plot_check_common_pattern: Posterior predictive checking for the nested partially class...

In oslerinhealth/baker: Bayesian Analysis Kit for Etiology Research

Description

At each MCMC iteration, we generate a new data set based on the model and parameter values at that iteration. The sample size of the new data set equals that of the actual data set, i.e. the same number of cases and controls.

Usage

plot_check_common_pattern(
  DIR_list,
  slice_vec = rep(1, length(DIR_list)),
  n_pat = 10,
  dodge_val = 0.8
)

Arguments

DIR_list	The list of directory paths, each storing a model output.
slice_vec	Default are 1s, for the first slice of BrS data.
n_pat	Number of the most common BrS measurement pattern among cases and controls. Default is 10.
dodge_val	Default is 0.8; For width of boxplots.

Value

A figure of posterior predicted frequencies compared with the observed frequencies of the most common patterns for the BrS data.

See Also

Other visualization functions: plot_BrS_panel(), plot_SS_panel(), plot_check_pairwise_SLORD(), plot_etiology_regression(), plot_etiology_side_by_side(), plot_etiology_strat_nested(), plot_etiology_strat(), plot_group_etiology(), plot_panels(), plot_pie_panel(), plot_selected_etiology(), plot_subwt_regression()

Examples

## Not run: 
DIR_list <- list("C:\\2015_09_04_05SAF_k=1","C:\\2015_09_04_05SAF_k=2")
plot_check_common_pattern(DIR_list)
plot_check_common_pattern(DIR_list[[1]])

## End(Not run)

oslerinhealth/baker documentation built on May 22, 2021, 12:05 p.m.