Methods are presented for using linear contrasts to make inferences about differences between the means of several populations on continuous dependent variables. These methods control the experimentwise error rate (the probability of committing one or more type 1 errors in the set of decisions made within the experiment) for linear contrasts which compare some sub-sets of populations with others. Appropriate methods are outlined for testing contrasts which have been planned (i.e., specified independently of the data on which they are tested) and defined post hoc (i.e., after an inspection of the data). We show how these methods can be adapted to the analysis of data from factorial analysis of variance research designs.
References
1.
BaileyB. J. R. (1977), Tables of the Bonferroni t statistic, Journal of the American Statistical Association72, 469–77.
2.
BirdK. D. (1975), Simultaneous contrast testing procedures for multivariate experiments, Multivariate Behavioral Research, 10, 343–52.
3.
BraduD.GabrielK. R. (1974), Simultaneous statistical inference in two-way analysis of variance, Journal of the American Statistical Association69, 428–36.
4.
EinotI.GabrielK. R. (1975), A study of the powers of several multiple comparison procedures, Journal of the American Statistical Association70, 574–83.
5.
GamesP. (1971), Multiple comparisons of means, American Educational Research Journal8, 531–65.
6.
HallW.BirdK. D. (1985), The problem of multiple inference in psychiatric research, Australian and New Zealand Journal of Psychiatry19, 265–74.
7.
HarrisR. (1985), A Primer of Multivariate Statistics, 2nd edn, Academic Press, Orlando.
8.
HaysW. L. (1981), Statistics for the Social Sciences, 3rd edn, Holt Rinehart and Winston, New York.
