A contribution to adaptive robust estimation

This study initially set out to consider the possibility of constructing an adaptive robust estimation procedure for the standard linear regression model when the disturbance vector deviated from normality, however, after the initial success in that field it seemed only appropriate that the approach be extended to robust location parameter estimation. This is a particular case of the regression model and an area in which a number of different estimators have been proposed and a great deal of comparative research work done. Due to the wider scope of such research the greater part of the thesis is devoted to this field of research which led to many interesting and useful results and conclusions.

Grantor dc:publisher.institution

Department of Statistical Sciences

Year dc:date.issued

1981

Author dc:creator

• Barr, Graham Douglas Irving

Advisors dc:contributor.advisor

• Money, A H
• Affleck-Graves , J F
• Hart, M L

Language dc:language.iso

eng

Handle dc:identifier.uri

http://hdl.handle.net/11427/9905

OAI identifier oai:identifier

oai:open.uct.ac.za:11427/9905