Abstract
The present paper discusses the problem of estimating the reliability measures of geometric distribution when the sample contains discordant observations. Bayes point estimators of the reliability measures of geometric distribution under the identified, exchangeable and censored models are obtained in the presence of outliers. The performances of the proposed estimators have been compared, in terms of bias and mean square error, using simulated data.
Additional information
Notes on contributors
Mathachan Pathiyil
Mathachan Pathiyil M.Phil from the University of Kerala, Kerala, India. He is currently working as Lecturer, Selection Grade, in the department of Statistics, Nirmala College, Muvattupuzha, Kerala. His research interests include Bayes estimation, inference and reliability analysis. he is active in research and his publications have appeared in statistical literature.
E.S. Jeevanand
E.S Jeevanand Ph.D from the Cochin University of Science and Technology, Cochin, Kerala, India .He is currently working as Reader in Statistics, Union Christian College, Aluva, Kerala. His research interests include Bayes estimation, outlier analysis, reliability, statistical planning and inference and statistical computing. Dr. Jeevanand is a currently Associate Editor of the Multi-disciplinary Journal-Half Yearly Discourses. He is active in research and has published a number of research articles in statistical literature.