O. Gefeller et al., AN EMPIRICAL-INVESTIGATION ON MATCHING IN PUBLISHED CASE-CONTROL STUDIES, European journal of epidemiology, 14(4), 1998, pp. 321-325
The methodological discussion about matching when recruiting controls
in case-control studies has been controversial for a long time. To del
ineate the impact of this discussion on the practice of matching we re
viewed 266 case-control studies published in nine yearly volumes of th
ree major epidemiological journals within the period 1955-1994. Among
studies published until 1980 71.7% of the control groups were recruite
d by individual matching compared to 46.4% in 1994. This decline is pa
ralleled by an increase in the application of frequency matching (from
5.0% to 26.2%). As the issue of matching is closely connected with me
thodological questions of the statistical analysis we also examined th
e type of analysis applied to the data. We found that the use of logis
tic regression modeling has dramatically increased during this period
(from 18.4% up to 87.2%), whereas application of the traditional Mante
l-Haenszel technique for estimating summary odds ratios has nearly van
ished. The correct approach for individually matched data in the logis
tic modeling framework, the conditional likelihood technique, has been
unknown in the early part of the time window of our investigation, bu
t is even nowadays applied by only three quarters of the corresponding
studies. Our literature-based investigation provides thus compelling
evidence that the type of control selection and statistical, analysis
used in case-control studies have changed substantially during recent
years.