Genelleştirilmiş T (Gt) Dağılımına Dayalı Regresyon Analizi
Year 2003,
Volume: 2 Issue: 3, 1 - 9, 15.12.2003
Ali İhsan Genç
Olcay Arslan
Abstract
Bu çalışmada y = xβ + u çoklu lineer regresyon modelindeki u hata teriminin 0 ortalamalı ve σ ölçek parametreli genelleştirilmiş t (GT) dağılımından geldiği kabul edilmiştir. GT dağılımının şekil parametrelerinin bilindiği varsayımı altında regresyon modelinin parametreleri ve σ ölçek parametresi tahmin edilmiştir. Önerilen kestirim yöntemi bir takım problemli veri kümelerine uygulanmış ve alınan sonuçlar diğer dayanıklı (robust) kestirimlerle karşılaştırılmıştır.
References
- ANDREWS, D. F. (1974). A robust method for multiple linear regression. Technometrics, 16,4, 523-531.
- ARSLAN, O. (1992). Multivariate robust analysis based on the t distribution and the EM algorithm. Unpublished PhD thesis, Leeds University, Leeds, U.K.
- ARSLAN, O., GENÇ, A. İ. (2002). Robust location and scale estimation based on the univariate generalized t (GT) distribution. (Submitted.)
- ARSLAN (2002). A simple test to identify good solutions to redescending M-estimating equations for regression. In Development in Robust Statistics, Proceedings of ICORS 2001. Edited by R. Dutter, U. Gather, P.J. Rousseeuw and P. Filzmoser, pp. 50-61.
- BLOOMFIELD, P., STEIGER, W. L. (1983). Least Absolute Deviations Theory: Applications and Algorithms. Boston: Birkhauser.
- BUTLER. R. J., McDONALD. J. B .. NELSON, R. D .• WHITE, S. B. (1990). Robust and partially adaptive estimation of regression models. The Review of Economics and Statistics, 72, 321-327.
- KLEIN, R, SPADY, R. (1984). Quasi-maximum Likelihood as o parametric approach to robust estimation. working paper, Bell Communication Research.
- LANGE, K. L ., LlTTLE, J. A., TAYLOR, J. M. G. (1989). Robust statistical modeling using the t distribution. Journal of the American Statistical Association, 84, 881-896.
Year 2003,
Volume: 2 Issue: 3, 1 - 9, 15.12.2003
Ali İhsan Genç
Olcay Arslan
References
- ANDREWS, D. F. (1974). A robust method for multiple linear regression. Technometrics, 16,4, 523-531.
- ARSLAN, O. (1992). Multivariate robust analysis based on the t distribution and the EM algorithm. Unpublished PhD thesis, Leeds University, Leeds, U.K.
- ARSLAN, O., GENÇ, A. İ. (2002). Robust location and scale estimation based on the univariate generalized t (GT) distribution. (Submitted.)
- ARSLAN (2002). A simple test to identify good solutions to redescending M-estimating equations for regression. In Development in Robust Statistics, Proceedings of ICORS 2001. Edited by R. Dutter, U. Gather, P.J. Rousseeuw and P. Filzmoser, pp. 50-61.
- BLOOMFIELD, P., STEIGER, W. L. (1983). Least Absolute Deviations Theory: Applications and Algorithms. Boston: Birkhauser.
- BUTLER. R. J., McDONALD. J. B .. NELSON, R. D .• WHITE, S. B. (1990). Robust and partially adaptive estimation of regression models. The Review of Economics and Statistics, 72, 321-327.
- KLEIN, R, SPADY, R. (1984). Quasi-maximum Likelihood as o parametric approach to robust estimation. working paper, Bell Communication Research.
- LANGE, K. L ., LlTTLE, J. A., TAYLOR, J. M. G. (1989). Robust statistical modeling using the t distribution. Journal of the American Statistical Association, 84, 881-896.