1. unnecessary matching: the pairing of research participants on an excessive number of characteristics or on characteristics having little or no potential influence upon the outcome of interest. For example, a researcher investigating a new drug treatment for cancer might create two groups whose members are of the same age and sex, administering the drug to one group and a placebo to the other group. Such group comparability would allow the researcher greater validity in attributing any changes between them to the treatment rather than to sex or age differences. If, however, the researcher were to pair the groups on such additional factors as area of residence and household income, overmatching would be present and likely to mask the true nature of the relationship under investigation and lead to statistical bias, such as by reducing the power and efficiency of analyses.

2. see matching law.