Doğrusal Olmayan Regresyondaki Kendinden Eşik Değerli Otoregresif Hatalar Sorununa Uyarlamalı Bir Yaklaşım

Abstract

Bu çalışma, doğrusal olmayan regresyon modellerinde kendinden eşik değerli otoregresif (KEDAR) hataların varlığında etkin parametre kestirimleri elde edebilmeyi amaçlamaktadır. Bu doğrultuda, otoregresif (AR) süreçlere karşı önerilen iki aşamalı en küçük kareler (İAEKK) yöntemi KEDAR süreçleri için ele alınacak ve etkin parametre kestirimleri elde edilebilmesi için uyarlamalı bir yaklaşım araştırılacaktır. Karesel çokterimli (polinomiyel) daraltma fonksiyonu kullanılarak İAEKK yöntemine bir uyarlama yapılıp bu yeni yaklaşımın etkinliği farklı senaryolar altında bir benzetim çalışması ile incelenecektir.

Keywords

• Doğrusal Olmayan Regresyon
• Otokorelasyon
• Kendinden Eşik Değerli Otoregresif Süreçler
• Uyarlamalı İki Aşamalı Yaklaşım

An Adaptive Estimation Method for Nonlinear Regression with Self-Exciting Threshold Autoregressive Errors

Abstract

This study aims to obtain efficient parameter estimates in the presence of self-exciting threshold autoregressive (SETAR) errors in nonlinear regression models. In this way, the two-stage least squares (TSLS) method proposed for autoregressive (AR) processes is discussed for SETAR processes and an adaptive approach is investigated to obtain efficient parameter estimates. An adaptation of TSLS method is made by using a quadratic polynomial tapering function and the efficiency of this new approach is examined with a simulation study under different scenarios.

Keywords

• Nonlinear Regression
• Autocorrelation
• Self-Exciting Threshold Autoregressive Processes
• Adaptive Two-Stage Approach

References

1. Gallant, A.R. (1987). Nonlinear Statistical Models. John Wiley and Sons, New York.
2. Gallant, A.R. ve Goebel, J.J. (1976). Nonlinear regression with autocorrelated errors. Journal of the American Statistical Association, 71(356), 961-967.
3. Glasbey, C.A. (1980). Nonlinear regression with autoregressive time series errors. Biometrics, 36(1), 135-139.
4. Glasbey, C.A. (1979). Correlated Residuals in Nonlinear Regression Applied to Growth Data. Applied Statistics, 28(3), 251-259.
5. Glasbey, C.A. (1988). Examples of Regression with Serially Correlated Errors. The Statistician, 37(3), 277-291.
6. Huang, M.N.L. ve Huang, M.K. (1991). A Parameter-Elimination Method for Nonlinear Regression with Linear Parameters and Autocorrelated Errors. Biometrical Journal, 33(8), 937-950.
7. Bender, R. ve Heinemann, L. (1995). Fitting Nonlinear Regression Models with Correlated Errors to Individual Pharmacodynamic Data Using SAS Software. Journal of Pharmacokinetics and Biopharmaceutics, 23(1), 87-100.
8. Aşıkgil, B. ve Erar, A. (2013). Polynomial tapered two-stage least squares method in nonlinear regression. Applied Mathematics and Computation, 219(18), 9743-9754.

9. Enders, W. (1995). Applied Econometric Time Series. John Wiley and Sons, New York.
10. Tong, H. (1983). Threshold Models in Nonlinear Time Series Analysis. Lecture Notes in Statistics, Springer-Verlag, New York.
11. Tsay, R.S. (1989). Testing and modeling threshold autoregressive processes. Journal of the American Statistical Association, 84(405), 231-240.
12. Chan, K.S. ve Tong, H. (1986). On estimating thresholds in autoregressive models. Journal of Time Series Analysis, 7(3), 179-190.
13. Chan, K.S. (1993). Consistency and limiting distribution of the least squares estimator of a threshold autoregressive model. The Annals of Statistics, 21(1), 520-533.
14. Chan, W.S. ve Cheung, S.H. (1994). On robust estimation of threshold autoregressions. Journal of Forecasting, 13(1), 37-49.
15. Jaras, J. ve Gishani, A.M. (2010). Threshold Detection in Autoregressive Nonlinear Models. MSc. Thesis, Lund University, Sweden.
16. Seber, G.A.F. ve Wild, C.J. (1989). Nonlinear Regression. John Wiley and Sons, New York.
17. Aşıkgil, B. (2018). An Adapted Approach for Self -Exciting Threshold Autoregressive Disturbances in Multiple Linear Regression. Gazi University Journal of Science, 31(4), 1268-1282.