The Significance Test Controversy by Denton E. Morrison

Author:Denton E. Morrison
Language: eng
Format: epub
Publisher: Transaction Publishers

17. The Sacredness of .05: A Note Concerning the Uses of Statistical Levels of Significance in Social Science

JAMES K. SKIPPER, JR., ANTHONY L. GUENTHER, and GILBERT NASS

Decisions regarding the uses of statistical levels of significance have typically been rendered by social scientists with specialized training and considerable expertise. However, a strong case can be made for more involvement in such issues by researchers whose activities include tests of significance in an applied context. The issue of whether inference should be made at all has been rather thoroughly debated (Selvin, 1957 [Chapter 9]; Gold, 1958 [Chapter 10]; and Kish, 1959 [Chapter 15]),1 but there are indications that the use of present "recommended" levels of significance is due for reassessment. This note attempts to state the problem, explore the issues involved, and suggest an alternative to current policy.

The choice of a statistical level of significance, that is, establishing the probability of rejecting the null hypothesis when in fact it is true, apparently demands little psychic energy on the part of researchers. Casual examination of the literature discloses that the common, arbitrary, and virtually sacred levels of .05, .01, and .001 are almost universally selected regardless of the nature and type of problem. Of these three, .05 is perhaps most sacred.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.