This is an archived version of the Handbook. For the current version, please go to training.cochrane.org/handbook/current or search for this chapter here.

We now outline the data that need to be collected from each study for analyses of dichotomous outcomes, continuous outcomes and other types of outcome data. These types of data are discussed in Chapter 9 (Section 9.2). It is usually desirable to collect summary data separately for each intervention group and to enter these into RevMan, where effect estimates can be calculated. Sometimes the required data may be obtained only indirectly, and the relevant results may not be obvious. This section provides some useful tips and techniques to deal with some of these situations. If summary data cannot be obtained from each intervention group, effect estimates may be presented directly. In Section 7.7.7 we describe how standard errors of such effect estimates can be obtained from confidence intervals and P values.