pglmmObj-class: Class 'pglmmObj' of Fitted Penalized Generalized...

pglmmObj-classR Documentation

Class pglmmObj of Fitted Penalized Generalized Mixed-Effects Models for package glmmPen

Description

The functions glmm, glmmPen, glmm_FA, and glmmPen_FA from the package glmmPen output the reference class object of type pglmmObj.

Usage

## S3 method for class 'pglmmObj'
fixef(object, ...)

## S3 method for class 'pglmmObj'
ranef(object, ...)

## S3 method for class 'pglmmObj'
sigma(object, ...)

## S3 method for class 'pglmmObj'
coef(object, ...)

## S3 method for class 'pglmmObj'
family(object, ...)

## S3 method for class 'pglmmObj'
nobs(object, ...)

## S3 method for class 'pglmmObj'
ngrps(object, ...)

## S3 method for class 'pglmmObj'
formula(x, fixed.only = FALSE, random.only = FALSE, ...)

## S3 method for class 'pglmmObj'
model.frame(formula, fixed.only = FALSE, ...)

## S3 method for class 'pglmmObj'
model.matrix(object, type = c("fixed", "random"), ...)

## S3 method for class 'pglmmObj'
fitted(object, fixed.only = TRUE, ...)

## S3 method for class 'pglmmObj'
predict(
  object,
  newdata = NULL,
  type = c("link", "response"),
  fixed.only = TRUE,
  ...
)

## S3 method for class 'pglmmObj'
residuals(object, type = c("deviance", "pearson", "response", "working"), ...)

## S3 method for class 'pglmmObj'
print(x, digits = c(fef = 4, ref = 4), ...)

## S3 method for class 'pglmmObj'
summary(
  object,
  digits = c(fef = 4, ref = 4),
  resid_type = switch(object$family$family, gaussian = "pearson", "deviance"),
  ...
)

## S3 method for class 'pglmmObj'
logLik(object, ...)

## S3 method for class 'pglmmObj'
BIC(object, ...)

## S3 method for class 'pglmmObj'
plot(x, fixed.only = FALSE, type = NULL, ...)

Arguments

object

pglmmObj object output from glmm, glmmPen, or glmmPen_FineSearch

...

potentially further arguments passed from other methods

x

an R object of class pglmmObj

fixed.only

logical value; default TRUE indicates that only the fixed effects should be used in the fitted value/prediction, while FALSE indicates that both the fixed and random effects posterior modes should be used in the fitted value/prediction

random.only

logical value used in formula; TRUE indicates that only the formula elements relating to the random effects should be returned

formula

in the case of model.frame, a pglmmObj object

type

See details of type options for each function under "Functions" section.

newdata

optional new data.frame containing the same variables used in the model fit procedure

digits

number of significant digits for printing; default of 4

resid_type

type of residuals to summarize in output. See predict.pglmmObj for residual options available.

Value

The pglmmObj object returns the following items:

fixef

vector of fixed effects coefficients

ranef

matrix of random effects coefficients for each explanatory variable for each level of the grouping factor

sigma

random effects covariance matrix

scale

if family is Gaussian, returns the residual error variance

posterior_samples

Samples from the posterior distribution of the random effects, taken at the end of the model fit (after convergence or after maximum iterations allowed). Can be used for diagnositics purposes. Note: These posterior samples are from a single chain.

sampling

character string for type of sampling used to calculate the posterior samples in the E-step of the algorithm

results_all

matrix of results from all model fits during variable selection (if selection performed). Output for each model includes: penalty parameters for fixed (lambda0) and random (lambda1) effects, BIC-derived quantities and the log-likelihood (note: the arguments BIC_option and logLik_calc in selectControl determine which of these quantities are calculated for each model), the number of non-zero fixed and random effects (includes intercept), number of EM iterations used for model fit, whether or not the model converged (0 for no vs 1 for yes), and the fixed and random effects coefficients

results_optim

results from the 'best' model fit; see results_all for details. BICh, BIC, BICNgrp, and LogLik computed for this best model if not previously calculated.

family

Family

penalty_info

list of penalty information

call

arguments plugged into glmm, glmmPen, glmm_FA, or glmmPen_FA

formula

formula

fixed_vars

names of fixed effects variables

data

list of data used in model fit, including the response y, the fixed effects covariates matrix X, the random effects model matrix Z (which is composed of values from the standardized fixed effects model matrix), the grouping factor, offset, model frame, and standarization information used to standardize the fixed effects covariates

optinfo

Information about the optimization of the 'best' model

control_info

optimization parameters used for the model fit

Estep_init

materials that can be used to initialize another E-step, if desired

Gibbs_info

list of materials to perform diagnositics on the Metropolis-within-Gibbs sample chains, including the Gibbs acceptance rates (included for both the independence and adaptive random walk samplers) and the final proposal standard deviations (included for the adaptive random walk sampler only))

r_estimation

list of output related to estimation of number of latent common factors, r. Only relevant for the output of functions glmm_FA and glmmPen_FA, which are currently in development and are not yet ready for general use.

showClass("pglmmObj") methods(class = "pglmmObj")

Functions

  • fixef.pglmmObj: Provides the fixed effects coefficients

  • ranef.pglmmObj: Provides the random effects posterior modes for each explanatory variable for each level of the grouping factor

  • sigma.pglmmObj: Provides the random effect covariance matrix. If family is Gaussian, also returns the standard deviation of the residual error.

  • coef.pglmmObj: Computes the sum of the fixed effects coefficients and the random effect posterior modes for each explanatory variable for each level of each grouping factor.

  • family.pglmmObj: Family of the fitted GLMM

  • nobs.pglmmObj: Number of observations used in the model fit

  • ngrps.pglmmObj: Number of levels in the grouping factor

  • formula.pglmmObj: Formula used for the model fit. Can return the full formula, or just the formula elements relating to the fixed effects (fixed.only = TRUE) or random effects (random.only = TRUE)

  • model.frame.pglmmObj: Returns the model frame

  • model.matrix.pglmmObj: Returns the model matrix of either the fixed (type = "fixed") or random effects (type = "random")

  • fitted.pglmmObj: Fitted values, i.e., the linear predictor of the model.

  • predict.pglmmObj: Predictions for the model corresponding to the pglmmObj output object from the glmmPen package functions. The function predict can predict either the linear predictor of the model or the expected mean of the response, as specified by the type argument. Argument type: character string for type of predictors: "link" (default), which generates the linear predictor, and "response", which generates the expected mean values of the response.

  • residuals.pglmmObj: Residuals for the pglmmObj output object from the glmmPen package functions. Argument type: character string for type of residuals to report. Options include "deviance" (default), "pearson", "response", and "working", which specify the deviance residuals, Pearson residuals, the difference between the actual response y and the expected mean response (y - mu), and the working residuals (y - mu) / mu

  • print.pglmmObj: Prints a selection of summary information of fitted model

  • summary.pglmmObj: Returns a list of summary statistics of the fitted model.

  • logLik.pglmmObj: Returns the log-likelihood using the Corrected Arithmetic Mean estimator with importance sampling weights developed by Pajor (2017). Degrees of freedom give the sum of the non-zero fixed and random effects coefficients. Citation: Pajor, A. (2017). Estimating the marginal likelihood using the arithmetic mean identity. Bayesian Analysis, 12(1), 261-287.

  • BIC.pglmmObj: Returns BIC, BICh (hybrid BIC developed by Delattre et al., citation: Delattre, M., Lavielle, M., & Poursat, M. A. (2014). A note on BIC in mixed-effects models. Electronic journal of statistics, 8(1), 456-475.), BICNgrps (BIC using N = number of groups in the penalty term), and possibly BIC-ICQ (labeled as "BICq") if the argument BIC_option was set to "BICq" in selectControl (citation for BIC-ICQ: Ibrahim, J. G., Zhu, H., Garcia, R. I., & Guo, R. (2011). Fixed and random effects selection in mixed effects models. Biometrics, 67(2), 495-503.)

  • plot.pglmmObj: Plot residuals for the pglmmObj output object from the glmmPen package. Argument type: character string for type of residuals to report. Options include "deviance" (default for non-Gaussian family), "pearson" (default for Gaussian family), "response", and "working", which specify the deviance residuals, Pearson residuals, the difference between the actual response y and the expected mean response (y - mu), and the working residuals (y - mu) / mu


hheiling/glmmPen documentation built on Jan. 15, 2024, 11:47 p.m.