pcvr (version 1.2.0)

brmViolin: Function to visualize hypotheses tested on brms models similar to those made using growthSS outputs.

Description

Function to visualize hypotheses tested on brms models similar to those made using growthSS outputs.

Usage

brmViolin(fit, ss, hypothesis)

Value

Returns a ggplot showing a brms model's posterior distributions as violins and filled by posterior probability of some hypothesis.

Arguments

fit

A brmsfit object or a dataframe of draws. If you need to combine multiple models then use combineDraws to merge their draws into a single dataframe for testing.

ss

A pcvrss object. The only component that is currently used is the pcvrForm.

hypothesis

A hypothesis expressed as a character string in the style of that used by brms::hypothesis and testGrowth. In the hypothesis "..." can be used to mean "all groups for this parameter" so that the hypothesis "... / A_group1 > 1.05" would include all the "A" coefficients for groups 1:N along the x axis, see examples. If a hypothesis is using several parameters per group (second example) then math around those parameters and any ellipses should be wrapped in parentheses. Note that currently the single hypothesis option (no ...) only supports hypotheses using two parameters from the model at a time (ie, "groupA / groupB > 1.05" works but "(groupA / groupB) - (groupC / groupD) > 1" does not).

Examples

# \donttest{
set.seed(123)
simdf <- growthSim(
  "logistic",
  n = 20, t = 25,
  params = list("A" = c(200, 180, 190, 160), "B" = c(13, 11, 10, 10), "C" = c(3, 3, 3.25, 3.5))
)
ss <- growthSS(
  model = "logistic", form = y ~ time | id / group, sigma = "int",
  list("A" = 130, "B" = 10, "C" = 3),
  df = simdf, type = "brms"
)

fit <- fitGrowth(ss, backend = "cmdstanr", iter = 500, chains = 1, cores = 1)
brmViolin(fit, ss, ".../A_groupd > 1.05") # all groups used
brmViolin(fit, ss, "abs(1 - ((...)/(C_groupd - B_groupd))) > 0.05") # rather arbitrary
brmViolin(fit, ss, "abs(1 - ((...)/(C_groupa - B_groupd))) > 0.05") # totally arbitrary
brmViolin(fit, ss, "A_groupa/A_groupd > 1.05") # only these two groups
# }