mice.impute.2l.glm.pois {micemd}

Imputation of count variable using a Bayesian mixed model based on non-informative prior distributions

Description

Imputes univariate missing data using a Bayesian mixed model (Poisson regression) based on non-informative prior distributions. The method is dedicated to a count outcome stratified in severals clusters. Should be used with few clusters and few individuals per cluster. Can be very slow to perform otherwise.

Usage

mice.impute.2l.glm.pois(y, ry, x, type,...)

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.

type

Vector of length ncol(x) identifying random and class variables. Random variables are identified by a '2'. The class variable (only one is allowed) is coded as '-2'. Random variables also include the fixed effect.

...

Other named arguments.

Details

Imputes univariate missing data using a Bayesian mixed model (Poisson regression) based on non-informative prior distributions. The variability on the parameters of the imputation is propagated according to an explicit Bayesian modelling. More precisely, improper prior distributions are used for regression coefficients and variances components. The method is recommended for datasets with a small number of clusters and a small number of individuals per cluster. Otherwise, the method can be very slow to perform.

Value

A vector of length nmis with imputations.

Author(s)

Vincent Audigier [e-mail] from the R code of Shahab Jolani.

References

Jolani, S., Debray, T. P. A., Koffijberg, H., van Buuren, S., and Moons, K. G. M. (2015). Imputation of systematically missing predictors in an individual participant data meta-analysis: a generalized approach using MICE. Statistics in Medicine, 34(11):1841-1863. doi:10.1002/sim.6451

See Also

mice,mice.impute.2l.2stage.pois