Multiple Imputation for Missing Data in Survival Analysis

This title is printed to order. This book may have been self-published. If so, we cannot guarantee the quality of the content. In the main most books will have gone through the editing process however some may not. We therefore suggest that you be aware of this before ordering this book. If in doubt check either the author or publisher’s details as we are unable to accept any returns unless they are faulty. Please contact us if you have any questions.

In this method a dummy variable for each predictor is included in the regression model. These dummy variables indicate whether or not the data in the predictors is missing (Cohen and Cohen, 1985). Cases with missing data on a predictor are coded as having some constant value, usually the mean for observed cases on that predictor. Though the method use all the available information in the data and may produce reasonably good standard error estimates, it could not become popular as it produces biased estimates of the regression coefficients, even if the data are MCAR (Jones, 1996). There are different methods in which missing values of variables are substituted with some plausible values (Little and Rubin, 2002; Schafer, 1999). The data obtained through these methods are then treated as complete data and is analyzed using conventional statistical methods. Single imputation refers to fill in one value for each missing value in a variable (Haukoos and Newgaurd, 2007). Some single imputation methods are described below.