چکیده:
این مقاله به ارزیابی عملکرد کوچک نمونه ای سه تخمین زن عناصر واریانس در مدل اثرات تصادفی (Random Effects) برای داده های پانل می پردازد. تخمین زن های مربوطه عبارتند از Swamy-Arora، Wansbeek-Kaptayn و Wallace-Hussain در راستای این هدف، بوسیله شبیه سازی یک مدل خطای مرکب یک طرفه در قالب اثرات تصادفی، عملکرد کوچک نمونه ای تخمین زن واریانس عناصر مطالعه می شود. نتایج این شبیه سازی در مورد شناسایی و تخمین مدل مطرح می گردد. به عنوان نتیجه در این شبیه سازی ها، شرایطی بیان می گردد که تحت آنها تخمین زن Swamy-Arora نسبت به سایرین عملکرد بدتری دارد. نشان داده می شود که در نمونه های کوچک، تخمین زن حاصله به شکل بسیار نامطلوبی عمل می کند. در مدل جمله خطای مرکب، منظور از حجم نمونه کوچک، تعداد مقاطع می باشد
This paper presents an assessment of the small-sample performance of the three well-known estimators of components variance in random effects model for panel data. The estimators considered are Swamy-Arora، Wansbeek-Kaptayn and Wallace- Hussain. To this end، by simulating a one-way error component model in the form of random effects، small sample performance of three variance estimators is studied. The implications of these results for indentifying the model and its estimation are specified. In these simulations، conditions under which Swamy-Arora estimator is inferior to alternatives are expressed. It is shown that in small samples the estimator thus obtained can give highly wrong guidance. In one-way error component model this small sample size refers to the number of cross-sections.
خلاصه ماشینی:
"1. Introduction Three well-known components variance estimators in random effects models for panel data, are Swamy-Arora, Wansbeek-Kaptayn and Wallace-Hussain.
com sample justifications and are presented in Section 2, we have mentioned in Section 3 that, by simulating a random effects model and Monte-Carlo experiment based on it, there are cases in which, Swamy-Arora estimator (and the corresponding FGLS estimator of the mean equation) does not have a high mark, hence the alternatives may outperform it.
Method: Pooled EGLS (Cross-section random effects) Date: 01/27/12 Time: 14:34 Sample: 1 10 Included observations: 10 Cross-sections included: 2 Total pool (balanced) observations: 20 Swamy and Arora estimator of component variances Variable Coefficient Std. Error t-Statistic Prob.
Method: Pooled EGLS (Cross-section random effects) Date: 01/27/12 Time: 14:34 Sample: 1 10 Included observations: 10 Cross-sections included: 2 Total pool (balanced) observations: 20 Wallace and Hussain estimator of component variances Variable Coefficient Std. Error t-Statistic Prob.
Method: Pooled EGLS (Cross-section random effects) Date: 01/27/12 Time: 14:35 Sample: 1 10 Included observations: 10 Cross-sections included: 2 Total pool (balanced) observations: 20 Wansbeek and Kapteyn estimator of component variances Variable Coefficient Std. Error t-Statistic Prob.
Method: Panel Least Squares Date: 01/28/12 Time: 18:27 Sample: 1 10 Included observations: 10 Cross-sections included: 2 Total pool (balanced) observations: 20 Variable Coefficient Std. Error t-Statistic Prob.
Method: Panel Least Squares Date: 01/28/12 Time: 18:27 Sample: 1 10 Included observations: 10 Cross-sections included: 2 Total pool (balanced) observations: 20 Variable Coefficient Std. Error t-Statistic Prob."