Abstract
The overwhelming number of different types of multiple-comparison procedures has been one of the main sources of confusion in the use of statistical analyses for many years. One method of approaching the problem is to compare the various procedures in terms of their emphases on Type I and Type II errors. The primary issue in the choice of multiple-comparison procedures is how much Type I error should be controlled for and how much Type II should be controlled for. Various multiple-comparison procedures are examined from a historical perspective, with a focus on Type I and Type II errors. As a result, a combination of high emphasis on Type II error and multiple experimentation is found to be a highly commendable choice.