[Examples of pitfalls in statistical analysis--6. Evaluation of data consisting of the elapsed time between two events].

In comparing two or more groups, we usually compare the values of averages and/or medians of the groups. We do this because the averages can be easily calculated from the raw data, and because we feel able, to some extent, to recognize the results from the values. However, since the comparison with the averages is only an evaluation of one aspect of the data, we have to keep in mind the risk of unreasonable analysis and erroneous results. Particularly in evaluating data consisting of the elapsed time between two events of interest, survival analysis is a suite of statistical analyses. In this article, I will show an example to illustrate the method used to compare the elapsed time between two groups using survival analysis.