simdata_2mglrm: Multigroup data

Description Usage Format


Simulated dataset following the mglrm for two groups.




A data frame with 4000 respondents allocated equally to two groups via indicator variable S. They face a test of 20 items Y of which the first 18 are binary and the last two are ordinal with 4 categories. Three covariates X are generated from a multivariate normal distribution, where the variables each have a mean of 0, unit variance and pairwise correlations equal to 0.5. X1 is transformed into a binary variable with a split value of 0. The corresponding parameters of the population model including an intercept are set to γ_1=(-0.5,0.2,0.2,-0.5)', γ_2=(1,0.4,-0.2,-0.7)', σ^2_1=0.5^2 and σ^2_2=0.6^2. 5 percent of the observations in Y18, Y20, X1 and X2 are deleted completely at random.

jcgaasch/LaRA documentation built on Dec. 20, 2017, 12:19 p.m.