mirtjml_conf: Constrained joint maximum likelihood estimation for...

In mirtjml: Joint Maximum Likelihood Estimation for High-Dimensional Item Factor Analysis

Description

Constrained joint maximum likelihood estimation for confirmatory item factor analysis on the multidimensional two parameter logistic model.

Usage

mirtjml_conf(
  response,
  Q,
  theta0,
  A0,
  d0,
  cc = NULL,
  tol = 5,
  print_proc = TRUE
)

Arguments

response	N by J matrix containing 0/1/NA responses, where N is the number of respondents, J is the number of items, and NA indicates a missing response.
Q	J by K matrix containing 0/1 entries, where J is the number of items and K is the number of latent traits. Each entry indicates whether an item measures a certain latent trait.
theta0	N by K matrix, the initial value of latent factor scores for each respondent.
A0	J by K matrix, the initial value of loading matrix, satisfying the constraints given by Q.
d0	Length J vector, the initial value of intercept parameters.
cc	A constant constraining the magnitude of the norms of person and item parameter vectors.
tol	The tolerance for convergence with a default value 5.
print_proc	Print the precision during the estimation procedure with a default value TRUE.

Value

The function returns a list with the following components:

theta_hat

The estimated person parameter matrix.

A_hat

The estimated loading parameter matrix

d_hat

The estimated intercept parameters.

References

Chen, Y., Li, X., & Zhang, S. (2019). Structured Latent Factor Analysis for Large-scale Data: Identifiability, Estimability, and Their Implications. Journal of the American Statistical Association <doi: 10.1080/01621459.2019.1635485>.

Examples

# load a simulated dataset
attach(data_sim)

# generate starting values for the algorithm
A0 <- Q
d0 <- rep(0, J)
theta0 <- matrix(rnorm(N*K, 0, 1),N)

# use all available cores by running
# setMIRTthreads(-1)

# run the confirmatory analysis
res_conf <- mirtjml_conf(response, Q, theta0, A0, d0)

mirtjml documentation built on July 1, 2020, 6:05 p.m.