Problems With Null Hypothesis Significance Testing
In our last column, we discussed inferential statistics and hypothesis testing, both instrumental in the process of null hypothesis significance testing (NHST). Although NHST has been the hallmark of biological, behavioral, and social sciences for most of the past century, objections and concerns have recently increased for two reasons. First, the logic underlying NHST is difficult to understand and appears to be backward. Second, and perhaps more important, NHST is often improperly used in medical and behavioral research.
Gliner, Jeffrey A.; Morgan, George A.; Leech, Nancy L.; and Harmon, Robert J., "Problems With Null Hypothesis Significance Testing" (2001). RSEM Faculty Publications. 32.