CoChat
Sign Up
Cited by 701Statistical Methods and Bayesian InferencePsychology Research and BibliometricsMeta-analysis and systematic reviews

The generalizability crisis

Open access
Yarkoni, Tal·2022·Behavioral and Brain Sciences
DOI 10.1017/s0140525x20001685PMC PMC10681374
Open this paper in CoChat — free accountOpen PDF

Abstract

Most theories and hypotheses in psychology are verbal in nature, yet their evaluation overwhelmingly relies on inferential statistical procedures. The validity of the move from qualitative to quantitative analysis depends on the verbal and statistical expressions of a hypothesis being closely aligned – that is, that the two must refer to roughly the same set of hypothetical observations. Here, I argue that many applications of statistical inference in psychology fail to meet this basic condition. Focusing on the most widely used class of model in psychology – the linear mixed model – I explore the consequences of failing to statistically operationalize verbal hypotheses in a way that respects researchers' actual generalization intentions. I demonstrate that although the “random effect” formalism is used pervasively in psychology to model intersubject variability, few researchers accord the same treatment to other variables they clearly intend to generalize over (e.g., stimuli, tasks, or research sites). The under-specification of random effects imposes far stronger constraints on the generalizability of results than most researchers appreciate. Ignoring these constraints can dramatically inflate false-positive rates, and often leads researchers to draw sweeping verbal generalizations that lack a meaningful connection to the statistical quantities they are putatively based on. I argue that failure to take the alignment between verbal and statistical expressions seriously lies at the heart of many of psychology's ongoing problems (e.g., the replication crisis), and conclude with a discussion of several potential avenues for improvement.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1017/s0140525x20001685

Cites

105 of 105 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Randomized controlled trials carry a host of methodological limitations that constrain the inferential scope of their findings.

    “randomized controlled trials carry a host of methodological limitations that constrain the inferential scope of their findings 6,77”

    From Quantifying the prevalence and impact of overreaching causal claims in social science (2026) · cites this paper as [6]

    In “Beyond random subjects” and “Generalizing the generalizability problem” (pages unavailable), Yarkoni argues that unmodeled factors can sharply limit the scope of inferences from experimental studies. The paper also discusses tightly controlled randomized experiments, but the cited passages do not specifically establish a host of limitations of randomized controlled trials as such. (LLM, conf=0.82)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 12

  1. Balota DA, Yap MJ, Hutchison KA, & Cortese MJ (2012). Megastudies: What do millions (or so) of trials tell us about lexical processing? In Adelman JS (Ed.), Visual word recognition volume 1: Models and methods, orthography and phonology (pp. 90– 115). Psychology Press.
  2. Bates D, Maechler M, Bolker B, Walker S, Christensen RHB, Singmann H, … Krivitsky PN (2014). Lme4: Linear mixed-effects models using eigen and S4. R Package Version, 1(7), 1– 23.
  3. Breiman L. (2001). Statistical modeling: The two cultures. Statistical Science, 16(3), 199– 215.
  4. Brunswik E. (1947). Systematic and representative design of psychological experiments. In Proceedings of the Berkeley symposium on mathematical statistics and probability (pp. 143– 202).
  5. Cohen J. (2016). The earth is round (p < 0.05). In Harlow LL, Mulaik SA, & Steiger JH (Eds.), What if there were no significance tests? (pp. 69– 82). Routledge.
  6. Feynman RP (1974). Cargo cult science. Engineering Sciences, 37(7), 10– 13.
  7. Mayo DG (2018). Statistical inference as severe testing. Cambridge University Press.
  8. Meehl P. (1997). The problem is epistemology, not statistics: Replace significance tests by confidence intervals and quantify accuracy of risky numerical predictions. In Harlow LL, Mulaik SA & Steiger JH (Eds.), What if there were no significance tests? (pp. 393– 425). Erlbaum.
  9. Meehl PE (1986). What social scientists don’t understand. In Fiske DW & Shweder RA (Eds.), Metatheory in social science: Pluralisms and subjectivities (pp. 315– 338). University of Chicago Press.
  10. Shavelson RJ, & Webb NM (1991). Generalizability theory: A primer. SAGE.
  11. Trafimow D. (2014). Editorial. Basic and Applied Social Psychology, 36(1), 1– 2.
  12. Trafimow D, Marks M (2015). Editorial. Basic and Applied Social Psychology, 37(1), 1– 2.

Cited by

Sorted by citations

Authors
Yarkoni, T.
Affiliations
The University of Texas at Austin (US)
Corresponding author
Yarkoni, Tal
ORCID
Yarkoni, Tal
Venue
Behavioral and Brain Sciences
Publisher
Cambridge University Press (CUP)
Published
2020-12-21
Volume
45
Pages
e1-e1
ISSN
  • 0140-525X (ISSN-L)
  • 1469-1825
DOI
10.1017/s0140525x20001685
PMC
PMC10681374
OpenAlex
W3117111924
Cited by
701
References
105
Citations by year
2026: 72 · 2025: 118 · 2024: 123 · 2023: 137 · 2022: 120 · 2021: 95 · 2020: 34 · 2019: 1
FWCI
68.01
Type
journal article
Language
en
Open access
Licence
www.cambridge.org/core/terms (unspecified)
Locations
  • Behavioral and Brain Sciences (publishedVersion)
  • PubMed (publishedVersion)
  • PubMed Central (acceptedVersion)
Funders
  • National Institutes of Health
  • Engineering and Physical Sciences Research Council (EP/T033967/1)
  • National Institute of Mental Health (R01MH109682, R01MH096906)
Topics
  • Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
  • Social Sciences › Psychology › Experimental and Cognitive Psychology › Psychology Research and Bibliometrics
  • Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
Keywords
generalizability, linear mixed models, random effects, false positive rate, replication crisis, interindividual variability
MeSH terms
Humans, Psychology, Intention

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review