Cross validation of ridge regression estimator in autocorrelated linear regression models


Acar T. S. , Ozkale M. R.

JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION, cilt.86, ss.2429-2440, 2016 (SCI İndekslerine Giren Dergi) identifier identifier

  • Cilt numarası: 86 Konu: 12
  • Basım Tarihi: 2016
  • Doi Numarası: 10.1080/00949655.2015.1112392
  • Dergi Adı: JOURNAL OF STATISTICAL COMPUTATION AND SIMULATION
  • Sayfa Sayıları: ss.2429-2440

Özet

In this paper, we investigated the cross validation measures, namely OCV, GCV and Cp under the linear regression models when the error structure is autocorrelated and regressor data are correlated. The best performed ridge regression estimator is obtained by getting the optimal ridge parameter so as to minimize these measures. A Monte Carlo simulation study is given to see how the optimal ridge parameter is affected by autocorrelation and the strength of multicollinearity.