Testing hypotheses for linear functions of parameters in

Rok, strany: 1999, 103 - 110

In the paper an effective method of testing hypotheses for fixed effects and variance components in mixed linear model is presented. The well known $F$-test for vanishing linear estimable functions of fixed effects and single variance components is derived from quadratic unbiased estimators of corresponding quadratic function of fixed parameters or variance components. The test rejects null hypothesis if the ratio of positive and negative part of this estimator is sufficiently large. This approach gives unified theory of testing hypotheses both for fixed effects and variance components.

ISO 690:

Michalski, A., Zmyślony, R. 1999. Testing hypotheses for linear functions of parameters in. In Tatra Mountains Mathematical Publications, vol. 17, no.3, pp. 103-110. 1210-3195.

APA:

Michalski, A., Zmyślony, R. (1999). Testing hypotheses for linear functions of parameters in. Tatra Mountains Mathematical Publications, 17(3), 103-110. 1210-3195.