No Detail Found!

Modified Regression Estimators for Improving Mean Estimation -Poisson Regression Approach

Author(s)
Zakir Hussain Wani Division of Statistics and Computer Science,Main Campus SKUAST-J, Chatha Jammu-180009,India
S.E.H. Rizvi Division of Statistics and Computer Science,Main Campus SKUAST-J, Chatha Jammu-180009,India
Manish Sharma Division of Statistics and Computer Science,Main Campus SKUAST-J, Chatha Jammu-180009,India
M. Iqbal Jeelani Division of Statistics and Computer Science,Main Campus SKUAST-J, Chatha Jammu-180009,India
Saqib Mushtaq Department of Mathematics, Main Campus University of Kashmir Srinagar-190006-India
Abstract
In this article, a class of Poisson-regression based estimators has been proposed for estimating the finite population mean in simple random sampling without replacement (SRSWOR). The Poisson-regression model is the most common method used to model count responses in many studies. The expression for bias and mean square error (MSE) of proposed class of estimators are obtained up to first order of approximation. The proposed estimators have been compared theoretically with the existing estimators, and the condition under which the proposed class of estimators perform better than existing estimators have been obtained. Two real data sets are considered to assess the performance of the proposed estimators. Numerical findings confirms that the proposed estimators dominate over the existing estimators such as Koc (2021) and Usman et al. (2021) in terms of mean squared error.
Publication Details
Page(s) 985-994
DOI 10.18187/pjsor.v18i4.3955
Published Journal: Pakistan Journal of Statistics and Operation Research, Volume: 18, Issue: 4, Year: 2022

Request the full text from PASTIC

Keywords
efficiency, mean square error, Bias, Auxiliary Variable, Ratio estimator., Poisson regression
More from Pakistan Journal of Statistics and Operation Research
0

Citations

0

Downloads

65

Views

Copyright ©  PASTIC National Center, Islamabad www.pastic.gov.pk