Simultaneous identification of influential subsets and variable selection using quantabilities

Van Vuuren J.O. (2005)

Article

Ideally, outlier detection and variable selection should be dealt with at the same time. Literature, however, proposes only a few practical procedures for handling this problem. A procedure is proposed where dummy variables, variable selection, and a simple selection rule are used to find an optimal model which includes the relevant predictors and excludes the outliers influential on the fit.

Please refer to this item in SUNScholar by using the following persistent URL: http://hdl.handle.net/10019.1/12507
This item appears in the following collections: