Predictive Mean Matching Multiple Imputation Method in Version 4.0

Missing or incomplete responses are a common feature with many clinical trials, censuses and sample surveys. The problem created by a survey non-response is that data values designed to be observed are in fact missing. These missing values not only mean less efficient estimates, but also that standard complete-data methods cannot be used to analyse the data.

Originally proposed by Prof. D. Rubin, Harvard University. multiple imputation is the technique that replaces each missing or deficient value with two or more acceptable values representing a distribution of the possibilities.

Predictive Mean Matching Method

This method applies Ordinary Least Squares Regression for estimating predicted values for each case in the dataset. Rather than using the predicted values for the imputation, they are used to identify similarities between cases with missing values and fully observed cases. Cases are sorted into Donor Pools and similar to the Mahalanobis Distance method, imputations are drawn from these pools.

Check out our website for full details regarding SOLAS for Missing Data Analysis 4.0.

SOLAS for Missing Data Analysis has been developed with guidance from Prof. Donald B. Rubin, the inventor of Multiple Imputation. It provides 9 different methods for imputing missing values, including 5 techniques for multiple imputation.

41