Comparing WDEEs and WEEs Methods for Non response Effect Adjustment in Panel Surveys
In most surveys unit nonresponse is a serious problem. This problem also exists in panel surveys. In panel survey we often face with attrition from the second wave. This problem has significantly impact on survey statistics, e. g., biased estimations. Weighting is a method to adjust for unit nonresponse in panel surveys. In this paper we simulate unit nonresponse in the data comes from the British Household Panel Survey and thenadjust for biasedness using Robins et at. (1995) weighted generalized estimating equations (WGEE) method. In a simulation study we compare results of WGEE method with weighted estimating equations method (WEE). Findings of the study show Robins et al. (1995) WGEE method performs better than the WEE method in all cases (different sample sizes, correlations between waves, and nonresponse rates).
- حق عضویت دریافتی صرف حمایت از نشریات عضو و نگهداری، تکمیل و توسعه مگیران میشود.
- پرداخت حق اشتراک و دانلود مقالات اجازه بازنشر آن در سایر رسانههای چاپی و دیجیتال را به کاربر نمیدهد.