datsim: Simulate Data for a Single Response Style

Description

Simulate data containing a single repsponse style.

Usage

datsim(
  nr.indv = 100,
  m = 5,
  scales = 1:7,
  err.coeff = 0.1,
  resp.style = c(-Inf, 1/7, 2/7, 3/7, 4/7, 5/7, 6/7, Inf),
  true.mu = NULL,
  a = 0,
  b = 1,
  plot.graph = FALSE,
  use.copula = FALSE,
  reverse.thresh = 1,
  ...
)

Arguments

nr.indv: Integer giving the number of individuals required in the sample.
m: The number of items.
scales: The rating scale used for all items.
err.coeff: The standard error used in simulating the truncated normal distribution.
resp.style: A set of cut points across the interval [0, 1] defining the response style transformation.
true.mu: Optional vector of length m giving the true preferences for the items.
a: Lower boundary of the truncation interval for the simulated true preferences.
b: Upper boundary for the truncation interval for the simulated true preferences.
plot.graph: Logical indicating whether to visualize the response style in a plot.
use.copula: Logical indicating whether to simulate dependent items using a copula.
reverse.thresh: A proportion giving the proportion of item preferences which should be reversed to induce a negative association.
...: Additional arguments passed to plot.

Author

Pieter C. Schoonees

References

Schoonees, P.C., Velden, M. van de & Groenen, P.J.F. (2013). Constrained Dual Scaling for Detecting Response Styles in Categorical Data. (EI report series EI 2013-10). Rotterdam: Econometric Institute.