LMERlike-class: Wrapper for lmer/glmer

In RGLab/MAST: Model-based Analysis of Single Cell Transcriptomics

Wrapper for lmer/glmer

Description

A horrendous hack is employed in order to do arbitrary likelihood ratio tests: the model matrix is built, the names possibly mangled, then fed in as a symbolic formula to glmer/lmer. This is necessary because there is no (easy) way to specify an arbitrary fixed-effect model matrix in glmer.

Usage

## S4 method for signature 'LMERlike'
update(object, formula., design, keepDefaultCoef = FALSE, ...)

## S4 method for signature 'LMERlike'
vcov(object, which, ...)

## S4 method for signature 'LMERlike'
coef(object, which, singular = TRUE, ...)

## S4 method for signature 'LMERlike'
logLik(object)

Arguments

object	LMERlike
formula.	formula
design	something coercible to a data.frame
keepDefaultCoef	logical. Should the coefficient names be preserved from object or updated if the model matrix has changed?
...	In the case of vcov, ignored. In the case of update, passed to model.matrix.
which	character, one of 'C', 'D'.
singular	logical. Should NA coefficients be returned?

Value

see the section "Methods (by generic)"

Methods (by generic)

• update(LMERlike): update the formula or design matrix

• vcov(LMERlike): return the variance/covariance of component which

• coef(LMERlike): return the coefficients. The horrendous hack is attempted to be undone.

• logLik(LMERlike): return the log-likelihood

Slots

pseudoMM

part of this horrendous hack.

strictConvergence

logical (default: TRUE) return results even when the optimizer or *lmer complains about convergence

optimMsg

character record warnings from lme. NA_character_ means no warnings.

RGLab/MAST documentation built on Sept. 30, 2023, 1:08 p.m.