sim_style_data: Simulate Data From a Multidimensional Rasch Model

In hplieninger/stylesim: Simulate (and Analyse) Data Distorted by Response Styles

Description

This function allows to simulate data from a multidimensional Rasch model, in which one (or more) latent variables represent response styles such as extreme response style or acquiescence.

Usage

sim_style_data(n = 200, items = 10, categ = 5, ndimc = 1,
  style = NULL, irtmodel = "RSM", reversed = 1/3, var.s, mu.s = 0,
  cor.cc, pop.thres = FALSE, my.theta, my.thres, emp = TRUE, sig = NULL)

Arguments

n	Numeric. Desired number of observations/persons.
items	Numeric. Desired number of items/stimuli. If ndimc > 1, this specifies the number of items per dimension.
categ	Numeric. Desired number of categories per item.
ndimc	Numeric. Desired number of content-related latent variables (irrespective of number of style-related latent variables).
style	Parameter to specify which response style(s) influence the data, can be either numeric or character. Users may choose one or more among "ERS1" (e.g., 1 / 0 / 0 / 0 / 1), "ERS2" (e.g., 2 / 1 / 0 / 1 / 2), "ARS" (e.g., 0 / 0 / 0 / 1 / 1), "ADRS" (e.g, -1 / -1 / 0 / 1 / 1), and "MRS" (e.g., 0 / 0 / 1 / 0 / 0). Alternatively, a user-specified vector of weights can be employed. Can also be NULL indicating complete abscence of response styles.
irtmodel	A character string indicating which model to use. Currently available is "RSM" (i.e., rating scale model).
reversed	Numeric. Indicates the number of reverse-coded items. Can be either a ratio between 0 and 1 indicating the ratio of reverse-coded items or an integer between 0 and items) indicating the number of reverse-coded items.
var.s	Numeric. The variance(s) of the response style distribution.
mu.s	Numeric. The mean(s) of the response style distribution.
cor.cc	An optional vector indicating the correlation between the content-related variables (if ndimc > 1). If ndimc > 2, cor.cc is recycled if it is not of length ndimc*(ndimc-1)/2.
pop.thres	Logical. If TRUE, the thresholds of the RSM are set to their expected value.
my.theta	Optional argument to employ a pre-specified vector of person parameters theta
my.thres	Optional argument to employ a pre-specified vector of item parameters.
emp	Logical. If true, mu.s and var.s/sig specify the empirical not population mean and covariance matrix.
sig	Numeric matrix. The variance-covariance matrix of the multivariate distribution of thetas. If non-NULL, this overrides var.s.

Value

Returns a list containing the data and basically a summary of the input specifications:

dat	An array containing the data/responses of format n x items x ndimc
theta	A matrix containing the true person parameters of format n x (ndimc + length(style)). For example, if ndimc = 1, and style = c("ERS1", "ARS"), then the second column corresponds to "ERS1" and the third column to "ARS".
item.par	A vector of item parameters
n	n
items.per.dim	Number of items per dimension
rev.coded.items	Number of reverse-coded items per dimension
categories	categ
irtmodel	irtmodel
dims.content	ndimc
var.style	Variance of the style-related latent variable(s).
c.c.cor	Correlation of the content-related latent variables.
response.style	style – The specified response style(s) coding – The implied coding scheme mu – mu.s sig – The employed variance-covariance matrix

References

Adams, R. J., Wilson, M., & Wang, W.-C. (1997). The multidimensional random coefficients multinomial logit model. Applied Psychological Measurement, 21, 1-23. doi:10.1177/0146621697211001

Plieninger, H. (in press). Mountain or molehill: A simulation study on the impact of reponse styles. Educational and Psychological Measurement.

Wetzel, E. & Carstensen, C. H. (2015). Multidimensional modeling of traits and response styles. European Journal of Psychological Assessment. Advance online publication. doi:10.1027/1015-5759/a000291

hplieninger/stylesim documentation built on May 17, 2019, 4:54 p.m.