In praise of the null hypothesis statistical test.

Abstract

Jacob Cohen (1994) raised a number of questions about the logic and information value of the null hypothesis statistical test (NHST). Specifically, he suggested that: (a) The NHST does not tell us what we want to know; (b) the null hypothesis is always false; and (c) the NHST lacks logical integrity. It is the author's view that although there may be good reasons to give up the NHST, these particular points made by Cohen are not among those reasons. When addressing these points, the author also attempts to demonstrate the elegance and usefulness of the NHST. ~ n the past 30 years, a series of lively, imaginative articles have chided us for misinterpreting the null hypothesis statistical test (NHST;

A Comparison Of Equivalence Testing In Combination With Hypothesis Testing And Effect Sizes

“…Some classic references criticizing standard hypothesis testing include Boring (1919), Berkson (1938Berkson ( , 1942, Rozeboom (1960), Meehl (1967Meehl ( , 1978, and Carver (1978). More recently, some support the continued usage of significance testing (Abelson, 1997;Hagan, 1997Hagan, , 1998Harris, 1997;McLean & Ernest, 1998), while others desire a greater reliance on alternatives such as confidence intervals or effect sizes (Cohen, 1992(Cohen, , 1994Knapp, 1998Knapp, , 2002Meehl, 1997;Serlin, 2002;Thompson, 1998Thompson, , 2001Vacha-Haase, 2001), and still others advocate an outright ban on significance testing (Carver, 1993;Falk, 1998;Nix & Barnette, 1998;Schmidt & Hunter, 1997).…”

Data analysis in forest sciences: why do we continue using null hypothesis significance tests?

“…Furthermore, it is important to notice that H 0 makes reference to an exact value (usually 0), but H 1 represents all other infinite possibilities. The logical inconsistency of NHSTs is a fact acknowledged by their followers, who recognize some usefulness despite these inconsistencies (Chow 1988, Hagen 1997. As Falk (1998) pointed out, defending a logically invalid argument could make some sense if experience indicates some valid relationship.…”

An empirical analysis of eating disorders and anxiety disorders publications (1980-2000)—part II: Statistical hypothesis testing

“…[1][2][3][4][5][6][7][8][9] Although some critics have questioned the fundamental rationale of hypothesis testing, 3,[10][11][12] others have attempted to articulate the appropriate use of statistical hypothesis testing. [13][14][15][16] In particular, there has been a growing sensitivity to particular issues such as reporting effect sizes and interval estimates, handling multiple statistical tests in terms of inflated alpha, and considering issues of statistical power in behavioral research, all of which were emphasized in the American Psychological Association (APA) Task Force on Statistical Inference. 17 Researchers have also been interested in empirical trends in the social and behavioral sciences literature regarding specific approaches to statistical analysis and hypothesis testing.…”