African Journal of
Mathematics and Computer Science Research

  • Abbreviation: Afr. J. Math. Comput. Sci. Res.
  • Language: English
  • ISSN: 2006-9731
  • DOI: 10.5897/AJMCSR
  • Start Year: 2008
  • Published Articles: 262

Full Length Research Paper

Consistent estimators of intrinsically linear econometric model of the Nigerian economy

  Nwabueze Joy Chioma1* and E. Nworuh Godwin2
1Department of Statistics, Abia State University, Uturu, Abia State, Nigeria.   2Department of Project Management, Federal University of Technology Owerri, Imo State, Nigeria.  
Email: [email protected]

  •  Accepted: 05 November 2009
  •  Published: 30 November 2010

Abstract

 

 

This study compares the simulation performance of an operational econometric model of the Nigerian economy. Five estimators namely OLS, 2SPC4, 2SPC6 and 2SPC8 were used to obtain consistent estimators of the structural parameters in an econometric model of the Nigerian economy when some of the equations are non-linear but intrinsically linear. The performance of the estimators was ranked using Friedman’s test statistics based on four criteria namely, root mean square error (RMSE), Theils inequality coefficients, bias and variance proportions. The result of this ranking show that 2SPC6 and 2SPC8 emerged as the best estimators. The least preferred estimators were the OLS and 2SPC4 in that order.

 

Key words: Intrinsically linear model, non-linear, econometric, Friedman test statistic, root mean square error.