Abstract
In sample survey methods the use of product estimators was suggested byMurthy [1964] andSrivastava [1966] and were found to serve good purpose provided the two variables viz. the main variable under study and the auxiliary variable have a very high negative correlation between them. The product estimators suggested by them are biased. In the present paper the author has obtained unbiased product estimators (to the first degree of approximation) with the help of the technique developed byQuenouille [1956] and has established that this new estimator is better than the other product estimator in the mean square error sense.
Similar content being viewed by others
References
Durbin, J.: A note on the application of Quenouille's method of bias reduction to the estimation of ratios. Biometrika,46, 477–480, 1959.
Murthy, M.N.: Product Method of Estimation. Sankhya,26 69–74, 1964.
Srivastava, S.K.: Product estimator, Jour. Ind. Stat. Assoc., Vol.IV, 29–37, 1966.
Shukla, N.D.: Contributions to sampling theory and inferences for incompletely specified models using preliminary tests of significance. Ph. D. dissertation thesis, submitted to University of Luckow, 1974.
Quenouille, M.H.: Notes on Bias in Estimation Biometrika,43, 353–360, 1956.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Shukla, N.D. Almost unbiased product-type estimator. Metrika 23, 127–133 (1976). https://doi.org/10.1007/BF01902857
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF01902857