Robust Wald-type tests for non-homogeneous observations based on the minimum density power divergence estimator
- 12 Downloads
This paper considers the problem of robust hypothesis testing under non-identically distributed data. We propose Wald-type tests for both simple and composite hypothesis for independent but non-homogeneous observations based on the robust minimum density power divergence estimator of the common underlying parameter. Asymptotic and theoretical robustness properties of the proposed tests are discussed. Application to the problem of testing for the general linear hypothesis in a generalized linear model with a fixed-design has been considered in detail with specific illustrations for its special cases under the normal and Poisson distributions.
KeywordsNon-homogeneous data Robust hypothesis testing Wald-type test Minimum density power divergence estimator Power influence function Linear regression Poisson regression
The authors wish to thank two anonymous referees for several constructive suggestions which have significantly improved the paper. This research has been partially supported by Grant MTM2015-67057-P from Ministerio de Economia y Competitividad, Spain.
- Basu A, Ghosh A, Mandal A, Martin N, Pardo L (2018) Robust Wald-type tests in GLM with random design based on minimum density power divergence estimators. arXiv:1804.00160
- Ghosh A, Basu A (2018) Robust bounded influence tests for independent but non-homogeneous observations. Stat Sin 28(3) (to appear)Google Scholar
- Ghosh A, Martin N, Basu A, Pardo L (2017) A new class of robust two-sample Wald-type tests. arXiv:1702.04552
- Huber PJ (1983) Minimax aspects of bounded-influence regression (with discussion). J Am Stat Assoc 69:383–393Google Scholar
- Rousseeuw PJ, Ronchetti E (1979) The influence curve for tests. Research Report 21, Fachgruppe für Statistik, ETH, ZurichGoogle Scholar