 0.912 | 0.943 |
| 0.1 | 2 | 0.636 | 0.768 | 0.518 | 0.592 |
| 0.2 | 2 | 0.903 | 0.929 | 0.829 | 0.859 |
| Note: | |||||
| lambda = 1 |
Estimate residual variance
l=5
est = TRUE
valid.in = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample%>% filter(estimate_residual_variance==est & L == l), sum)
total.in = aggregate(DSC~ pve+n_signal, dscout.susierss.in_sample%>% filter(estimate_residual_variance==est & L == l), length)
total.in$total_true = total.in$DSC * total.in$n_signal
power.susierss.in = merge(valid.in, total.in)
power.susierss.in$in_sample = round(power.susierss.in$valid/(power.susierss.in$total_true), 3)
power.susierss.in = power.susierss.in[,-c(3,4,5)]
valid.in.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.addz%>% filter(estimate_residual_variance==est & L == l), sum)
total.in.addz = aggregate(DSC~ pve+n_signal, dscout.susierss.in_sample.addz%>% filter(estimate_residual_variance==est & L == l), length)
total.in.addz$total_true = total.in.addz$DSC * total.in.addz$n_signal
power.susierss.in.addz = merge(valid.in.addz, total.in.addz)
power.susierss.in.addz$in_sample.addz = round(power.susierss.in.addz$valid/(power.susierss.in.addz$total_true), 3)
power.susierss.in.addz = power.susierss.in.addz[,-c(3,4,5)]
valid.out = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample%>% filter(estimate_residual_variance==est & L == l), sum)
total.out = aggregate(DSC~ pve+n_signal, dscout.susierss.out_sample%>% filter(estimate_residual_variance==est & L == l), length)
total.out$total_true = total.out$DSC * total.out$n_signal
power.susierss.out = merge(valid.out, total.out)
power.susierss.out$out_sample = round(power.susierss.out$valid/(power.susierss.out$total_true), 3)
power.susierss.out = power.susierss.out[,-c(3,4,5)]
valid.out.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.addz%>% filter(estimate_residual_variance==est & L == l), sum)
total.out.addz = aggregate(DSC~ pve+n_signal, dscout.susierss.out_sample.addz%>% filter(estimate_residual_variance==est & L == l), length)
total.out.addz$total_true = total.out.addz$DSC * total.out.addz$n_signal
power.susierss.out.addz = merge(valid.out.addz, total.out.addz)
power.susierss.out.addz$out_sample.addz = round(power.susierss.out.addz$valid/(power.susierss.out.addz$total_true), 3)
power.susierss.out.addz = power.susierss.out.addz[,-c(3,4,5)]
power.susierss = cbind(power.susierss.in, power.susierss.in.addz, power.susierss.out, power.susierss.out.addz)
power.susierss = power.susierss[,-c(4,5,7,8,10,11)]
power.susierss %>% kable() %>% kable_styling(bootstrap_options = c("striped", "condensed", "responsive","bordered"), full_width = F, repeat_header_continued=T) %>% footnote(general = "lambda = 0")| pve | n_signal | in_sample | in_sample.addz | out_sample | out_sample.addz |
|---|---|---|---|---|---|
| 0.1 | 1 | 0.827 | 0.860 | 0.753 | 0.860 |
| 0.1 | 2 | 0.263 | 0.193 | 0.201 | 0.210 |
| 0.2 | 1 | 0.953 | 0.973 | 0.813 | 0.953 |
| 0.2 | 2 | 0.733 | 0.557 | 0.574 | 0.607 |
| Note: | |||||
| lambda = 0 |
l=5
est = TRUE
valid.in = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.l1%>% filter(estimate_residual_variance==est & L == l), sum)
total.in = aggregate(DSC~ pve+n_signal, dscout.susierss.in_sample.l1%>% filter(estimate_residual_variance==est & L == l), length)
total.in$total_true = total.in$DSC * total.in$n_signal
power.susierss.in = merge(valid.in, total.in)
power.susierss.in$in_sample = round(power.susierss.in$valid/(power.susierss.in$total_true), 3)
power.susierss.in = power.susierss.in[,-c(3,4,5)]
valid.in.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.addz.l1%>% filter(estimate_residual_variance==est & L == l), sum)
total.in.addz = aggregate(DSC~ pve+n_signal, dscout.susierss.in_sample.addz.l1%>% filter(estimate_residual_variance==est & L == l), length)
total.in.addz$total_true = total.in.addz$DSC * total.in.addz$n_signal
power.susierss.in.addz = merge(valid.in.addz, total.in.addz)
power.susierss.in.addz$in_sample.addz = round(power.susierss.in.addz$valid/(power.susierss.in.addz$total_true), 3)
power.susierss.in.addz = power.susierss.in.addz[,-c(3,4,5)]
valid.out = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.l1%>% filter(estimate_residual_variance==est & L == l), sum)
total.out = aggregate(DSC~ pve+n_signal, dscout.susierss.out_sample.l1%>% filter(estimate_residual_variance==est & L == l), length)
total.out$total_true = total.out$DSC * total.out$n_signal
power.susierss.out = merge(valid.out, total.out)
power.susierss.out$out_sample = round(power.susierss.out$valid/(power.susierss.out$total_true), 3)
power.susierss.out = power.susierss.out[,-c(3,4,5)]
valid.out.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.addz.l1%>% filter(estimate_residual_variance==est & L == l), sum)
total.out.addz = aggregate(DSC~ pve+n_signal, dscout.susierss.out_sample.addz.l1%>% filter(estimate_residual_variance==est & L == l), length)
total.out.addz$total_true = total.out.addz$DSC * total.out.addz$n_signal
power.susierss.out.addz = merge(valid.out.addz, total.out.addz)
power.susierss.out.addz$out_sample.addz = round(power.susierss.out.addz$valid/(power.susierss.out.addz$total_true), 3)
power.susierss.out.addz = power.susierss.out.addz[,-c(3,4,5)]
power.susierss = cbind(power.susierss.in, power.susierss.in.addz, power.susierss.out, power.susierss.out.addz)
power.susierss = power.susierss[,-c(4,5,7,8,10,11)]
power.susierss %>% kable() %>% kable_styling(bootstrap_options = c("striped", "condensed", "responsive","bordered"), full_width = F, repeat_header_continued=T) %>% footnote(general = "lambda = 1e-4")| pve | n_signal | in_sample | in_sample.addz | out_sample | out_sample.addz |
|---|---|---|---|---|---|
| 0.1 | 1 | 0.847 | 0.873 | 0.753 | 0.860 |
| 0.1 | 2 | 0.267 | 0.307 | 0.203 | 0.210 |
| 0.2 | 1 | 0.960 | 0.960 | 0.807 | 0.953 |
| 0.2 | 2 | 0.730 | 0.570 | 0.583 | 0.597 |
| Note: | |||||
| lambda = 1e-4 |
l=5
est = TRUE
valid.in = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.l2%>% filter(estimate_residual_variance==est & L == l), sum)
total.in = aggregate(DSC~ pve+n_signal, dscout.susierss.in_sample.l2%>% filter(estimate_residual_variance==est & L == l), length)
total.in$total_true = total.in$DSC * total.in$n_signal
power.susierss.in = merge(valid.in, total.in)
power.susierss.in$in_sample = round(power.susierss.in$valid/(power.susierss.in$total_true), 3)
power.susierss.in = power.susierss.in[,-c(3,4,5)]
valid.in.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.addz.l2%>% filter(estimate_residual_variance==est & L == l), sum)
total.in.addz = aggregate(DSC~ pve+n_signal, dscout.susierss.in_sample.addz.l2%>% filter(estimate_residual_variance==est & L == l), length)
total.in.addz$total_true = total.in.addz$DSC * total.in.addz$n_signal
power.susierss.in.addz = merge(valid.in.addz, total.in.addz)
power.susierss.in.addz$in_sample.addz = round(power.susierss.in.addz$valid/(power.susierss.in.addz$total_true), 3)
power.susierss.in.addz = power.susierss.in.addz[,-c(3,4,5)]
valid.out = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.l2%>% filter(estimate_residual_variance==est & L == l), sum)
total.out = aggregate(DSC~ pve+n_signal, dscout.susierss.out_sample.l2%>% filter(estimate_residual_variance==est & L == l), length)
total.out$total_true = total.out$DSC * total.out$n_signal
power.susierss.out = merge(valid.out, total.out)
power.susierss.out$out_sample = round(power.susierss.out$valid/(power.susierss.out$total_true), 3)
power.susierss.out = power.susierss.out[,-c(3,4,5)]
valid.out.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.addz.l2%>% filter(estimate_residual_variance==est & L == l), sum)
total.out.addz = aggregate(DSC~ pve+n_signal, dscout.susierss.out_sample.addz.l2%>% filter(estimate_residual_variance==est & L == l), length)
total.out.addz$total_true = total.out.addz$DSC * total.out.addz$n_signal
power.susierss.out.addz = merge(valid.out.addz, total.out.addz)
power.susierss.out.addz$out_sample.addz = round(power.susierss.out.addz$valid/(power.susierss.out.addz$total_true), 3)
power.susierss.out.addz = power.susierss.out.addz[,-c(3,4,5)]
power.susierss = cbind(power.susierss.in, power.susierss.in.addz, power.susierss.out, power.susierss.out.addz)
power.susierss = power.susierss[,-c(4,5,7,8,10,11)]
power.susierss %>% kable() %>% kable_styling(bootstrap_options = c("striped", "condensed", "responsive","bordered"), full_width = F, repeat_header_continued=T) %>% footnote(general = "lambda = 0.1")| pve | n_signal | in_sample | in_sample.addz | out_sample | out_sample.addz |
|---|---|---|---|---|---|
| 0.1 | 1 | 0.880 | 0.880 | 0.740 | 0.867 |
| 0.1 | 2 | 0.347 | 0.477 | 0.180 | 0.223 |
| 0.2 | 1 | 0.933 | 0.900 | 0.907 | 0.980 |
| 0.2 | 2 | 0.743 | 0.753 | 0.560 | 0.623 |
| Note: | |||||
| lambda = 0.1 |
l=5
est = TRUE
valid.in = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.l3%>% filter(estimate_residual_variance==est & L == l), sum)
total.in = aggregate(DSC~ pve+n_signal, dscout.susierss.in_sample.l3%>% filter(estimate_residual_variance==est & L == l), length)
total.in$total_true = total.in$DSC * total.in$n_signal
power.susierss.in = merge(valid.in, total.in)
power.susierss.in$in_sample = round(power.susierss.in$valid/(power.susierss.in$total_true), 3)
power.susierss.in = power.susierss.in[,-c(3,4,5)]
valid.in.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.addz.l3%>% filter(estimate_residual_variance==est & L == l), sum)
total.in.addz = aggregate(DSC~ pve+n_signal, dscout.susierss.in_sample.addz.l3%>% filter(estimate_residual_variance==est & L == l), length)
total.in.addz$total_true = total.in.addz$DSC * total.in.addz$n_signal
power.susierss.in.addz = merge(valid.in.addz, total.in.addz)
power.susierss.in.addz$in_sample.addz = round(power.susierss.in.addz$valid/(power.susierss.in.addz$total_true), 3)
power.susierss.in.addz = power.susierss.in.addz[,-c(3,4,5)]
valid.out = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.l3%>% filter(estimate_residual_variance==est & L == l), sum)
total.out = aggregate(DSC~ pve+n_signal, dscout.susierss.out_sample.l3%>% filter(estimate_residual_variance==est & L == l), length)
total.out$total_true = total.out$DSC * total.out$n_signal
power.susierss.out = merge(valid.out, total.out)
power.susierss.out$out_sample = round(power.susierss.out$valid/(power.susierss.out$total_true), 3)
power.susierss.out = power.susierss.out[,-c(3,4,5)]
valid.out.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.addz.l3%>% filter(estimate_residual_variance==est & L == l), sum)
total.out.addz = aggregate(DSC~ pve+n_signal, dscout.susierss.out_sample.addz.l3%>% filter(estimate_residual_variance==est & L == l), length)
total.out.addz$total_true = total.out.addz$DSC * total.out.addz$n_signal
power.susierss.out.addz = merge(valid.out.addz, total.out.addz)
power.susierss.out.addz$out_sample.addz = round(power.susierss.out.addz$valid/(power.susierss.out.addz$total_true), 3)
power.susierss.out.addz = power.susierss.out.addz[,-c(3,4,5)]
power.susierss = cbind(power.susierss.in, power.susierss.in.addz, power.susierss.out, power.susierss.out.addz)
power.susierss = power.susierss[,-c(4,5,7,8,10,11)]
power.susierss %>% kable() %>% kable_styling(bootstrap_options = c("striped", "condensed", "responsive","bordered"), full_width = F, repeat_header_continued=T) %>% footnote(general = "lambda = 1")| pve | n_signal | in_sample | in_sample.addz | out_sample | out_sample.addz |
|---|---|---|---|---|---|
| 0.1 | 1 | 0.867 | 0.900 | 0.780 | 0.880 |
| 0.1 | 2 | 0.380 | 0.477 | 0.273 | 0.330 |
| 0.2 | 1 | 0.947 | 0.927 | 0.907 | 0.967 |
| 0.2 | 2 | 0.747 | 0.760 | 0.597 | 0.683 |
| Note: | |||||
| lambda = 1 |
NOT estimate residual variance
l=5
est = FALSE
valid.in = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample%>% filter(estimate_residual_variance==est & L == l), sum)
total.in = aggregate(DSC~ pve+n_signal, dscout.susierss.in_sample%>% filter(estimate_residual_variance==est & L == l), length)
total.in$total_true = total.in$DSC * total.in$n_signal
power.susierss.in = merge(valid.in, total.in)
power.susierss.in$in_sample = round(power.susierss.in$valid/(power.susierss.in$total_true), 3)
power.susierss.in = power.susierss.in[,-c(3,4,5)]
valid.in.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.addz%>% filter(estimate_residual_variance==est & L == l), sum)
total.in.addz = aggregate(DSC~ pve+n_signal, dscout.susierss.in_sample.addz%>% filter(estimate_residual_variance==est & L == l), length)
total.in.addz$total_true = total.in.addz$DSC * total.in.addz$n_signal
power.susierss.in.addz = merge(valid.in.addz, total.in.addz)
power.susierss.in.addz$in_sample.addz = round(power.susierss.in.addz$valid/(power.susierss.in.addz$total_true), 3)
power.susierss.in.addz = power.susierss.in.addz[,-c(3,4,5)]
valid.out = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample%>% filter(estimate_residual_variance==est & L == l), sum)
total.out = aggregate(DSC~ pve+n_signal, dscout.susierss.out_sample%>% filter(estimate_residual_variance==est & L == l), length)
total.out$total_true = total.out$DSC * total.out$n_signal
power.susierss.out = merge(valid.out, total.out)
power.susierss.out$out_sample = round(power.susierss.out$valid/(power.susierss.out$total_true), 3)
power.susierss.out = power.susierss.out[,-c(3,4,5)]
valid.out.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.addz%>% filter(estimate_residual_variance==est & L == l), sum)
total.out.addz = aggregate(DSC~ pve+n_signal, dscout.susierss.out_sample.addz%>% filter(estimate_residual_variance==est & L == l), length)
total.out.addz$total_true = total.out.addz$DSC * total.out.addz$n_signal
power.susierss.out.addz = merge(valid.out.addz, total.out.addz)
power.susierss.out.addz$out_sample.addz = round(power.susierss.out.addz$valid/(power.susierss.out.addz$total_true), 3)
power.susierss.out.addz = power.susierss.out.addz[,-c(3,4,5)]
power.susierss = cbind(power.susierss.in, power.susierss.in.addz, power.susierss.out, power.susierss.out.addz)
power.susierss = power.susierss[,-c(4,5,7,8,10,11)]
power.susierss %>% kable() %>% kable_styling(bootstrap_options = c("striped", "condensed", "responsive","bordered"), full_width = F, repeat_header_continued=T) %>% footnote(general = "lambda = 0")| pve | n_signal | in_sample | in_sample.addz | out_sample | out_sample.addz |
|---|---|---|---|---|---|
| 0.1 | 1 | 0.820 | 0.860 | 0.753 | 0.860 |
| 0.1 | 2 | 0.243 | 0.193 | 0.201 | 0.200 |
| 0.2 | 1 | 0.953 | 0.973 | 0.813 | 0.953 |
| 0.2 | 2 | 0.690 | 0.557 | 0.574 | 0.563 |
| Note: | |||||
| lambda = 0 |
l=5
est = FALSE
valid.in = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.l1%>% filter(estimate_residual_variance==est & L == l), sum)
total.in = aggregate(DSC~ pve+n_signal, dscout.susierss.in_sample.l1%>% filter(estimate_residual_variance==est & L == l), length)
total.in$total_true = total.in$DSC * total.in$n_signal
power.susierss.in = merge(valid.in, total.in)
power.susierss.in$in_sample = round(power.susierss.in$valid/(power.susierss.in$total_true), 3)
power.susierss.in = power.susierss.in[,-c(3,4,5)]
valid.in.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.addz.l1%>% filter(estimate_residual_variance==est & L == l), sum)
total.in.addz = aggregate(DSC~ pve+n_signal, dscout.susierss.in_sample.addz.l1%>% filter(estimate_residual_variance==est & L == l), length)
total.in.addz$total_true = total.in.addz$DSC * total.in.addz$n_signal
power.susierss.in.addz = merge(valid.in.addz, total.in.addz)
power.susierss.in.addz$in_sample.addz = round(power.susierss.in.addz$valid/(power.susierss.in.addz$total_true), 3)
power.susierss.in.addz = power.susierss.in.addz[,-c(3,4,5)]
valid.out = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.l1%>% filter(estimate_residual_variance==est & L == l), sum)
total.out = aggregate(DSC~ pve+n_signal, dscout.susierss.out_sample.l1%>% filter(estimate_residual_variance==est & L == l), length)
total.out$total_true = total.out$DSC * total.out$n_signal
power.susierss.out = merge(valid.out, total.out)
power.susierss.out$out_sample = round(power.susierss.out$valid/(power.susierss.out$total_true), 3)
power.susierss.out = power.susierss.out[,-c(3,4,5)]
valid.out.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.addz.l1%>% filter(estimate_residual_variance==est & L == l), sum)
total.out.addz = aggregate(DSC~ pve+n_signal, dscout.susierss.out_sample.addz.l1%>% filter(estimate_residual_variance==est & L == l), length)
total.out.addz$total_true = total.out.addz$DSC * total.out.addz$n_signal
power.susierss.out.addz = merge(valid.out.addz, total.out.addz)
power.susierss.out.addz$out_sample.addz = round(power.susierss.out.addz$valid/(power.susierss.out.addz$total_true), 3)
power.susierss.out.addz = power.susierss.out.addz[,-c(3,4,5)]
power.susierss = cbind(power.susierss.in, power.susierss.in.addz, power.susierss.out, power.susierss.out.addz)
power.susierss = power.susierss[,-c(4,5,7,8,10,11)]
power.susierss %>% kable() %>% kable_styling(bootstrap_options = c("striped", "condensed", "responsive","bordered"), full_width = F, repeat_header_continued=T) %>% footnote(general = "lambda = 1e-4")| pve | n_signal | in_sample | in_sample.addz | out_sample | out_sample.addz |
|---|---|---|---|---|---|
| 0.1 | 1 | 0.827 | 0.847 | 0.753 | 0.860 |
| 0.1 | 2 | 0.243 | 0.193 | 0.203 | 0.200 |
| 0.2 | 1 | 0.960 | 0.967 | 0.807 | 0.953 |
| 0.2 | 2 | 0.690 | 0.553 | 0.583 | 0.563 |
| Note: | |||||
| lambda = 1e-4 |
l=5
est = FALSE
valid.in = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.l2%>% filter(estimate_residual_variance==est & L == l), sum)
total.in = aggregate(DSC~ pve+n_signal, dscout.susierss.in_sample.l2%>% filter(estimate_residual_variance==est & L == l), length)
total.in$total_true = total.in$DSC * total.in$n_signal
power.susierss.in = merge(valid.in, total.in)
power.susierss.in$in_sample = round(power.susierss.in$valid/(power.susierss.in$total_true), 3)
power.susierss.in = power.susierss.in[,-c(3,4,5)]
valid.in.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.addz.l2%>% filter(estimate_residual_variance==est & L == l), sum)
total.in.addz = aggregate(DSC~ pve+n_signal, dscout.susierss.in_sample.addz.l2%>% filter(estimate_residual_variance==est & L == l), length)
total.in.addz$total_true = total.in.addz$DSC * total.in.addz$n_signal
power.susierss.in.addz = merge(valid.in.addz, total.in.addz)
power.susierss.in.addz$in_sample.addz = round(power.susierss.in.addz$valid/(power.susierss.in.addz$total_true), 3)
power.susierss.in.addz = power.susierss.in.addz[,-c(3,4,5)]
valid.out = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.l2%>% filter(estimate_residual_variance==est & L == l), sum)
total.out = aggregate(DSC~ pve+n_signal, dscout.susierss.out_sample.l2%>% filter(estimate_residual_variance==est & L == l), length)
total.out$total_true = total.out$DSC * total.out$n_signal
power.susierss.out = merge(valid.out, total.out)
power.susierss.out$out_sample = round(power.susierss.out$valid/(power.susierss.out$total_true), 3)
power.susierss.out = power.susierss.out[,-c(3,4,5)]
valid.out.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.addz.l2%>% filter(estimate_residual_variance==est & L == l), sum)
total.out.addz = aggregate(DSC~ pve+n_signal, dscout.susierss.out_sample.addz.l2%>% filter(estimate_residual_variance==est & L == l), length)
total.out.addz$total_true = total.out.addz$DSC * total.out.addz$n_signal
power.susierss.out.addz = merge(valid.out.addz, total.out.addz)
power.susierss.out.addz$out_sample.addz = round(power.susierss.out.addz$valid/(power.susierss.out.addz$total_true), 3)
power.susierss.out.addz = power.susierss.out.addz[,-c(3,4,5)]
power.susierss = cbind(power.susierss.in, power.susierss.in.addz, power.susierss.out, power.susierss.out.addz)
power.susierss = power.susierss[,-c(4,5,7,8,10,11)]
power.susierss %>% kable() %>% kable_styling(bootstrap_options = c("striped", "condensed", "responsive","bordered"), full_width = F, repeat_header_continued=T) %>% footnote(general = "lambda = 0.1")| pve | n_signal | in_sample | in_sample.addz | out_sample | out_sample.addz |
|---|---|---|---|---|---|
| 0.1 | 1 | 0.800 | 0.813 | 0.740 | 0.847 |
| 0.1 | 2 | 0.220 | 0.187 | 0.177 | 0.190 |
| 0.2 | 1 | 0.973 | 0.980 | 0.907 | 0.987 |
| 0.2 | 2 | 0.693 | 0.577 | 0.557 | 0.553 |
| Note: | |||||
| lambda = 0.1 |
l=5
est = FALSE
valid.in = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.l3%>% filter(estimate_residual_variance==est & L == l), sum)
total.in = aggregate(DSC~ pve+n_signal, dscout.susierss.in_sample.l3%>% filter(estimate_residual_variance==est & L == l), length)
total.in$total_true = total.in$DSC * total.in$n_signal
power.susierss.in = merge(valid.in, total.in)
power.susierss.in$in_sample = round(power.susierss.in$valid/(power.susierss.in$total_true), 3)
power.susierss.in = power.susierss.in[,-c(3,4,5)]
valid.in.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.addz.l3%>% filter(estimate_residual_variance==est & L == l), sum)
total.in.addz = aggregate(DSC~ pve+n_signal, dscout.susierss.in_sample.addz.l3%>% filter(estimate_residual_variance==est & L == l), length)
total.in.addz$total_true = total.in.addz$DSC * total.in.addz$n_signal
power.susierss.in.addz = merge(valid.in.addz, total.in.addz)
power.susierss.in.addz$in_sample.addz = round(power.susierss.in.addz$valid/(power.susierss.in.addz$total_true), 3)
power.susierss.in.addz = power.susierss.in.addz[,-c(3,4,5)]
valid.out = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.l3%>% filter(estimate_residual_variance==est & L == l), sum)
total.out = aggregate(DSC~ pve+n_signal, dscout.susierss.out_sample.l3%>% filter(estimate_residual_variance==est & L == l), length)
total.out$total_true = total.out$DSC * total.out$n_signal
power.susierss.out = merge(valid.out, total.out)
power.susierss.out$out_sample = round(power.susierss.out$valid/(power.susierss.out$total_true), 3)
power.susierss.out = power.susierss.out[,-c(3,4,5)]
valid.out.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.addz.l3%>% filter(estimate_residual_variance==est & L == l), sum)
total.out.addz = aggregate(DSC~ pve+n_signal, dscout.susierss.out_sample.addz.l3%>% filter(estimate_residual_variance==est & L == l), length)
total.out.addz$total_true = total.out.addz$DSC * total.out.addz$n_signal
power.susierss.out.addz = merge(valid.out.addz, total.out.addz)
power.susierss.out.addz$out_sample.addz = round(power.susierss.out.addz$valid/(power.susierss.out.addz$total_true), 3)
power.susierss.out.addz = power.susierss.out.addz[,-c(3,4,5)]
power.susierss = cbind(power.susierss.in, power.susierss.in.addz, power.susierss.out, power.susierss.out.addz)
power.susierss = power.susierss[,-c(4,5,7,8,10,11)]
power.susierss %>% kable() %>% kable_styling(bootstrap_options = c("striped", "condensed", "responsive","bordered"), full_width = F, repeat_header_continued=T) %>% footnote(general = "lambda = 1")| pve | n_signal | in_sample | in_sample.addz | out_sample | out_sample.addz |
|---|---|---|---|---|---|
| 0.1 | 1 | 0.767 | 0.767 | 0.680 | 0.800 |
| 0.1 | 2 | 0.203 | 0.167 | 0.170 | 0.160 |
| 0.2 | 1 | 0.993 | 1.000 | 0.933 | 0.993 |
| 0.2 | 2 | 0.587 | 0.513 | 0.480 | 0.510 |
| Note: | |||||
| lambda = 1 |
Estimate residual variance
l = 5
est = TRUE
valid.in = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample%>% filter(estimate_residual_variance==est & L == l), sum)
total.in = aggregate(total~ pve+n_signal, dscout.susierss.in_sample%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.in = merge(valid.in, total.in)
fdr.in$in_sample = round((fdr.in$total - fdr.in$valid)/fdr.in$total, 4)
fdr.in = fdr.in[,-c(3,4)]
valid.in.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.addz%>% filter(estimate_residual_variance==est & L == l), sum)
total.in.addz = aggregate(total~ pve+n_signal, dscout.susierss.in_sample.addz%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.in.addz = merge(valid.in.addz, total.in.addz)
fdr.in.addz$in_sample.addz = round((fdr.in.addz$total - fdr.in.addz$valid)/fdr.in.addz$total, 4)
fdr.in.addz = fdr.in.addz[,-c(3,4)]
valid.out = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample%>% filter(estimate_residual_variance==est & L == l), sum)
total.out = aggregate(total~ pve+n_signal, dscout.susierss.out_sample%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.out = merge(valid.out, total.out)
fdr.out$out_sample = round((fdr.out$total - fdr.out$valid)/fdr.out$total, 4)
fdr.out = fdr.out[,-c(3,4)]
valid.out.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.addz%>% filter(estimate_residual_variance==est & L == l), sum)
total.out.addz = aggregate(total~ pve+n_signal, dscout.susierss.out_sample.addz%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.out.addz = merge(valid.out.addz, total.out.addz)
fdr.out.addz$out_sample.addz = round((fdr.out.addz$total - fdr.out.addz$valid)/fdr.out.addz$total, 4)
fdr.out.addz = fdr.out.addz[,-c(3,4)]
fdr.susierss = cbind(fdr.in, fdr.in.addz, fdr.out, fdr.out.addz)
fdr.susierss = fdr.susierss[,-c(4,5,7,8,10,11)]
fdr.susierss %>% kable() %>% kable_styling(bootstrap_options = c("striped", "condensed", "responsive","bordered"), full_width = F, repeat_header_continued=T) %>% footnote(general = "lambda = 0")| pve | n_signal | in_sample | in_sample.addz | out_sample | out_sample.addz |
|---|---|---|---|---|---|
| 0.1 | 1 | 0.0388 | 0.0227 | 0.1504 | 0.0915 |
| 0.1 | 2 | 0.1856 | 0.2468 | 0.2593 | 0.2317 |
| 0.2 | 1 | 0.0467 | 0.0267 | 0.2561 | 0.1538 |
| 0.2 | 2 | 0.1200 | 0.1566 | 0.2366 | 0.1947 |
| Note: | |||||
| lambda = 0 |
l = 5
est = TRUE
valid.in = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.l1%>% filter(estimate_residual_variance==est & L == l), sum)
total.in = aggregate(total~ pve+n_signal, dscout.susierss.in_sample.l1%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.in = merge(valid.in, total.in)
fdr.in$in_sample = round((fdr.in$total - fdr.in$valid)/fdr.in$total, 4)
fdr.in = fdr.in[,-c(3,4)]
valid.in.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.addz.l1%>% filter(estimate_residual_variance==est & L == l), sum)
total.in.addz = aggregate(total~ pve+n_signal, dscout.susierss.in_sample.addz.l1%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.in.addz = merge(valid.in.addz, total.in.addz)
fdr.in.addz$in_sample.addz = round((fdr.in.addz$total - fdr.in.addz$valid)/fdr.in.addz$total, 4)
fdr.in.addz = fdr.in.addz[,-c(3,4)]
valid.out = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.l1%>% filter(estimate_residual_variance==est & L == l), sum)
total.out = aggregate(total~ pve+n_signal, dscout.susierss.out_sample.l1%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.out = merge(valid.out, total.out)
fdr.out$out_sample = round((fdr.out$total - fdr.out$valid)/fdr.out$total, 4)
fdr.out = fdr.out[,-c(3,4)]
valid.out.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.addz.l1%>% filter(estimate_residual_variance==est & L == l), sum)
total.out.addz = aggregate(total~ pve+n_signal, dscout.susierss.out_sample.addz.l1%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.out.addz = merge(valid.out.addz, total.out.addz)
fdr.out.addz$out_sample.addz = round((fdr.out.addz$total - fdr.out.addz$valid)/fdr.out.addz$total, 4)
fdr.out.addz = fdr.out.addz[,-c(3,4)]
fdr.susierss = cbind(fdr.in, fdr.in.addz, fdr.out, fdr.out.addz)
fdr.susierss = fdr.susierss[,-c(4,5,7,8,10,11)]
fdr.susierss %>% kable() %>% kable_styling(bootstrap_options = c("striped", "condensed", "responsive","bordered"), full_width = F, repeat_header_continued=T) %>% footnote(general = "lambda = 1e-4")| pve | n_signal | in_sample | in_sample.addz | out_sample | out_sample.addz |
|---|---|---|---|---|---|
| 0.1 | 1 | 0.0305 | 0.0296 | 0.1504 | 0.0915 |
| 0.1 | 2 | 0.1919 | 0.2137 | 0.2469 | 0.2410 |
| 0.2 | 1 | 0.0400 | 0.0400 | 0.2484 | 0.1538 |
| 0.2 | 2 | 0.1205 | 0.1450 | 0.2325 | 0.2149 |
| Note: | |||||
| lambda = 1e-4 |
l = 5
est = TRUE
valid.in = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.l2%>% filter(estimate_residual_variance==est & L == l), sum)
total.in = aggregate(total~ pve+n_signal, dscout.susierss.in_sample.l2%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.in = merge(valid.in, total.in)
fdr.in$in_sample = round((fdr.in$total - fdr.in$valid)/fdr.in$total, 4)
fdr.in = fdr.in[,-c(3,4)]
valid.in.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.addz.l2%>% filter(estimate_residual_variance==est & L == l), sum)
total.in.addz = aggregate(total~ pve+n_signal, dscout.susierss.in_sample.addz.l2%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.in.addz = merge(valid.in.addz, total.in.addz)
fdr.in.addz$in_sample.addz = round((fdr.in.addz$total - fdr.in.addz$valid)/fdr.in.addz$total, 4)
fdr.in.addz = fdr.in.addz[,-c(3,4)]
valid.out = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.l2%>% filter(estimate_residual_variance==est & L == l), sum)
total.out = aggregate(total~ pve+n_signal, dscout.susierss.out_sample.l2%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.out = merge(valid.out, total.out)
fdr.out$out_sample = round((fdr.out$total - fdr.out$valid)/fdr.out$total, 4)
fdr.out = fdr.out[,-c(3,4)]
valid.out.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.addz.l2%>% filter(estimate_residual_variance==est & L == l), sum)
total.out.addz = aggregate(total~ pve+n_signal, dscout.susierss.out_sample.addz.l2%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.out.addz = merge(valid.out.addz, total.out.addz)
fdr.out.addz$out_sample.addz = round((fdr.out.addz$total - fdr.out.addz$valid)/fdr.out.addz$total, 4)
fdr.out.addz = fdr.out.addz[,-c(3,4)]
fdr.susierss = cbind(fdr.in, fdr.in.addz, fdr.out, fdr.out.addz)
fdr.susierss = fdr.susierss[,-c(4,5,7,8,10,11)]
fdr.susierss %>% kable() %>% kable_styling(bootstrap_options = c("striped", "condensed", "responsive","bordered"), full_width = F, repeat_header_continued=T) %>% footnote(general = "lambda = 0.1")| pve | n_signal | in_sample | in_sample.addz | out_sample | out_sample.addz |
|---|---|---|---|---|---|
| 0.1 | 1 | 0.0897 | 0.1951 | 0.1048 | 0.0370 |
| 0.1 | 2 | 0.2239 | 0.3158 | 0.2603 | 0.2209 |
| 0.2 | 1 | 0.0850 | 0.1718 | 0.1392 | 0.0870 |
| 0.2 | 2 | 0.1553 | 0.2014 | 0.2000 | 0.1343 |
| Note: | |||||
| lambda = 0.1 |
l = 5
est = TRUE
valid.in = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.l3%>% filter(estimate_residual_variance==est & L == l), sum)
total.in = aggregate(total~ pve+n_signal, dscout.susierss.in_sample.l3%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.in = merge(valid.in, total.in)
fdr.in$in_sample = round((fdr.in$total - fdr.in$valid)/fdr.in$total, 4)
fdr.in = fdr.in[,-c(3,4)]
valid.in.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.addz.l3%>% filter(estimate_residual_variance==est & L == l), sum)
total.in.addz = aggregate(total~ pve+n_signal, dscout.susierss.in_sample.addz.l3%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.in.addz = merge(valid.in.addz, total.in.addz)
fdr.in.addz$in_sample.addz = round((fdr.in.addz$total - fdr.in.addz$valid)/fdr.in.addz$total, 4)
fdr.in.addz = fdr.in.addz[,-c(3,4)]
valid.out = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.l3%>% filter(estimate_residual_variance==est & L == l), sum)
total.out = aggregate(total~ pve+n_signal, dscout.susierss.out_sample.l3%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.out = merge(valid.out, total.out)
fdr.out$out_sample = round((fdr.out$total - fdr.out$valid)/fdr.out$total, 4)
fdr.out = fdr.out[,-c(3,4)]
valid.out.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.addz.l3%>% filter(estimate_residual_variance==est & L == l), sum)
total.out.addz = aggregate(total~ pve+n_signal, dscout.susierss.out_sample.addz.l3%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.out.addz = merge(valid.out.addz, total.out.addz)
fdr.out.addz$out_sample.addz = round((fdr.out.addz$total - fdr.out.addz$valid)/fdr.out.addz$total, 4)
fdr.out.addz = fdr.out.addz[,-c(3,4)]
fdr.susierss = cbind(fdr.in, fdr.in.addz, fdr.out, fdr.out.addz)
fdr.susierss = fdr.susierss[,-c(4,5,7,8,10,11)]
fdr.susierss %>% kable() %>% kable_styling(bootstrap_options = c("striped", "condensed", "responsive","bordered"), full_width = F, repeat_header_continued=T) %>% footnote(general = "lambda = 1")| pve | n_signal | in_sample | in_sample.addz | out_sample | out_sample.addz |
|---|---|---|---|---|---|
| 0.1 | 1 | 0.1391 | 0.1615 | 0.1397 | 0.1081 |
| 0.1 | 2 | 0.2450 | 0.2886 | 0.2991 | 0.2826 |
| 0.2 | 1 | 0.1069 | 0.1420 | 0.1338 | 0.1317 |
| 0.2 | 2 | 0.1884 | 0.1886 | 0.2149 | 0.1992 |
| Note: | |||||
| lambda = 1 |
NOT estimate residual variance
l = 5
est = FALSE
valid.in = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample%>% filter(estimate_residual_variance==est & L == l), sum)
total.in = aggregate(total~ pve+n_signal, dscout.susierss.in_sample%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.in = merge(valid.in, total.in)
fdr.in$in_sample = round((fdr.in$total - fdr.in$valid)/fdr.in$total, 4)
fdr.in = fdr.in[,-c(3,4)]
valid.in.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.addz%>% filter(estimate_residual_variance==est & L == l), sum)
total.in.addz = aggregate(total~ pve+n_signal, dscout.susierss.in_sample.addz%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.in.addz = merge(valid.in.addz, total.in.addz)
fdr.in.addz$in_sample.addz = round((fdr.in.addz$total - fdr.in.addz$valid)/fdr.in.addz$total, 4)
fdr.in.addz = fdr.in.addz[,-c(3,4)]
valid.out = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample%>% filter(estimate_residual_variance==est & L == l), sum)
total.out = aggregate(total~ pve+n_signal, dscout.susierss.out_sample%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.out = merge(valid.out, total.out)
fdr.out$out_sample = round((fdr.out$total - fdr.out$valid)/fdr.out$total, 4)
fdr.out = fdr.out[,-c(3,4)]
valid.out.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.addz%>% filter(estimate_residual_variance==est & L == l), sum)
total.out.addz = aggregate(total~ pve+n_signal, dscout.susierss.out_sample.addz%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.out.addz = merge(valid.out.addz, total.out.addz)
fdr.out.addz$out_sample.addz = round((fdr.out.addz$total - fdr.out.addz$valid)/fdr.out.addz$total, 4)
fdr.out.addz = fdr.out.addz[,-c(3,4)]
fdr.susierss = cbind(fdr.in, fdr.in.addz, fdr.out, fdr.out.addz)
fdr.susierss = fdr.susierss[,-c(4,5,7,8,10,11)]
fdr.susierss %>% kable() %>% kable_styling(bootstrap_options = c("striped", "condensed", "responsive","bordered"), full_width = F, repeat_header_continued=T) %>% footnote(general = "lambda = 0")| pve | n_signal | in_sample | in_sample.addz | out_sample | out_sample.addz |
|---|---|---|---|---|---|
| 0.1 | 1 | 0.0315 | 0.0227 | 0.1504 | 0.0444 |
| 0.1 | 2 | 0.1889 | 0.2468 | 0.2593 | 0.2405 |
| 0.2 | 1 | 0.0467 | 0.0267 | 0.2561 | 0.1062 |
| 0.2 | 2 | 0.1229 | 0.1566 | 0.2366 | 0.1716 |
| Note: | |||||
| lambda = 0 |
l = 5
est = FALSE
valid.in = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.l1%>% filter(estimate_residual_variance==est & L == l), sum)
total.in = aggregate(total~ pve+n_signal, dscout.susierss.in_sample.l1%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.in = merge(valid.in, total.in)
fdr.in$in_sample = round((fdr.in$total - fdr.in$valid)/fdr.in$total, 4)
fdr.in = fdr.in[,-c(3,4)]
valid.in.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.addz.l1%>% filter(estimate_residual_variance==est & L == l), sum)
total.in.addz = aggregate(total~ pve+n_signal, dscout.susierss.in_sample.addz.l1%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.in.addz = merge(valid.in.addz, total.in.addz)
fdr.in.addz$in_sample.addz = round((fdr.in.addz$total - fdr.in.addz$valid)/fdr.in.addz$total, 4)
fdr.in.addz = fdr.in.addz[,-c(3,4)]
valid.out = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.l1%>% filter(estimate_residual_variance==est & L == l), sum)
total.out = aggregate(total~ pve+n_signal, dscout.susierss.out_sample.l1%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.out = merge(valid.out, total.out)
fdr.out$out_sample = round((fdr.out$total - fdr.out$valid)/fdr.out$total, 4)
fdr.out = fdr.out[,-c(3,4)]
valid.out.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.addz.l1%>% filter(estimate_residual_variance==est & L == l), sum)
total.out.addz = aggregate(total~ pve+n_signal, dscout.susierss.out_sample.addz.l1%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.out.addz = merge(valid.out.addz, total.out.addz)
fdr.out.addz$out_sample.addz = round((fdr.out.addz$total - fdr.out.addz$valid)/fdr.out.addz$total, 4)
fdr.out.addz = fdr.out.addz[,-c(3,4)]
fdr.susierss = cbind(fdr.in, fdr.in.addz, fdr.out, fdr.out.addz)
fdr.susierss = fdr.susierss[,-c(4,5,7,8,10,11)]
fdr.susierss %>% kable() %>% kable_styling(bootstrap_options = c("striped", "condensed", "responsive","bordered"), full_width = F, repeat_header_continued=T) %>% footnote(general = "lambda = 1e-4")| pve | n_signal | in_sample | in_sample.addz | out_sample | out_sample.addz |
|---|---|---|---|---|---|
| 0.1 | 1 | 0.0236 | 0.0231 | 0.1504 | 0.0444 |
| 0.1 | 2 | 0.1889 | 0.2468 | 0.2469 | 0.2500 |
| 0.2 | 1 | 0.0400 | 0.0333 | 0.2484 | 0.1062 |
| 0.2 | 2 | 0.1229 | 0.1487 | 0.2325 | 0.1756 |
| Note: | |||||
| lambda = 1e-4 |
l = 5
est = FALSE
valid.in = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.l2%>% filter(estimate_residual_variance==est & L == l), sum)
total.in = aggregate(total~ pve+n_signal, dscout.susierss.in_sample.l2%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.in = merge(valid.in, total.in)
fdr.in$in_sample = round((fdr.in$total - fdr.in$valid)/fdr.in$total, 4)
fdr.in = fdr.in[,-c(3,4)]
valid.in.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.addz.l2%>% filter(estimate_residual_variance==est & L == l), sum)
total.in.addz = aggregate(total~ pve+n_signal, dscout.susierss.in_sample.addz.l2%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.in.addz = merge(valid.in.addz, total.in.addz)
fdr.in.addz$in_sample.addz = round((fdr.in.addz$total - fdr.in.addz$valid)/fdr.in.addz$total, 4)
fdr.in.addz = fdr.in.addz[,-c(3,4)]
valid.out = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.l2%>% filter(estimate_residual_variance==est & L == l), sum)
total.out = aggregate(total~ pve+n_signal, dscout.susierss.out_sample.l2%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.out = merge(valid.out, total.out)
fdr.out$out_sample = round((fdr.out$total - fdr.out$valid)/fdr.out$total, 4)
fdr.out = fdr.out[,-c(3,4)]
valid.out.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.addz.l2%>% filter(estimate_residual_variance==est & L == l), sum)
total.out.addz = aggregate(total~ pve+n_signal, dscout.susierss.out_sample.addz.l2%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.out.addz = merge(valid.out.addz, total.out.addz)
fdr.out.addz$out_sample.addz = round((fdr.out.addz$total - fdr.out.addz$valid)/fdr.out.addz$total, 4)
fdr.out.addz = fdr.out.addz[,-c(3,4)]
fdr.susierss = cbind(fdr.in, fdr.in.addz, fdr.out, fdr.out.addz)
fdr.susierss = fdr.susierss[,-c(4,5,7,8,10,11)]
fdr.susierss %>% kable() %>% kable_styling(bootstrap_options = c("striped", "condensed", "responsive","bordered"), full_width = F, repeat_header_continued=T) %>% footnote(general = "lambda = 0.1")| pve | n_signal | in_sample | in_sample.addz | out_sample | out_sample.addz |
|---|---|---|---|---|---|
| 0.1 | 1 | 0.0244 | 0.0161 | 0.1048 | 0.0231 |
| 0.1 | 2 | 0.1951 | 0.2329 | 0.2535 | 0.2297 |
| 0.2 | 1 | 0.0267 | 0.0200 | 0.1392 | 0.0390 |
| 0.2 | 2 | 0.1149 | 0.1218 | 0.2010 | 0.1354 |
| Note: | |||||
| lambda = 0.1 |
l = 5
est = FALSE
valid.in = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.l3%>% filter(estimate_residual_variance==est & L == l), sum)
total.in = aggregate(total~ pve+n_signal, dscout.susierss.in_sample.l3%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.in = merge(valid.in, total.in)
fdr.in$in_sample = round((fdr.in$total - fdr.in$valid)/fdr.in$total, 4)
fdr.in = fdr.in[,-c(3,4)]
valid.in.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.in_sample.addz.l3%>% filter(estimate_residual_variance==est & L == l), sum)
total.in.addz = aggregate(total~ pve+n_signal, dscout.susierss.in_sample.addz.l3%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.in.addz = merge(valid.in.addz, total.in.addz)
fdr.in.addz$in_sample.addz = round((fdr.in.addz$total - fdr.in.addz$valid)/fdr.in.addz$total, 4)
fdr.in.addz = fdr.in.addz[,-c(3,4)]
valid.out = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.l3%>% filter(estimate_residual_variance==est & L == l), sum)
total.out = aggregate(total~ pve+n_signal, dscout.susierss.out_sample.l3%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.out = merge(valid.out, total.out)
fdr.out$out_sample = round((fdr.out$total - fdr.out$valid)/fdr.out$total, 4)
fdr.out = fdr.out[,-c(3,4)]
valid.out.addz = aggregate(valid ~ pve+n_signal, dscout.susierss.out_sample.addz.l3%>% filter(estimate_residual_variance==est & L == l), sum)
total.out.addz = aggregate(total~ pve+n_signal, dscout.susierss.out_sample.addz.l3%>% filter(estimate_residual_variance==est & L == l), sum)
fdr.out.addz = merge(valid.out.addz, total.out.addz)
fdr.out.addz$out_sample.addz = round((fdr.out.addz$total - fdr.out.addz$valid)/fdr.out.addz$total, 4)
fdr.out.addz = fdr.out.addz[,-c(3,4)]
fdr.susierss = cbind(fdr.in, fdr.in.addz, fdr.out, fdr.out.addz)
fdr.susierss = fdr.susierss[,-c(4,5,7,8,10,11)]
fdr.susierss %>% kable() %>% kable_styling(bootstrap_options = c("striped", "condensed", "responsive","bordered"), full_width = F, repeat_header_continued=T) %>% footnote(general = "lambda = 1")| pve | n_signal | in_sample | in_sample.addz | out_sample | out_sample.addz |
|---|---|---|---|---|---|
| 0.1 | 1 | 0.0171 | 0.0171 | 0.0727 | 0.0083 |
| 0.1 | 2 | 0.2078 | 0.2308 | 0.2388 | 0.2381 |
| 0.2 | 1 | 0.0067 | 0.0000 | 0.0850 | 0.0197 |
| 0.2 | 2 | 0.1244 | 0.1250 | 0.1910 | 0.1453 |
| Note: | |||||
| lambda = 1 |
sessionInfo()R version 3.5.1 (2018-07-02)
Platform: x86_64-apple-darwin15.6.0 (64-bit)
Running under: macOS 10.14.4
Matrix products: default
BLAS: /Library/Frameworks/R.framework/Versions/3.5/Resources/lib/libRblas.0.dylib
LAPACK: /Library/Frameworks/R.framework/Versions/3.5/Resources/lib/libRlapack.dylib
locale:
[1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
attached base packages:
[1] stats graphics grDevices utils datasets methods base
other attached packages:
[1] bindrcpp_0.2.2 dplyr_0.7.8 kableExtra_1.0.1 tibble_2.0.1
[5] dscrutils_0.3.8
loaded via a namespace (and not attached):
[1] Rcpp_1.0.1 highr_0.7 pillar_1.3.1
[4] compiler_3.5.1 git2r_0.24.0 workflowr_1.3.0
[7] bindr_0.1.1 tools_3.5.1 digest_0.6.18
[10] evaluate_0.12 viridisLite_0.3.0 pkgconfig_2.0.2
[13] rlang_0.3.1 rstudioapi_0.9.0 yaml_2.2.0
[16] stringr_1.3.1 httr_1.4.0 knitr_1.20
[19] xml2_1.2.0 fs_1.2.6 hms_0.4.2
[22] tidyselect_0.2.5 rprojroot_1.3-2 webshot_0.5.1
[25] glue_1.3.0 R6_2.3.0 rmarkdown_1.11
[28] purrr_0.2.5 readr_1.3.1 magrittr_1.5
[31] whisker_0.3-2 backports_1.1.3 scales_1.0.0
[34] htmltools_0.3.6 assertthat_0.2.1 rvest_0.3.2
[37] colorspace_1.4-0 stringi_1.2.4 munsell_0.5.0
[40] crayon_1.3.4