How to Use the Two Sample t‐Test
- 1 January 1986
- journal article
- research article
- Published by Wiley in Biometrical Journal
- Vol. 28 (2) , 131-148
- https://doi.org/10.1002/bimj.4710280202
Abstract
This work discusses how two sample t‐tests behave when applied to data that may violate the classical statistical assumptions of independence, heteroscedasticity and Gaussianity. The usual two sample t‐statistic based on a pooled variance estimate and the Welch‐Aspin statistic are treated in detail. Practical “rules‐of‐thumb” are given along with their applications to various examples so that readers will easily be able to use such tests on their own data sets.Keywords
This publication has 26 references indexed in Scilit:
- Use of the one sample t-test in the real worldJournal of Chronic Diseases, 1984
- Playing Safe with Misweighted MeansJournal of the American Statistical Association, 1982
- Levels of significance of some two-sample tests wkem observations are from compound normal distributionsCommunications in Statistics - Theory and Methods, 1976
- The Behrens-Fisher problem, an old solution revisitedMetrika, 1975
- The two-sample trimmed t for unequal population variancesBiometrika, 1974
- Probabilities of the Type I Errors of the Welch Tests for the Behrens-Fisher ProblemJournal of the American Statistical Association, 1971
- Non-normality in two-sample t-testsBiometrika, 1953
- TABLES FOR USE IN COMPARISONS WHOSE ACCURACY INVOLVES TWO VARIANCES, SEPARATELY ESTIMATEDBiometrika, 1949
- THE COMPARISON OF SAMPLES WITH POSSIBLY UNEQUAL VARIANCESAnnals of Eugenics, 1939
- THE FIDUCIAL ARGUMENT IN STATISTICAL INFERENCEAnnals of Eugenics, 1935