Use of the Jackknife Statistic to Evaluate Result Replicability
- 1 July 1998
- journal article
- research article
- Published by Taylor & Francis in The Journal of General Psychology
- Vol. 125 (3) , 218-228
Abstract
Result replicability has often been confused with significance testing because of a misinformed view that statistical significance evaluates result importance and result replicability. Several alternatives, of which the jackknife statistic is one, provide researchers with the tools for estimating result replicability. In the present study, an available data set from A. L. Edwards (1985, p. 57) is used to illustrate the use of the jackknife statistic to assess the replicability of multiple regression results in a concrete fashion. The jackknifed coefficients are computed to assess the stability of beta weights and the multiple R 2 value. Confidence intervals and t statistics are also calculated to facilitate the interpretation of these jackknifed coefficients.Keywords
This publication has 20 references indexed in Scilit:
- The Case Against Statistical Significance Testing, RevisitedThe Journal of Experimental Education, 1993
- Things I have learned (so far).American Psychologist, 1990
- Toward an Operational Definition of the Logic of ConfidenceThe Journal of Experimental Education, 1987
- Cross-Validation for PredictionJournal of Marketing Research, 1987
- Computer-Intensive Methods in StatisticsScientific American, 1983
- The Case Against Statistical Significance TestingHarvard Educational Review, 1978
- Canonical correlation analysis: A general parametric significance-testing system.Psychological Bulletin, 1978
- Validation of Discriminant Analysis in Marketing ResearchJournal of Marketing Research, 1977
- A Cross-Validation Approach to Sample Size Determination for Regression ModelsJournal of the American Statistical Association, 1974
- NOTES ON BIAS IN ESTIMATIONBiometrika, 1956