Last updated: 2020-05-02

Checks: 6 1

Knit directory: social_immunity/

This reproducible R Markdown analysis was created with workflowr (version 1.6.1). The Checks tab describes the reproducibility checks that were applied when the results were created. The Past versions tab lists the development history.


The R Markdown file has unstaged changes. To know which version of the R Markdown file created these results, you’ll want to first commit it to the Git repo. If you’re still working on the analysis, you can ignore this warning. When you’re finished, you can run wflow_publish to commit the R Markdown file and build the HTML.

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(20191017) 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 job! Using relative paths to the files within your workflowr project makes it easier to run your code on other machines.

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 1c9a1c3. 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:    .DS_Store
    Ignored:    .Rhistory
    Ignored:    .Rproj.user/
    Ignored:    code/notes from old analysis of movement.R
    Ignored:    data/.DS_Store
    Ignored:    data/movement data - not used/
    Ignored:    output/exp1_model.rds
    Ignored:    output/exp1_post_prob.rds
    Ignored:    output/exp2_model.rds
    Ignored:    output/exp2_post_prob.rds
    Ignored:    output/exp3_model.rds
    Ignored:    output/exp3_post_prob.rds

Unstaged changes:
    Modified:   .gitignore
    Modified:   analysis/experiment1.Rmd
    Modified:   analysis/experiment2.Rmd
    Modified:   code/helper_functions.R
    Modified:   figures/fig1.pdf
    Modified:   figures/fig2.pdf
    Modified:   figures/fig3.pdf
    Modified:   figures/tableS3.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/experiment2.Rmd) and HTML (docs/experiment2.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
html 1c9a1c3 lukeholman 2020-05-02 Build site.
Rmd 3d21d6a lukeholman 2020-05-02 wflow_publish("*", republish = T)
html 3d21d6a lukeholman 2020-05-02 wflow_publish("*", republish = T)
html 93c487a lukeholman 2020-04-30 Build site.
html 5c45197 lukeholman 2020-04-30 Build site.
html 4bd75dc lukeholman 2020-04-30 Build site.
Rmd 12953af lukeholman 2020-04-30 test new theme
html 12953af lukeholman 2020-04-30 test new theme
html d6437a5 lukeholman 2020-04-25 Build site.
html e58e720 lukeholman 2020-04-25 Build site.
html 71b6160 lukeholman 2020-04-25 Build site.
Rmd 76a317d lukeholman 2020-04-25 tweaks
html 2235ae4 lukeholman 2020-04-25 Build site.
Rmd 99649a7 lukeholman 2020-04-25 tweaks
html 99649a7 lukeholman 2020-04-25 tweaks
html 0ede6e3 lukeholman 2020-04-24 Build site.
Rmd a1f8dc2 lukeholman 2020-04-24 tweaks
html 8c3b471 lukeholman 2020-04-21 Build site.
Rmd 1ce9e19 lukeholman 2020-04-21 First commit 2020
html 1ce9e19 lukeholman 2020-04-21 First commit 2020
Rmd aae65cf lukeholman 2019-10-17 First commit
html aae65cf lukeholman 2019-10-17 First commit

Load data and R packages

# All but 1 of these packages can be easily installed from CRAN.
# However it was harder to install the showtext package. On Mac, I did this:
# installed 'homebrew' using Terminal: ruby -e "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/master/install)" 
# installed 'libpng' using Terminal: brew install libpng
# installed 'showtext' in R using: devtools::install_github("yixuan/showtext")  
library(showtext)

library(brms)
library(bayesplot)
library(tidyverse)
library(gridExtra)
library(kableExtra)
library(bayestestR)
library(tidybayes)
library(cowplot)
source("code/helper_functions.R")

# set up nice font for figure
nice_font <- "Lora"
font_add_google(name = nice_font, family = nice_font, regular.wt = 400, bold.wt = 700)
showtext_auto()

exp2_treatments <- c("Ringers", "LPS")

durations <- read_csv("data/data_collection_sheets/experiment_durations.csv") %>%
  filter(experiment == 2) %>% select(-experiment)

outcome_tally <- read_csv(file = "data/clean_data/experiment_2_outcome_tally.csv") %>%
  mutate(
    outcome = str_replace_all(outcome, "Stayed inside the hive", "Stayed inside"),
    outcome = str_replace_all(outcome, "Left of own volition", "Left voluntarily"),
    outcome = factor(outcome, levels = c("Stayed inside", "Left voluntarily", "Forced out")),
         treatment = str_replace_all(treatment, "Ringer CHC", "Ringers"),
         treatment = str_replace_all(treatment, "LPS CHC", "LPS"),
         treatment = factor(treatment, levels = exp2_treatments))

# Re-formatted version of the same data, where each row is an individual bee. We need this format to run the brms model.
data_for_categorical_model <- outcome_tally %>%
  mutate(id = 1:n()) %>%
  split(.$id) %>%
  map(function(x){
    if(x$n[1] == 0) return(NULL)
    data.frame(
      treatment = x$treatment[1],
      hive = x$hive[1],
      colour = x$colour[1],
      outcome = rep(x$outcome[1], x$n))
  }) %>% do.call("rbind", .) %>% as_tibble() %>%
  arrange(hive, treatment) %>%
  mutate(outcome_numeric = as.numeric(outcome),
         hive = as.character(hive),
         treatment = factor(treatment, levels = exp2_treatments)) %>%
  left_join(durations, by = "hive") %>%
  mutate(hive = C(factor(hive), sum))  # use "sum coding" for hive, since there is no obvious reference level

Inspect the raw data

Click the three tabs to see each table.

Sample sizes by treatment

sample_sizes <- data_for_categorical_model %>%
  group_by(treatment) %>%
  summarise(n = n()) 

sample_sizes %>%
  kable() %>% kable_styling(full_width = FALSE)
treatment n
Ringers 294
LPS 291

Sample sizes by treatment and hive

data_for_categorical_model %>%
  group_by(hive, treatment) %>%
  summarise(n = n()) %>%
  spread(treatment, n) %>%
  kable() %>% kable_styling(full_width = FALSE)
hive Ringers LPS
Arts 70 68
Garden 75 75
Skylab 99 100
Zoology 50 48

Oberved outcomes

outcome_tally %>%
  select(-colour) %>% 
  spread(outcome, n) %>%
  kable(digits = 3) %>% kable_styling(full_width = FALSE) 
hive treatment Stayed inside Left voluntarily Forced out
Arts Ringers 64 5 1
Arts LPS 56 5 7
Garden Ringers 73 2 0
Garden LPS 70 2 3
Skylab Ringers 97 1 1
Skylab LPS 93 2 5
Zoology Ringers 42 2 6
Zoology LPS 38 4 6

Plot showing raw means and 95% CI of the mean

pd <- position_dodge(.3)
outcome_tally %>%
  group_by(treatment, outcome) %>%
  summarise(n = sum(n)) %>% mutate() %>%
  group_by(treatment) %>%
  mutate(total_n = sum(n),
         percent = 100 * n / sum(n),
         SE = sqrt(total_n * (percent/100) * (1-(percent/100)))) %>% 
  ungroup() %>%
  mutate(lowerCI = map_dbl(1:n(), ~ 100 * binom.test(n[.x], total_n[.x])$conf.int[1]),
         upperCI = map_dbl(1:n(), ~ 100 * binom.test(n[.x], total_n[.x])$conf.int[2])) %>%
  filter(outcome != "Stayed inside") %>%
  ggplot(aes(treatment, percent, fill = outcome)) + 
  geom_errorbar(aes(ymin=lowerCI, ymax=upperCI), position = pd, width = 0) + 
  geom_point(stat = "identity", position = pd, colour = "grey15", pch = 21, size = 4) + 
  scale_fill_brewer(palette = "Pastel1", name = "Outcome", direction = -1) + 
  xlab("Treatment") + ylab("% bees (\u00B1 95% CIs)") + 
  theme_bw(20) + 
  theme(text = element_text(family = nice_font),
        legend.position = "top") + 
  coord_flip()

Multinomial model of outcome

Run the models

Fit a multinomial logisitic model, with 3 possible outcomes describing what happened to each bee introduced to the hive: stayed inside, left of its own volition, or forced out by the other workers. To assess the effects of our predictor variables, we compare 5 models with different fixed factors, ranking them by posterior model probability.

if(!file.exists("output/exp2_model.rds")){
  exp2_model_v1 <- brm(
    outcome_numeric ~ treatment * hive + observation_time_minutes, 
    data = data_for_categorical_model, 
    prior = c(set_prior("normal(0, 3)", class = "b", dpar = "mu2"),
              set_prior("normal(0, 3)", class = "b", dpar = "mu3")),
    family = "categorical", save_all_pars = TRUE, sample_prior = TRUE,
    chains = 4, cores = 1, iter = 5000, seed = 1)
  
  exp2_model_v2 <- brm(
    outcome_numeric ~ treatment + hive + observation_time_minutes, 
    data = data_for_categorical_model, 
    prior = c(set_prior("normal(0, 3)", class = "b", dpar = "mu2"),
              set_prior("normal(0, 3)", class = "b", dpar = "mu3")),
    family = "categorical", save_all_pars = TRUE, sample_prior = TRUE,
    chains = 4, cores = 1, iter = 5000, seed = 1)
  
  exp2_model_v3 <- brm(
    outcome_numeric ~ hive + observation_time_minutes, 
    data = data_for_categorical_model, 
    prior = c(set_prior("normal(0, 3)", class = "b", dpar = "mu2"),
              set_prior("normal(0, 3)", class = "b", dpar = "mu3")),
    family = "categorical",  save_all_pars = TRUE, sample_prior = TRUE,
    chains = 4, cores = 1, iter = 5000, seed = 1)
  
  posterior_model_probabilities <- tibble(
    Model = c("treatment * hive + observation_time_minutes",
              "treatment + hive + observation_time_minutes",
              "hive + observation_time_minutes"),
    post_prob = as.numeric(post_prob(exp2_model_v1,
                                     exp2_model_v2,
                                     exp2_model_v3))) %>%
    arrange(-post_prob)
  
  saveRDS(exp2_model_v2, "output/exp2_model.rds") # save the top model, treatment + hive
  saveRDS(posterior_model_probabilities, "output/exp2_post_prob.rds")
}

exp2_model <- readRDS("output/exp2_model.rds")
posterior_model_probabilities <- readRDS("output/exp2_post_prob.rds")

Posterior model probabilites

posterior_model_probabilities %>% 
  kable(digits = 3) %>% kable_styling()
Model post_prob
hive + observation_time_minutes 0.530
treatment + hive + observation_time_minutes 0.466
treatment * hive + observation_time_minutes 0.003

Fixed effects from the top model

Raw output of the treatment + hive model

summary(exp2_model)
 Family: categorical 
  Links: mu2 = logit; mu3 = logit 
Formula: outcome_numeric ~ treatment + hive + observation_time_minutes 
   Data: data_for_categorical_model (Number of observations: 585) 
Samples: 4 chains, each with iter = 5000; warmup = 2500; thin = 1;
         total post-warmup samples = 10000

Population-Level Effects: 
                             Estimate Est.Error l-95% CI u-95% CI Rhat Bulk_ESS Tail_ESS
mu2_Intercept                   -6.37      6.67   -19.69     6.68 1.00     3993     5078
mu3_Intercept                   -5.18      6.71   -18.32     7.89 1.00     4124     5202
mu2_treatmentLPS                 0.38      0.44    -0.48     1.25 1.00     9937     7148
mu2_hive1                        0.11      1.52    -2.87     3.08 1.00     4029     5114
mu2_hive2                       -0.18      0.68    -1.51     1.16 1.00     4964     6483
mu2_hive3                        0.08      2.53    -4.84     5.11 1.00     4134     5283
mu2_observation_time_minutes     0.03      0.07    -0.10     0.16 1.00     3993     5015
mu3_treatmentLPS                 1.10      0.43     0.29     1.99 1.00     8715     6616
mu3_hive1                       -0.03      1.54    -3.06     2.97 1.00     4022     5092
mu3_hive2                       -0.85      0.71    -2.27     0.49 1.00     4813     6207
mu3_hive3                        0.05      2.55    -4.89     5.09 1.00     4203     5413
mu3_observation_time_minutes     0.01      0.07    -0.12     0.15 1.00     4104     5308

Samples were drawn using sampling(NUTS). For each parameter, Bulk_ESS
and Tail_ESS are effective sample size measures, and Rhat is the potential
scale reduction factor on split chains (at convergence, Rhat = 1).

Formatted brms output for Table S3

The code chunk below wrangles the raw output of the summary() function for brms models into a more readable table of results, and also adds ‘Bayesian p-values’ (i.e. the posterior probability that the true effect size has the same sign as the reported effect).


Table S3: Table summarising the posterior estimates of each fixed effect in the best-fitting model of Experiment 2. This was a multinomial model with three possible outcomes (stay inside, leave voluntarily, be forced out), and so there are two parameter estimates for the intercept and for each predictor in the model. ‘Treatment’ is a fixed factor with two levels, and the effect of LPS shown here is expressed relative to the ‘Ringers’ treatment. ‘Hive’ was a fixed factor with four levels; unlike for treatment, we modelled hive using deviation coding, such that the intercept term represents the mean across all hives (in the Ringers treatment), and the three hive terms represent the deviation from this mean for three of the four hives. Lastly, observation duration was a continuous variable expressed to the nearest minute. The \(p\) column gives the posterior probability that the true effect size is opposite in sign to what is reported in the Estimate column, similarly to a \(p\)-value.

tableS3 <- get_fixed_effects_with_p_values(exp2_model) %>% 
  mutate(mu = map_chr(str_extract_all(Parameter, "mu[:digit:]"), ~ .x[1]),
         Parameter = str_remove_all(Parameter, "mu[:digit:]_"),
         Parameter = str_replace_all(Parameter, "treatment", "Treatment: "),
         Parameter = str_replace_all(Parameter, "observation_time_minutes", "Observation duration (minutes)")) %>%
  arrange(mu) %>%
  select(-mu, -Rhat, -Bulk_ESS, -Tail_ESS) 

names(tableS3)[3:5] <- c("Est. Error", "Lower 95% CI", "Upper 95% CI")

saveRDS(tableS3, file = "figures/tableS3.rds")

tableS3 %>%
  kable(digits = 3) %>% 
  kable_styling(full_width = FALSE) %>%
  pack_rows("% bees leaving voluntarily", 1, 6) %>%
  pack_rows("% bees forced out", 7, 12)
Parameter Estimate Est. Error Lower 95% CI Upper 95% CI PP
% bees leaving voluntarily
Intercept -6.368 6.669 -19.689 6.679 0.168
Treatment: LPS 0.377 0.439 -0.480 1.245 0.197
hive1 0.111 1.522 -2.868 3.075 0.466
hive2 -0.183 0.679 -1.513 1.160 0.390
hive3 0.082 2.531 -4.835 5.113 0.491
Observation duration (minutes) 0.029 0.068 -0.103 0.165 0.337
% bees forced out
Intercept -5.179 6.708 -18.321 7.894 0.222
Treatment: LPS 1.105 0.433 0.291 1.989 0.004 **
hive1 -0.030 1.544 -3.059 2.971 0.490
hive2 -0.847 0.705 -2.266 0.490 0.112
hive3 0.049 2.554 -4.892 5.089 0.493
Observation duration (minutes) 0.015 0.069 -0.118 0.149 0.414

Plotting estimates from the model

Derive prediction from the posterior

get_posterior_preds <- function(hive){
  new <- expand.grid(treatment = levels(data_for_categorical_model$treatment), 
                     hive = "Zoology",
                     observation_time_minutes = 120) 
  
  preds <- fitted(exp2_model, newdata = new, summary = FALSE)
  dimnames(preds) <- list(NULL, paste(new$treatment, new$hive, sep = "~"), NULL)
  
  rbind(
    as.data.frame(preds[,, 1]) %>% mutate(outcome = "Stayed inside", posterior_sample = 1:n()),
    as.data.frame(preds[,, 2]) %>% mutate(outcome = "Left voluntarily", posterior_sample = 1:n()),
    as.data.frame(preds[,, 3]) %>% mutate(outcome = "Forced out", posterior_sample = 1:n())) %>%
    gather(treatment, prop, contains("~")) %>%
    mutate(treatment = strsplit(treatment, split = "~"),
           hive = map_chr(treatment, ~ .x[2]),
           treatment = map_chr(treatment, ~ .x[1]),
           treatment = factor(treatment, c("Ringers", "LPS")),
           outcome = factor(outcome, c("Stayed inside", "Left voluntarily", "Forced out"))) %>%
    arrange(treatment, outcome) %>% as_tibble() %>% select(-hive)
}


# plotting data for panel A: one specific hive
plotting_data <- get_posterior_preds(hive = "Zoology")

# stats data: for comparing means across all hives
stats_data <- get_posterior_preds(hive = NA)

Make Figure 2

cols <- c("#34558b", "#4ec5a5", "#ffaf12")

dot_plot <- plotting_data %>%
  left_join(sample_sizes, by = "treatment") %>%
  arrange(treatment) %>%
  mutate(treatment = factor(paste(treatment, "\n(n = ", n, ")", sep = ""),
                            unique(paste(treatment, "\n(n = ", n, ")", sep = "")))) %>% 
  ggplot(aes(100 * prop, treatment)) + 
  stat_dotsh(quantiles = 100, fill = "grey40", colour = "grey40") + 
  stat_pointintervalh(aes(colour = outcome, fill = outcome), 
                      .width = c(0.5, 0.95),
                      position = position_nudge(y = -0.07), point_colour = "grey26", pch = 21, stroke = 0.4) + 
  scale_colour_manual(values = cols) + 
  scale_fill_manual(values = cols) + 
  facet_wrap( ~ outcome, scales = "free_x") + 
  xlab("% bees (posterior estimate)") + ylab("Treatment") + 
  theme_bw() + 
  coord_cartesian(ylim=c(1.4, 2.2)) + 
  theme(
    text = element_text(family = nice_font),
    strip.background = element_rect(fill = "#eff0f1"),
    panel.grid.major.y = element_blank(),
    legend.position = "none"
  ) 
  

get_log_odds <- function(trt1, trt2){ # positive effect = odds of this outcome are higher for trt2 than trt1 (put control as trt1)
  log((trt2 / (1 - trt2) / (trt1 / (1 - trt1))))
}

LOR <- plotting_data %>%
  spread(treatment, prop) %>%
  mutate(LOR = get_log_odds(Ringers, LPS)) %>%
  select(posterior_sample, outcome, LOR)



LOR_plot <- LOR %>%
  ggplot(aes(LOR, outcome, colour = outcome)) + 
  geom_vline(xintercept = 0, linetype = 2) +
  geom_vline(xintercept = log(2), linetype = 2, colour = "pink") +
  geom_vline(xintercept = -log(2), linetype = 2, colour = "pink") +
  stat_pointintervalh(aes(colour = outcome, fill = outcome), 
                      position = position_dodge(0.4), 
                      .width = c(0.5, 0.95),
                      point_colour = "grey26", pch = 21, stroke = 0.4) + 
  scale_colour_manual(values = cols) + 
  scale_fill_manual(values = cols) + 
  xlab("Effect size of LPS\n(log odds ratio)") + ylab("Mode of exit") + 
  theme_bw() +
  theme(
    text = element_text(family = nice_font),
    panel.grid.major.y = element_blank(),
    legend.position = "none"
  ) 

diff_in_forced_out_plot <- plotting_data %>%
  spread(outcome, prop) %>%
  mutate(prop_leavers_that_were_forced_out = `Forced out` / (`Forced out` + `Left voluntarily`)) %>%
  select(posterior_sample, treatment, prop_leavers_that_were_forced_out)  %>%
  spread(treatment, prop_leavers_that_were_forced_out) %>% 
  mutate(difference_prop_forced_out_LOR = get_log_odds(Ringers, LPS)) %>%
  ggplot(aes(difference_prop_forced_out_LOR, y =1)) + 
  geom_vline(xintercept = 0, linetype = 2) +
  stat_dotsh(quantiles = 100, fill = "grey40", colour = "grey40") + 
  xlab("Effect of LPS on proportion\nbees leaving by force\n(log odds ratio)") + 
  ylab("Posterior density") + 
  theme_bw() +
  theme(
    text = element_text(family = nice_font),
    panel.grid.major.y = element_blank(),
    legend.position = "none"
  ) 

bottom_row <- cowplot::plot_grid(LOR_plot, diff_in_forced_out_plot, 
                                 labels = c("B", "C"),
                                 nrow = 1, align = 'hv', axis = 'l', rel_heights = c(1.6, 1))
top_row <- cowplot::plot_grid(dot_plot, labels = "A")
p <- cowplot::plot_grid(top_row, bottom_row, 
                        nrow = 2, align = 'v', axis = 'l', rel_heights = c(1.4, 1))
ggsave(plot = p, filename = "figures/fig2.pdf", height = 6, width = 6)
p

The dashed lines mark \(LOR = 0\), indicating no effect, and \(LOR = \pm log(2)\), i.e. the point at which the odds are twice as high in one treatment as the other.

Hypothesis testing and effect sizes

This section calculates the posterior difference in treatment group means, in order to perform some null hypothesis testing, calculate effect size, and calculate the 95% credible intervals on the effect size. In all cases, the effect size expresses the effect of the “LPS-treated bee CHCs” treatment relative to the “Ringer-treated bee CHCs” control.

Stats associated with Figure 2B

Making Table S4

my_summary <- function(df, columns, outcome) {
  lapply(columns, function(x){
    
    p <- 1 - (df %>% pull(!! x) %>%
                bayestestR::p_direction() %>% as.numeric())
    
    df %>% pull(!! x) %>% posterior_summary() %>% as_tibble() %>% 
      mutate(PP = p, Outcome = outcome, Metric = x) %>% 
      select(Outcome, Metric, everything())
  }) %>% do.call("rbind", .)
}

stats_table <- rbind(
  plotting_data %>%
    filter(outcome == "Stayed inside") %>%
    spread(treatment, prop) %>%
    mutate(`Absolute difference in % bees staying inside` = 100 * (LPS - Ringers),
           `Log odds ratio` = get_log_odds(Ringers, LPS)) %>%
    my_summary(c("Absolute difference in % bees staying inside", 
                 "Log odds ratio"),
               outcome = "Stayed inside") %>%
    mutate(PP = c(" ", format(round(PP[2], 4), nsmall = 4))),
  
  plotting_data %>%
    filter(outcome == "Left voluntarily") %>%
    spread(treatment, prop) %>%
    mutate(`Absolute difference in % bees leaving voluntarily` = 100 * (LPS - Ringers),
           `Log odds ratio` = get_log_odds(Ringers, LPS)) %>%
    my_summary(c("Absolute difference in % bees leaving voluntarily", 
                 "Log odds ratio"),
               outcome = "Left voluntarily") %>%
    mutate(PP = c(" ", format(round(PP[2], 4), nsmall = 4))),
  
  plotting_data %>%
    filter(outcome == "Forced out") %>%
    spread(treatment, prop) %>%
    mutate(`Absolute difference in % bees forced out` = 100 * (LPS - Ringers),
           `Log odds ratio` = get_log_odds(Ringers, LPS)) %>%
    my_summary(c("Absolute difference in % bees forced out", 
                 "Log odds ratio"),
               outcome = "Forced out") %>%
    mutate(PP = c(" ", format(round(PP[2], 4), nsmall = 4))) 
) %>%
  mutate(` ` = ifelse(PP < 0.05, "\\*", ""),
         ` ` = replace(` `, PP < 0.01, "**"),
         ` ` = replace(` `, PP < 0.001, "***"),
         ` ` = replace(` `, PP == " ", ""))

stats_table[c(2,4,6), 1] <- " "

stats_table %>%
  select(-Outcome) %>%
  kable(digits = 3) %>% kable_styling(full_width = FALSE) %>% 
  row_spec(c(0,2,4,6), extra_css = "border-bottom: solid;") %>%
  pack_rows("% bees staying inside", 1, 2) %>%
  pack_rows("% bees leaving voluntarily", 3, 4) %>%
  pack_rows("% bees forced out", 5, 6)
Metric Estimate Est.Error Q2.5 Q97.5 PP
% bees staying inside
Absolute difference in % bees staying inside -11.949 4.942 -22.208 -2.753
Log odds ratio -0.836 0.331 -1.520 -0.199 0.0048 **
% bees leaving voluntarily
Absolute difference in % bees leaving voluntarily 1.335 2.623 -3.720 7.086
Log odds ratio 0.242 0.440 -0.621 1.106 0.2881
% bees forced out
Absolute difference in % bees forced out 10.614 4.627 2.538 20.464
Log odds ratio 1.079 0.433 0.270 1.967 0.0047 **

Table S4: This table gives statistics associated with each of the contrasts plotted in Figure 2B. Each pair of rows gives the absolute (i.e. the difference in % bees) and standardised effect size (as log odds ratio; LOR) for the LPS treatment, relative to the Ringers treatment, for one of the three possible outcomes (stayed inside, left voluntarily, or forced out). A LOR of \(|log(x)|\) indicates that the outcome is \(x\) times more frequent in one treatment compared to the other, e.g. \(log(2) = 0.69\) indicates a two-fold difference in frequency. The \(PP\) column gives the posterior probability that the true effect size has the same sign as is shown in the Estimate column; this metric has a similar interpretation to a one-tailed \(p\) value in frequentist statistics.

Evaluating evidence for the null hypothesis

Here, we derive the result present in prose in the Results, where we calculated the posterior probability that the true effect size lies in the range -log(2) < LOR < log(2).

LOR_forced <- LOR %>%
  filter(outcome == "Forced out") %>% 
  pull(LOR)

LOR_left <- LOR %>%
  filter(outcome == "Left voluntarily") %>%
  pull(LOR)

ROPE_calculation <- function(scale, LOR_data){
  round(sum(LOR_data > -log(scale) & LOR_data < log(scale)) / length(LOR_data), 3)
}

cat(
  paste(
    paste("Probability that |LOR|<2 for % bees leaving voluntarily:", ROPE_calculation(2, LOR_left)), "\n",
    paste("Probability that |LOR|<2 for % bees forced out:", ROPE_calculation(2, LOR_forced)), sep = "")
)
Probability that |LOR|<2 for % bees leaving voluntarily: 0.832
Probability that |LOR|<2 for % bees forced out: 0.187

Stats associated with Figure 2C

Here, we derive the result presented in prose in the Results, regarding the effect of LPS on the proportion of bees that left the hive by force.

difference_prop_forced_out_LOR <- plotting_data %>%
  spread(outcome, prop) %>%
  mutate(prop_leavers_that_were_forced_out = 
           `Forced out` / (`Forced out` + `Left voluntarily`)) %>%
  select(posterior_sample, 
         treatment, 
         prop_leavers_that_were_forced_out)  %>%
  spread(treatment, 
         prop_leavers_that_were_forced_out) %>% 
  mutate(difference_prop_forced_out_LOR = get_log_odds(Ringers, LPS)) %>%
  pull(difference_prop_forced_out_LOR)

hypothesis(difference_prop_forced_out_LOR, 
           "x > 0", alpha = 0.05)$hypothesis
  Hypothesis  Estimate Est.Error   CI.Lower CI.Upper Evid.Ratio Post.Prob Star
1    (x) > 0 0.7281842 0.5984938 -0.2336917 1.712823   8.082652    0.8899     

sessionInfo()
R version 3.6.3 (2020-02-29)
Platform: x86_64-apple-darwin15.6.0 (64-bit)
Running under: macOS Catalina 10.15.4

Matrix products: default
BLAS:   /Library/Frameworks/R.framework/Versions/3.6/Resources/lib/libRblas.0.dylib
LAPACK: /Library/Frameworks/R.framework/Versions/3.6/Resources/lib/libRlapack.dylib

locale:
[1] en_AU.UTF-8/en_AU.UTF-8/en_AU.UTF-8/C/en_AU.UTF-8/en_AU.UTF-8

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

other attached packages:
 [1] cowplot_1.0.0    tidybayes_2.0.1  bayestestR_0.5.1 kableExtra_1.1.0 gridExtra_2.3    forcats_0.5.0   
 [7] stringr_1.4.0    dplyr_0.8.5      purrr_0.3.3      readr_1.3.1      tidyr_1.0.2      tibble_3.0.0    
[13] ggplot2_3.3.0    tidyverse_1.3.0  bayesplot_1.7.1  brms_2.12.0      Rcpp_1.0.4.6     showtext_0.7-1  
[19] showtextdb_2.0   sysfonts_0.8    

loaded via a namespace (and not attached):
  [1] colorspace_1.4-1     ellipsis_0.3.0       ggridges_0.5.2       rsconnect_0.8.16     rprojroot_1.3-2     
  [6] markdown_1.1         base64enc_0.1-3      fs_1.4.1             rstudioapi_0.11      farver_2.0.3        
 [11] rstan_2.19.3         svUnit_0.7-12        DT_0.13              fansi_0.4.1          mvtnorm_1.1-0       
 [16] lubridate_1.7.8      xml2_1.3.1           bridgesampling_1.0-0 knitr_1.28           shinythemes_1.1.2   
 [21] jsonlite_1.6.1       workflowr_1.6.1      broom_0.5.4          dbplyr_1.4.2         shiny_1.4.0.2       
 [26] compiler_3.6.3       httr_1.4.1           backports_1.1.6      assertthat_0.2.1     Matrix_1.2-18       
 [31] fastmap_1.0.1        cli_2.0.2            later_1.0.0          htmltools_0.4.0.9003 prettyunits_1.1.1   
 [36] tools_3.6.3          igraph_1.2.5         coda_0.19-3          gtable_0.3.0         glue_1.4.0          
 [41] reshape2_1.4.4       cellranger_1.1.0     vctrs_0.2.4          nlme_3.1-147         crosstalk_1.1.0.1   
 [46] insight_0.8.1        xfun_0.13            ps_1.3.0             rvest_0.3.5          mime_0.9            
 [51] miniUI_0.1.1.1       lifecycle_0.2.0      gtools_3.8.2         zoo_1.8-7            scales_1.1.0        
 [56] colourpicker_1.0     hms_0.5.3            promises_1.1.0       Brobdingnag_1.2-6    parallel_3.6.3      
 [61] inline_0.3.15        RColorBrewer_1.1-2   shinystan_2.5.0      curl_4.3             yaml_2.2.1          
 [66] loo_2.2.0            StanHeaders_2.19.2   stringi_1.4.6        highr_0.8            dygraphs_1.1.1.6    
 [71] pkgbuild_1.0.6       rlang_0.4.5          pkgconfig_2.0.3      matrixStats_0.56.0   evaluate_0.14       
 [76] lattice_0.20-41      labeling_0.3         rstantools_2.0.0     htmlwidgets_1.5.1    processx_3.4.2      
 [81] tidyselect_1.0.0     plyr_1.8.6           magrittr_1.5         R6_2.4.1             generics_0.0.2      
 [86] DBI_1.1.0            pillar_1.4.3         haven_2.2.0          whisker_0.4          withr_2.1.2         
 [91] xts_0.12-0           abind_1.4-5          modelr_0.1.5         crayon_1.3.4         arrayhelpers_1.1-0  
 [96] rmarkdown_2.1.3      grid_3.6.3           readxl_1.3.1         callr_3.4.3          git2r_0.26.1        
[101] threejs_0.3.3        reprex_0.3.0         digest_0.6.25        webshot_0.5.2        xtable_1.8-4        
[106] httpuv_1.5.2         stats4_3.6.3         munsell_0.5.0        viridisLite_0.3.0    shinyjs_1.1