Nonparametric model checks for regression
Open Access
- 1 April 1997
- journal article
- Published by Institute of Mathematical Statistics in The Annals of Statistics
- Vol. 25 (2), 613-641
- https://doi.org/10.1214/aos/1031833666
Abstract
In this paper we study a marked empirical process based on residuals. Results on its large-sample behavior may be used to provide nonparametric full-model checks for regression. Their decomposition into principal components gives new insight into the question: which kind of departure from a hypothetical model may be well detected by residual-based goodness-of-fit methods? The work also contains a small simulation study on straight-line regression.Keywords
This publication has 37 references indexed in Scilit:
- Comparing Nonparametric Versus Parametric Regression FitsThe Annals of Statistics, 1993
- Detecting a smooth signal: Optimality of cusum based proceduresBiometrika, 1991
- On the asymptotic power of the two-sided Kolmogorov-Smirnov testJournal of Statistical Planning and Inference, 1990
- An Omnibus Test for Departures from Constant MeanThe Annals of Statistics, 1990
- Lack-of-Fit Testing When Replicates are Not AvailableThe American Statistician, 1989
- Testing Linear Regression Function Adequacy without ReplicationThe Annals of Statistics, 1985
- On Tests Applied to ResidualsJournal of the American Statistical Association, 1984
- Tests Based on Linear Combinations of the Orthogonal Components of the Cramer-von Mises Statistic When Parameters are EstimatedThe Annals of Statistics, 1980
- Testing lack of fit in regression without replicationThe Canadian Journal of Statistics / La Revue Canadienne de Statistique, 1979
- Asymptotic Properties of Tests Based on Linear Combinations of the Orthogonal Components of the Cramer-Von Mises StatisticThe Annals of Statistics, 1977