Missing data are ubiquitous in psychological research. By missing data, I mean data that are missing for some (but not all) variables and for some (but not all) cases. If data are missing on a variable for all cases, then that variable is said to be latent or unobserved. On the other hand, if data are missing on all variables for some cases, we have what is known as unit non-response, as opposed to item non-response which is another name for the subject of this chapter. I will not deal with methods for latent variables or unit nonresponse here, although some of the methods we will consider can be adapted to those situations.

Why are missing data a problem? Because conventional statistical methods and software presume that all variables in a specified model are measured for all cases. The default method for virtually all statistical software is simply to delete cases with any missing data on the variables of interest, a method known as listwise deletion or complete case analysis. The most obvious drawback of listwise deletion is that it often deletes a large fraction of the sample, leading to a severe loss of statistical power. Researchers are understandably reluctant to discard data that