International Journal of Sciences: Basic and Applied Research (IJSBAR) ISSN 2307-4531 http://gssrr.org/index.php?journal=JournalOfBasicAndApplied Combined Estimators as Alternative to Ordinary Least Square Estimator Kayode Ayinde a * a Department of Statistics, Ladoke Akintola University of Technology, P.M.B.4000, Ogbomoso,Oyo State, Nigeria a Email:bayoayinde@yahoo.com Abstract The Ordinary Least Square (OLS) estimator of the classical linear regression model is Best Linear Unbiased Estimator (BLUE) provided the assumptions of the model are not violated. In this paper, attempt is made to combine some Feasible Generalized Least Square (FGLS) estimators with the estimator based on Principal Component (PC) Analysis and compare their finite sampling properties and goodness-of-fit statistics with that of the OLS estimator through Monte Carlo Simulation study. Using both normally and uniformly distributed variables as regressors, results show that the estimators perform better and similar with increased sample sizes and that the results from normally distributed variables are much better on the basis of the criteria. The OLS estimator remains the most efficient and the combined estimators compete favorably with the estimator (OLS) especially when the sample size is large. The combined estimators are frequently more efficient than their separate counterpart estimator, asymptotically equivalent and best in terms of their goodness-of-statistics estimates. Thus, the combined estimators have the advantage of being used better for prediction. Numerical example supports findings. Keywords: OLS Estimator; Combined Estimator; Sampling Properties; Goodness –of – fit Statistics. 1. Introduction The Ordinary Least Square (OLS) estimator developed several years ago is a well known estimator for parameter estimation of the Classical Linear Regression Model. When the assumptions of the model are intact, the estimator is Best Linear Unbiased Estimator (BLUE) and computationally simple to use [1, 2, 3, 4.].Among these assumptions are the assumptions that regressors and error terms being assumed to be independent. The violation of the assumption of independence of regressors leads to multicollinearity while that of error terms results into autocorrelation. Various estimation methods have separately been developed to tackle these problems. Estimators which include the Ridge Regression estimator developed by Hoerl [5] and Hoerl and Kennard [6], Estim- ------------------------------------------------------------- * Corresponding author. Tel.: +234-803-585-0519; E-mail address: kayinde@lautech.edu.ng 74 brought to you by CORE View metadata, citation and similar papers at core.ac.uk provided by GSSRR.ORG: International Journals: Publishing Research Papers in all Fields