On Piecemeal Testing and The Possibility of Psychological Science

Abstract

This paper examines the practice of piecemeal testing in psychological science. We appraise a recent line of argument against its use in practice based on the conclusions drawn from a thought experiment purporting to show that piecemeal testing, even when confirmatory, can reduce the scope of a scientific theory to the extent that it applies to no one at all. We show that the line of reasoning fails to mount a compelling case against piecemeal testing. In addition to being founded upon a naive and unworkable logico-mathematical conception of scientific theory, the argument effectively imposes a rigid idealization of uncertainty over statistical quantities, enforces an untenable relationship between prediction satisfaction and individual differences, and incorrectly treats instances where no prediction is made as predictive failures.

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 — 2 citations exist upstream.

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