ABSTRACT
Now that we have all this useful information, it would be nice to do something with it. (Actually, it can be emotionally fulfilling just to get the information. This is usually only true, however, if you have the social life of a kumquat.)
— UNIX Programmer’s Manual
In his Presidential Address to the American Educational Research Association, Glass (1976) introduced the idea of “metaanalysis,” referring to a statistical integration of a set of studies that ask a common research question. The title of his address, “Primary, Secondary, and Meta-Analysis of Research,” distinguishes three types of data analysis.1 A primary analysis is the initial data analysis for an original research study. A secondary analysis is a reexamination of an existing dataset, possibly with different statistical and/or interpretative tools than originally used or available. Mosteller and Moynihan’s (1972) reanalysis of the Coleman (1966) data on equality of educational opportunity is a famous example of a secondary data analysis. Finally, a meta-analysis combines the analyses (both primary and secondary) for a number of studies into a coherent statistical review. This is in contrast to the more usual discursive literature review that was common up to the time of Glass’s address.
