[EMAIL PROTECTED] (Sapsi) wrote in message news:<[EMAIL PROTECTED]>... > Hi, > We are doing a regression, however there a plenty of missing values, > which cannot be dropped, so somehow have to be imputed. > Ther are some options, > a) Replace the problem regressor by a dummy variable > b) Replace the missing by median (it is demographic data) > c) Replace the missing data by the trimmed/winsorized mean. > d) Replace by mode > > Which is better altenative??
Most likely none of the above. Frank Harrell's book "Regression Modelling Strategies" is more helpful than most books when it comes to missing values. (Actually, if you see this post Frank, I'm quite impressed with the book for a variety of reasons.) Glen . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
