This is an archived version of the Handbook.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.

Ordinal and measurement scale outcomes are most commonly meta-analysed as dichotomous data (if so see Section 9.4.4) or continuous data (if so see Section 9.4.5) depending on the way that the study authors performed the original analyses.

Occasionally it is possible to analyse the data using proportional odds models where ordinal scales have a small number of categories, the numbers falling into each category for each intervention group can be obtained, and the same ordinal scale has been used in all studies. This approach may make more efficient use of all available data than dichotomization, but requires access to statistical software and results in a summary statistic for which it is challenging to find a clinical meaning.

The proportional odds model uses the proportional odds ratio as the measure of intervention effect (Agresti 1996). Suppose that there are three categories, which are ordered in terms of desirability such that 1 is the best and 3 the worst. The data could be dichotomized in two ways. That is, category 1 constitutes a success and categories 2-3 a failure, or categories 1-2 constitute a success and category 3 a failure. A proportional odds model would assume that there is an equal odds ratio for both dichotomies of the data. Therefore, the odds ratio calculated from the proportional odds model can be interpreted as the odds of success on the experimental intervention relative to control, irrespective of how the ordered categories might be divided into success or failure. Methods (specifically polychotomous logistic regression models) are available for calculating study estimates of the log odds ratio and its standard error and for conducting a meta-analysis in advanced statistical software packages (Whitehead 1994).

Estimates of log odds ratios and their standard errors from a proportional odds model may be meta-analysed using the generic inverse-variance method in RevMan (see Section 9.4.3.2). Both fixed-effect and random-effects methods of analysis are available. If the same ordinal scale has been used in all studies, but has in some reports been presented as a dichotomous outcome, it may still be possible to include all studies in the meta-analysis. In the context of the three-category model, this might mean that for some studies category 1 constitutes a success, while for others both categories 1 and 2 constitute a success. Methods are available for dealing with this, and for combining data from scales that are related but have different definitions for their categories (Whitehead 1994).