HARKing: Hypothesizing After the Results are Known

By N. Kerr. 1998

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Surrogate Science (2015, background): “Unfortunately, to the present day, many researchers first look at the data for patterns, check for significance, and then present the result as if it were a hypothesis test (Kerr, 1998).”
An Agenda for Open Science in Communication (2020, methodology): “This QRP is known as HARKing, an acronym for Hypothesizing After Results are Known (Kerr, 1998).”
P-curve: a key to the file-drawer. (2014, unknown): “Sometimes one may worry that the authors of a study modify their “predictions” upon seeing the data (Kerr, 1998), such that an interaction is reported as predicted to reverse sign only because this is what occurred.”
Robust Modeling in Cognitive Science (2019, unknown): “A closely related fourth problem is the possibility of selective reporting and hypothesizing after empirical results are known, sometimes called “HARKing” (see Bones 2012; Kerr 1998; and Fig.”
The Chrysalis Effect (2017, result): “Insight can still be gained from these surprising findings, hence the convention of two-tailed statistical significance tests, but if the a priori hypothesis was not supported, then changing the hypothesis to conform to the data capitalizes on chance (Bedeian, Taylor, & Miller, 2010; Kerr, 1998).”
Towards a taxonomy of research misconduct: The case of business school research (2019, background): “Another form of questionable data manipulation is HARKing or Hypothesizing After the Results are Known (Kerr, 1998) – i.”
How Trustworthy Is the Scientific Literature in Industrial and Organizational Psychology? (2013, background): “The lack of exact replication studies prevents the opportunity to disconfirm research results and thus to falsify theories (Kerr, 1998; Leung, 2011; Popper, 1959).”