rep_style_rel: Replicate a Style Simulation and Investigate Effect on...

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

Description

This function replicates sim_style_data and returns the observed coefficient alpha as well as the response style-free alpha for every replication sample.

Usage

rep_style_rel(reps = 1000, n = c(100, 1000), items = c(5, 10),
  categ = c(3, 7), ndimc = 1, style = NULL, reversed = c(0, 0.5),
  mu.s = c(-1, 1), var.s = c(0, 1), df = 10, sig = NULL, emp = TRUE,
  ...)

Arguments

reps	Numeric, the desired number of replications.
n	Numeric, the number of persons. If of length one, it's fixed to the provided value. If of length two, it's sampled from a uniform distribution using the two values as lower and upper limits, respectively.
items	Numeric, the number of items. If of length one, it's fixed to the provided value. If of length two, it's sampled from a uniform distribution using the two values as lower and upper limits, respectively.
categ	Numeric, the number of categories per item. If of length one, it's fixed to the provided value. If of length two, it's sampled from a uniform distribution using the two values as lower and upper limits, respectively..
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.
reversed	Numeric, the number of reverse-coded items. If of length one, it's fixed to the provided value. If of length two, it's sampled from a uniform distribution using the two values as lower and upper limits, respectively.
mu.s	Numeric, the response style mean. If of length one, it's fixed to the provided value. If of length two, it's sampled from a uniform distribution using the two values as lower and upper limits, respectively.
var.s	Numeric, the response style variance. If of length one, it's fixed to the provided value. If of length two, it's sampled from a uniform distribution using the two values as lower and upper limits, respectively.
df	Numeric. The df-parameter of the Wishart distribution from which the covariance is drawn.
sig	Numeric matrix. The variance-covariance matrix of the multivariate distribution of thetas. If non-NULL, this overrides var.s.
emp	Logical. If true, mu.s and var.s/sig specify the empirical not population mean and covariance matrix.
...	Other parameters passed to sim_style_data.

Value

Returns a matrix of length reps with the following columns:

bias	alpha minus true
true	Response style-free alpha
alpha	Observed coefficient alpha
dep	Response style-dependent alpha, equal to bias
	Further columns contain the input parameters such as the number of categories

See Also

The replicated function sim_style_data, covariate-free alpha alpha_cov

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