samples: Obtain posterior samples or jmap estimates for unique...

In boryspaulewicz/bhsdtr2: Bayesian (non-)hierarchical ordinal models with ordered thresholds

Obtain posterior samples or jmap estimates for unique combinations of predictor values

Description

Obtain posterior samples or jmap estimates for unique combinations of predictor values

Usage

samples(m, par, group = NULL, prior = F, ...)

Arguments

m	a fitted bhsdtr model object
par	the name of a parameter. Can be either "dprim", "metad", "thr", "sdratio", or "mean".
group	grouping variable number. For example, if this is the d' formula: dprim ~ f1 * f2 + (f1 | id) + (f2 | id), then group = 1 corresponds to the (f1 | id) part, and group = 2 corresponds to the (f2 | id) part. If this is not NULL then you will get samples for every unique combination of predictors and levels of this grouping factor.

Value

aa S x D x C array, where S is the number of posterior samples (= 1 for bhsdtr models fitted using jmap), D is the dimensionality of the parameter (dprim = 1, metad = 2, thr = K - 1, mean = 1, sdratio = 1), and C is the number of unique combinations of values of predictors for the given parameter.

boryspaulewicz/bhsdtr2 documentation built on July 17, 2024, 8:22 p.m.