A COMPARISON OF REGRESSION METHODS FOR IMPROVED ESTIMATION IN SAMPLING

  • G.C Misra Department of Statistics, D. A. V. College, Kanpur, India
  • A.K. Shukla Department of Statistics, D. A. V. College, Kanpur, India
  • S.K. Yadav Department of Statistics, D. A. V. College, Kanpur, India
Keywords: Inverse term model, linear regression estimator, Polynomial regression, simple random sampling

Abstract

A linear model with an inverse term is proposed for estimation of population mean and population total in regression analysis. A comparison has been made in precisions of estimates of parameters, considering ordinary linear regression estimate, regression estimates using second degree polynomial for relationship between dependent variable ( y )and auxiliary variable ( x ) and also with estimates obtained in regression method of estimation incorporating inverse term model for describing the relationship between y and x. The gain in efficiency is also demonstrated with the help of a data set in which comparison of various estimates of regression method of estimation has also been made with simple random sampling.

 

Downloads

Download data is not yet available.
Published
2009-08-29
Section
Articles