mice.impute.2l.pmm: Two-level predictive mean matching

In kkleinke/countimp: Multiple Imputation of incomplete count data

Two-level predictive mean matching

Description

The function imputes an incomplete variable based on a normal linear mixed effects model. The model is estimated using function glmmPQL() from package MASS. Matching is done by .pmm.match from package mice.

Usage

mice.impute.2l.pmm(y, ry, x, type, intercept = TRUE, donors = 5,
  wy = NULL, ...)

Arguments

y	Numeric vector with incomplete data
ry	Response pattern of y (TRUE=observed, FALSE=missing)
x	matrix with length(y) rows containing complete covariates
type	vector of length ncol(x) determining the imputation model; type is automatically extracted from the predictorMatrix argument of mice().
intercept	Logical. shall the intercept be included as a fixed and random effect?. TRUE = yes; FALSE = fixed effect only.
donors	The size of the donor pool; default is 5.
wy	Logical vector of length length(y). A TRUE value indicates locations in y for which imputations are created. Default is !ry
...	additional arguments passed down from the main mice call

Details

Model specification / allowed entries in mice's predictorMatrix:

• 0 = variable not included in imputation model

• 1 = fixed effect

• 2 = fixex and random effect

• -2 = class variable

Value

vector with imputations

Author(s)

Kristian Kleinke

References

• Kleinke, K. (2016, September). Multiple Imputation of Multilevel Data by "Two-Level Predictive Mean Matching". Paper presented at the 50th Congress of the German Psychological Society (DGPs), Leipzig, Germany.

kkleinke/countimp documentation built on Nov. 5, 2024, 11:51 a.m.