Monte Carlo Simulation Study of Biased Estimators in the Linear Regression Models with Correlated or Heteroscedastic Errors
COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION, cilt.43, sa.5, ss.1143-1186, 2014 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 43 Sayı: 5
- Basım Tarihi: 2014
- Doi Numarası: 10.1080/03610918.2012.728273
- Dergi Adı: COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
- Sayfa Sayıları: ss.1143-1186
- Çukurova Üniversitesi Adresli: Evet
Özet
In this study, the performance of the estimators proposed in the presence of multicollinearity in the linear regression model with heteroscedastic or correlated or both error terms is investigated under the matrix mean square error criterion. Structures of the autocorrelated error terms are given and a Monte Carlo simulation study is conducted to examine the relative efficiency of the estimators against each other.