impute.pmm: Elementary Imputation Method: Linear Regression Analysis
Description
Imputes univariate missing data using predictive mean matching
Usage
impute.pmm(y, ry, x)
Arguments
y
Incomplete data vector of length n
ry
Vector of missing data pattern (FALSE=missing, TRUE=observed)
x
Matrix (n x p) of complete covariates.
Value
impA vector of length nmis with imputations.
Details
Imputation of y by predictive mean matching, based on
Rubin (p. 168, formulas a and b).
The procedure is as follows:
enumerate
\itemDraw beta and sigma from the proper posterior
\itemCompute predicted values for yobs and ymis
\itemFor each ymis, find the observation with closest predicted
value, and take its observed y as the imputation.
enumerate
The matching is on yhat, NOT on y, which deviates from formula b.
References
Van Buuren, S. & Oudshoorn, C.G.M. (2000). Multivariate Imputation by Chained Equations:
MICE V1.0 User's manual. Report PG/VGZ/00.038, TNO Prevention and Health, Leiden.
Rubin, D.B. (1987). Multiple imputation for nonresponse in surveys. New York: Wiley.