sens.wald: Wald Test for Pooled Sensitivity Analysis Results

In davidaarmstrong/SensMiceDA: Multivariate Imputation by Chained Equations (Iteration Step for Sensitivity Analysis)

Description

Uses MIcombine to pool results from models estimated on the sensitivity imputed datasets.

Usage

sens.wald(obj, hyps, sensData, impData, digits=3, ...)

Arguments

obj	A model estimated on the original, list-wise deleted data. The model will be re-estimated on the complete data from the sensitivity analysis and the original mice procedure. Must be a model for which update will work.
hyps	A hypothesis matrix or a symbolic description of hypothesis tests to be passed to linearHypothesis from the car package.
sensData	Output from sens.est that includes multiply imputed datasets under a hypothetical non-ignorable mechanism.
impData	An object of class mids resulting from a call to mice that gives the imputed data assuming ignorability
digits	Number of digits to be printed in output
...	other arguments passed down to the model function, currently not implemented

Details

The function performs a wald test on the pooled coefficient and variance-covariance matrix. Note that currently, this does not use either the correction proposed by Li, Ragunathan and Rubin (1991) or Reiter (2007).

Value

Returns a matrix of average chi-squared statistics and average p-values

Author(s)

Noemie Resseguier, with contributions of Roch Giorgi, David Hajage, Yann De Rycke, Xavier Paoletti and Dave Armstrong

References

Resseguier, N., Giorgi, R. and Paoletti, X. (submitted) How to perform a senstivity analysis exploring the impact of missing not at random data under different sceanrios of non response mechanism with the R software.

Rubin, D.B. Multiple Imputation for Nonresponse in Surveys. New York: John Wiley & Sons, 1987.

van Buuren, S., Groothuis-Oudshoorn, K. MICE: Multivariate Imputation by Chained Equations in R.

See Also

mice, mids, sens.mice, sens.est

davidaarmstrong/SensMiceDA documentation built on July 2, 2019, 12:38 p.m.