Meta-Analysis and Science

Abstract

Meta-analytic writers have argued that psychological science is not working and that the solution to the problem is meta-analysis (MA), quantitative summaries of the research literature. This paper assesses these claims by evaluating MA as a means of scientific discovery and by considering the nature of effective science. It is shown that MA should not be credited as a means of discovery because its database, the research literature, is an untrustworthy source of information about nature. The difference between scientific activity, on the one hand, and literature study, on the other, is highlighted in the analyses. Both MA and empirical science are said to be misguided by a hypothesis-testing approach to science, which approach leads to an obliviousness with respect to mechanisms that underlie phenomena.

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 — 16 citations exist upstream.

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