Summary
An estimator of intercepts in two linear regression models based on preliminary test of significance has been found. This estimator is called ‘sometimes pool’ (S. P.) estimator. A detailed study of the s. p. estimator has been done by calculating a number of values of maximum and minimum relative efficiencies for a wide range of parameters.
Similar content being viewed by others
References
Bancroft, T. A. (1944): On biases in the estimation due to the use of preliminary test of significance. Ann. Math. Statist., 15, 190–204.
Bancroft, T. A. (1965): Inferences for incompletely specified models in physical sciencies. Proceedings of the 35th Session of the International Institute, Belgrade, Yugoslavia.
Bennett, B. M. (1952): Estimation of means on the basis of preliminary tests of significance. Ann. Inst. Statist Math., Tokyo, 4, 31–43.
Johnson, J. P. (1967): Pooling regressions and a statiska outlier methodology for lines. Unpublished Ph. D. Thesis, Iowa State University.
Kitagawa, T. (1963): Estimation after preliminary tests of significance. Univ. California, Publication Statist., 3, 147–186.
Saxena, K. P. and Srivastava, S. R. (1970): Inference for a linear hypothesis model using two preliminary tests of significance. Bull. Math. Statist., Japan, 14, 83–102.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Saxena, K.P. A note on relative efficiency of estimators based on preliminary tests in linear regression models. Trabajos de Estadistica y de Investigacion Operativa 28, 109–117 (1977). https://doi.org/10.1007/BF02898053
Issue Date:
DOI: https://doi.org/10.1007/BF02898053