|
Activity Number:
|
99
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Monday, August 3, 2009 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #304056 |
|
Title:
|
Modified Ratio Estimators in Simple Random Sampling
|
|
Author(s):
|
Evrim Oral*+ and Cem Kadilar
|
|
Companies:
|
Louisiana State University Health Sciences Center and Hacettepe University
|
|
Address:
|
School of Public Health, New Orleans, LA, 70112,
|
|
Keywords:
|
Survey methods ; Ratio type estimators ; Simple random sampling ; Robust regression ; Modified maximum likelihood
|
|
Abstract:
|
In sampling theory when the correlation between study variable and auxiliary variable is positively high, the classical ratio estimator (RE) is the most practicable estimator to estimate the population mean. Sisodio and Dwivedi(1981) and Upadhyaya and Singh(1999) suggested to use population information of the auxiliary variable to increase the efficiency of the RE. Kadilar and Cingi(2004) combined this suggestion with the estimators in Ray and Singh(1981) and proposed novel ratio estimators. In this study, we adapt robust regression to the Kadilar-Cingi estimators (KCE) and obtain the conditions where these adapted estimators are more efficient than KCE theoretically. We support the theoretical results with simulations and compare the adapted estimators both with KCE and the classical RE. We study the robustness properties of the new estimators via simulations and give a real life example.
|
