stanmer: Summarize a Stan model fit by glmer2stan
Description
Displays mean and standard deviations of fixed effects samples and variance-covariance samples. Returned value is a structured list of mean and standard deviations of all parameters.
Usage
stanmer( fit , digits=2 , probs=c(0.025,0.975) , fixed_prefix="beta_" , vary_prefix="vary_" )
Arguments
probs
quantiles to display in summary
digits
Number of digits to display in summaries
fixed_prefix
Identifying prefix for fixed effects, in the samples
vary_prefix
Identifying prefix for varying effects, in the samples
Details
This command displays summary statistics in a form resembling the output for a regular glmer model fit. Averages and standard deviations are shown for all fixed effects, and variance components are displayed as standard deviations and correlations.
The variance component display or each grouping variable shows standard deviation on the diagonal and correlations in the lower triangle.
Each grouping variable also displays a measure of imbalance in sampling across groups within it. This measure is simply the gini coeficient of the distribution of the number of samples in each unique group. If every group (individual, household, county, etc.) has the same number of cases in the data, then the gini is zero, indicating no imbalance in sampling. As imbalance increases, the gini approaches 1.
The returned value is a list of mean and standard deviations of all parameters in the Stan samples, organized as lists of arrays.