The DOI matches its Crossref record; 10 of the 11 references it cites were found in a registry or an index.
A Fail-Safe N for Effect Size in Meta-Analysis
Abstract
Rosenthan's (1979) concept of fail-safe N has thus far been applied to probability levels exclusively. This note introduces a fail-safe TV for effect size. Rosenthal's (1979) fail-safe N was an ingenious response to the so-called file drawer problem in research integration, in that it provided a direct assessment of the threat posed by sampling bias in the literature search. The algorithm was derived from the Stouffer method (Mosteller & Bush, 1954), in which an overall Z-score is computed by summing individual Z-scores and dividing by the square root of the number of scores. A significant overall Z-score, Rosenthal reasoned, could be made nonsignificant by adding some knowable number of hypothetical studies that averaged null results. The exact number of such studies needed to bring a significant overall p level up to some critical level (e.g., .05) has since become known as the fail-safe N (Nfs). The formula is
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“we also calculated the classic fail-safe N test (Orwin, 1983), which revealed that it would take 59 studies reporting null results (g = 0) to be included in our analyses in order for our findings to lose statistical significance.”
From Improving fluid intelligence with training on working memory: a meta-analysis (2015) · cites this paper as Orwin, 1983
In the citing paper
“The file drawer problem (publication bias) was examined by creating a funnel plot and calculating the fail safe N (45).”
From A Meta-Analysis of the Corpus Callosum in Autism (2009) · cites this paper as [45]
Citations
Cites
Statistical power analysis for the behavioral sciences
Cohen, J. (1990) · Computers Environment and Urban Systems · doi:10.1016/0198-9715(90)90050-4 · Cited by 65,417
The file drawer problem and tolerance for null results.
Rosenthal, R. (1979) · Psychological Bulletin · doi:10.1037/0033-2909.86.3.638 · Cited by 9,068
Distribution Theory for Glass's Estimator of Effect Size and Related Estimators
Hedges, L. V. (1981) · Journal of Educational Statistics · doi:10.2307/1164588 · Cited by 5,695
Primary, Secondary, and Meta-Analysis of Research
GLASS, G. V. (1976) · Educational Researcher · doi:10.3102/0013189x005010003 · Cited by 4,890
Smith, M. L., Glass, G. V., & Miller, T. I. (1980) · Medical Entomology and Zoology · Cited by 2,123
Johnson, D. W., Maruyama, G., Johnson, R., Nelson, D., & Skon, L. (1981) · Psychological Bulletin · doi:10.1037/0033-2909.89.1.47 · Cited by 1,588
Interpersonal expectancy effects: the first 345 studies
Rosenthal, R., & Rubin, D. B. (1978) · Behavioral and Brain Sciences · doi:10.1017/s0140525x00075506 · Cited by 1,158
Eagly, A. H., & Carli, L. L. (1981) · Psychological Bulletin · doi:10.1037/0033-2909.90.1.1 · Cited by 541
Cooper, H. M. (1979) · Journal of Personality and Social Psychology · doi:10.1037/0022-3514.37.1.131 · Cited by 418
Arkin, R. M., Cooper, H., & Kolditz, T. A. (1980) · Journal of Personality · doi:10.1111/j.1467-6494.1980.tb02378.x · Cited by 88
Flagged first, then by citations
1 of the 11 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Emotion-regulation strategies across psychopathology: A meta-analytic review
Aldao, A., Nolen-Hoeksema, S., & Schweizer, S. (2010) · Clinical Psychology Review · doi:10.1016/j.cpr.2009.11.004 · Cited by 6,686
The Handbook of Research Synthesis and Meta-Analysis
(2019) · doi:10.7758/9781610448864 · Cited by 4,553
Neurocognitive deficit in schizophrenia: A quantitative review of the evidence.
Heinrichs, R. W., & Zakzanis, K. K. (1998) · Neuropsychology · doi:10.1037/0894-4105.12.3.426 · Cited by 2,798
van Zomeren, M., Postmes, T., & Spears, R. (2008) · Psychological Bulletin · doi:10.1037/0033-2909.134.4.504 · Cited by 2,714
“First, the fail-safe N (Orwin, 1983; Rosenthal, 1979) for all three predictor samples suggests that many more independent samples showing null effects are needed before mean effect sizes are reduced to small effects (r .”
BackgroundEllis, P. D. (2010) · doi:10.1017/cbo9780511761676 · Cited by 2,461
Metadata
- Authors
- Orwin, R. G.
- Affiliations
- United States Department of Health and Human Services (US)
- Corresponding author
- Orwin, Robert G.
- Venue
- Journal of Educational Statistics
- Publisher
- JSTOR
- Published
- 1983
- Volume
- 8
- Issue
- 2
- Pages
- 157
- ISSN
- 0362-9791 (ISSN-L)
- OpenAlex
- W2112432954
- Cited by
- 2,064
- References
- 11
- Citations by year
- 2026: 51 · 2025: 75 · 2024: 91 · 2023: 121 · 2022: 114 · 2021: 129 · 2020: 129 · 2019: 120 · 2018: 116 · 2017: 109 · 2016: 95 · 2015: 113 · 2014: 108 · 2013: 76 · 2012: 88
- FWCI
- 7.68
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Journal of Educational Statistics (publishedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- Topics
- Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Psychology Research and Bibliometrics
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Epidemiology
- Keywords
- effect size, file drawer problem, sampling bias, negative results, meta-analysis, publication bias
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
