This is an archived version of the Handbook.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.

The term ‘continuous’ in statistics conventionally refers to data that can take any value in a specified range. When dealing with numerical data, this means that any number may be measured and reported to arbitrarily many decimal places. Examples of truly continuous data are weight, area and volume. In practice, in Cochrane reviews we can use the same statistical methods for other types of data, most commonly measurement scales and counts of large numbers of events (see Section 9.2.4).

Two summary statistics are commonly used for meta-analysis of continuous data: the mean difference and the standardized mean difference. These can be calculated whether the data from each individual are single assessments or change from baseline measures. It is also possible to measure effects by taking ratios of means, or by comparing statistics other than means (e.g. medians). However, methods for these are not addressed here.