Preregistration as a way to limit questionable research practice in advertising research

Abstract

This paper discusses two phenomena that threaten the credibility of scientific research and suggests an approach to limiting the extent of their use in advertising research. HARKing (hypothesizing after the results are known) refers to when hypotheses are formulated or modified after the results of a study are known. P-hacking refers to various practices (e.g., adding respondents, introducing control variables) that increase the likelihood of obtaining statistically significant results from a study. Both of these practices increase the risk of false positives (Type I errors) in research results and it is in the interest of the advertising research field that they are limited. Voluntary preregistration, where researchers commit to and register their research design and analytical approach before conducting the study, is put forward as a means to limiting both HARKing and p-hacking.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 17 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.