combine.mi: combine.mi

In vahidnassiri/imi: Implemenets Iterative Multiple Imputation

Description

This function combines vectors of estimated parameters and theircovariance matrices from different imputed sets of data using Rubin's rule (Rubin, 1978).

Usage

combine.mi(mi.param.est,mi.param.cov)

Arguments

mi.param.est	A matrix of size number of imputed datasets by number of parameters in the model. Each row of this matrix should present the estimated parameters from each imputed dataset.
mi.param.cov	A list of length number of imputed datasets. Each element of this list is a covariance matrix of the size of the number of parameters in the model.

Value

param.est	The combined vector of estimated parameters.
param.cov	The combined covariance matrix of the estimated parameters.
between.cov	The between-imputation covariance matrix.
within.cov	The within-imputation covariance matrix.

References

Rubin, Donald B. Multiple imputation for nonresponse in surveys. John Wiley & Sons, 1978.

vahidnassiri/imi documentation built on June 25, 2019, 5:50 a.m.