ROBUSTNESS AND INTEGRATIVE SURVIVAL IN SIGNIFICANCE TESTING - THE WORLDS CONTRIBUTION TO RATIONALITY

Significance testing is the primary method for establishing causal rel ationships in psychology. Meehl [1978, 1990a, 1990b] and Faust [1984] argue that significance tests and their interpretation are subject to actuarial and psychological biases, making continued adherence to thes e practices irrational, and even partially responsible for the slow pr ogress of the 'soft' areas of psychology. I contend that familiar stan dards of testing and literature review, along with recently developed meta-analytic techniques, are able to correct the proposed actuarial a nd psychological biases. In particular, psychologists embrace a princi ple of robustness which states that real psychological effects are (1) reproducible by similar methods, (2) detectable by diverse means, and (3) able to survive theoretical integration. By contrast, spurious si gnificant findings perish under the strain of persistent tests of thei r robustness. The resulting vindication of significance testing confer s on the world a role in determining the rationality of a method, and also affords us an explanation for the fast progress of 'hard' areas o f psychology.