Document Type
Article (Restricted)
Publication Date
1-1-2013
Abstract
The investigation on the identification of outliers in linear regression models can be extended to those for circular regression case. In this paper, we propose a new numerical statistic called mean circular error to identify possible outliers in circular regression models by using a row deletion approach. Through intensive simulation studies, the cut-off points of the statistic are obtained and its power of performance investigated.It is found that the performance improves as the concentration parameter of circular residuals becomes larger or the sample size becomes smaller. As an illustration, the statistic is applied to a wind direction data set.
Keywords
Circular distance, circular regression model, mean circular error, outlier, row deletion
Divisions
MathematicalSciences
Publication Title
Journal of Statistical Computation and Simulation
Volume
83
Issue
2
Publisher
Taylor & Francis
Additional Information
Institute of Mathematical Sciences, University of Malaya