Facebook Instagram Twitter RSS Feed PodBean Back to top on side

Comparison of approximate tests of fixed effects in linear repeated measures design models with covariates

In: Tatra Mountains Mathematical Publications, vol. 39, no. 1
Júlia Volaufová - Lynn Roy Lamotte
Detaily:
Rok, strany: 2008, 17 - 25
O článku:
The topic of testing linear hypotheses about parameters of fixed effects in models with variance-covariance components has been investigated extensively in the past decades. The main question is in determination of the degrees of freedom of an approximate $F$-test. The approximation is based on the choice of the estimate of the approximate variance-covariance matrix of the estimator of the fixed effect parameters. Various approximations have been suggested in the literature and some have already been implemented in statistical packages, such as the generalized Satterthwaite approximation of degrees of freedom, sandwich estimator, the Harville-Jeske-Kenward-Roger approximation, to name a few. For repeated measures designs there are some possibilities of modeling the covariance matrix as well as different choices of approximations. There are still open questions about how the different choices, either of the covariance structure or of the approximating distribution of the test statistic, affect the size (and power) of the tests. Here the sizes of different options of tests are determined and compared by a simulation study.
Ako citovať:
ISO 690:
Volaufová, J., Lamotte, L. 2008. Comparison of approximate tests of fixed effects in linear repeated measures design models with covariates. In Tatra Mountains Mathematical Publications, vol. 39, no.1, pp. 17-25. 1210-3195.

APA:
Volaufová, J., Lamotte, L. (2008). Comparison of approximate tests of fixed effects in linear repeated measures design models with covariates. Tatra Mountains Mathematical Publications, 39(1), 17-25. 1210-3195.