bootstrap_poisIRT: Parametric Bootstrap of EM Standard Errors

In davidycliao/redguards: A replication package for the paper of "Factionalism and the Red Guards under Mao’s China: Ideal Point Estimation Using Text Data."

Parametric Bootstrap of EM Standard Errors

Description

bootstrap_poisIRT take an poisIRT() object (from emIRT package) and implements a parametric bootstrap of the standard errors for the ideal points. It assumes you have already run the Poisson IRT estimation via EM , and takes the output from that estimate, along with the original dataset, word frequency matrix. This function will conduct a bootstrap by running the estimates from sub-sampled observations based on the a poisson distribution.

Usage

bootstrap_poisIRT(
  emIRT.out,
  .data,
  .starts,
  .priors,
  .control = {     list(threads = 1, verbose = TRUE, thresh = 1e-06, maxit = 5000) },
  set.seed = 1234,
  Ntrials = 5
)

Arguments

emIRT.out	an emIRT() object, which is output from a call to poisIRT
.data	the data used to produce the emIRT object.
.starts	a list containing several matrices of starting values for the parameters, which include alpha A (J x 1) matrix , psi A (K x 1) matrix, beta A (J x 1) matrix and x An (NI x 1) matrix.
.priors	list, containing several matrices of starting values for the parameters. .priors can be generated by create_prior() by default via mu = 0 and variance = 100.

davidycliao/redguards documentation built on Feb. 28, 2023, 11:30 p.m.