summary_quantiles: Produce quantile summaries of model posterior samples

In growcurves: Bayesian Semi and Nonparametric Growth Curve Models that Additionally Include Multiple Membership Random Effects

Description

Inputs MCMC samples for model parameters and constructs c(2.5%,50%,97.5%) quantile summaries.

Usage

summary_quantiles(model.output, Nfixed, Nrandom, Nsubject, Nsubj.aff = NULL,
  Nmv = 1, Nsession = NULL)

Arguments

model.output	An output object of class within c("dpgrow", "dpgrowmm")
Nfixed	Number of total fixed effects, both time-based and nuisance.
Nrandom	Number of total random effects, both time-based and nuisance, all grouped by subject.
Nsubject	Number of unique subjects (on which repeated measures are observed).
Nsubj.aff	Number of subjects, P.aff, receiving multiple membership effects
Nmv	Number of multivariate MM effects. Defaults to 1 for univariate MM if left blank.
Nsession	Number of multiple membership effects for each entry in "Nmv". May be left blank for univariate MM.

Value

A list object containing quantile summaries for all sampled model parameters.

deviance.summary	vector of length 3 summarizing quantiles for model deviance.
beta.summary	Nfixed x 3 quantile summaries of model fixed effects.
alpha.summary	quantile summary of model global intercept parameter.
bmat.summary	list object of length Nrandom, each cell containing a Nsubject x 3 matrix of by-subject parameter quantile summaries.
tauu.summary	Nmv x 3 quantile summary for prior precision parameters employed for multiple membership random effects. An nty x 3 matrix in the case of nty multiple membership effect terms.
taue.summary	quantile summary for model error precision parameter.
taub	Nrandom x 3 quantile summaries for subject effect precision parameters.
u.summary	S*Nmv x 3 quantile summaries for multiple membership random effect parameters. A list of such matrices in the case of nty multiple membership effect terms.
mm.summary	Nsubj.aff x 3 quantile summaries derived from multiplying the affected subject weight matrix by the multiple membership random effects.
M.summary	quantile summary for number of DP posterior clusters formed.
Dbar	Model fit statistics.
pD	Model fit statistics.
pV	Model fit statistics.
DIC	Model fit statistics.
lpml	Model fit statistics.

Author(s)

Terrance Savitsky [e-mail]

See Also

dpgrowmm, dpgrow

growcurves documentation built on May 2, 2019, 7:03 a.m.