MEDIAN BASED MODIFIED RATIO ESTIMATORS WITH KNOWN SKEWNESS AND CORRELATION COEFFICIENT FOR THE ESTIMATION OF FINITE POPULATION MEAN

  • J. Subramani Department of Statistics, Ramanujan School of Mathematical Sciences Pondicherry University, Puducherry, India
  • G. Prabavathy Department of Statistics, Ramanujan School of Mathematical Sciences Pondicherry University, Puducherry, India
Keywords: Bias, Linear Regression Estimator, Mean Squared Error, Natural Population, Simple Random Sampling

Abstract

In this study, two new median based modified ratio estimators with the linear combinations of population correlation coefficient and skewness of an auxiliary variable have been proposed. The bias and mean squared error of the proposed estimators are obtained and the efficiencies of the proposed estimators are compared with that of the simple random sampling without replacement (SRSWOR) sample mean, the usual ratio estimator, the corresponding modified ratio estimators, the linear regression estimator and the median based ratio estimator for certain natural populations. It is shown from the numerical study that the proposed median based modified ratio estimators are outperformed all the existing estimators mentioned above including the linear regression estimator.

 

Downloads

Download data is not yet available.
Published
2015-05-20
Section
Articles