Meehl, P. E. (1978). Theoretical risks and tabular asterisks: Sir karl, sir ronald, and the slow progress of soft psychology. Journal of Consulting and Clinical Psychology, 46(4), 806-834.
From PsychWiki - A Collaborative Psychology Wiki
In this review, Meehl offered his thoughts and critiques regarding the utility of significance testing in soft (or social) sciences. Even though this article is roughly 30 years old, it is still the subject of much discussion and debate in social science related fields. Through a series of well-articulated and complex arguments, Meehl suggested that accepting and rejecting the null (basic significance testing) was flawed in rationale because of different rules that govern the process. He methodically offered 20 separate points to illustrate and support his thoughts on this practice. Although it is impossible to recount each of his twenty main ideas, the critique covers everything from problems of statistical methods to larger philosophical and methodological issues which shape the way that we theorize and understand results in soft sciences.
This article is classic because it was one of the first to debase and challenge the thinking and direction of psychology research. Anyone who attempts to critique the direction of any social science field in the modern day would almost certainly have to reference this critique by Meehl.