Estimation of a common location
- 1 January 1981
- journal article
- research article
- Published by Taylor & Francis in Communications in Statistics - Theory and Methods
- Vol. 10 (10) , 955-961
- https://doi.org/10.1080/03610928108828087
Abstract
Consider two independent random samples, from two distributions characterized by a common unknown location parameter θ and unknown scale parameters possibly different. Assume that the distributions are symmetric about θ. Let be odd location estimators of θ based on the individual samples. For this situation Cohen (1976) suggested a combined estimator which is unbiased and has a variance smaller than that of . To use Cohen's estimator x in practice one needs to know the upper limit of a constant 'a' which appears in his estimator. This paper points out that the upper limit of the constant 'a' given by Cohen (1976) for use in practice needs improvement and provides an improved one which appears to be satisfactory.Keywords
This publication has 4 references indexed in Scilit:
- Estimation of a Common Mean and Recovery of Interblock InformationThe Annals of Statistics, 1980
- Combining Estimates of LocationJournal of the American Statistical Association, 1976
- Point and Confidence Estimation of a Common Mean and Recovery of Interblock InformationThe Annals of Statistics, 1974
- On Conditional Expectations of Location StatisticsJournal of the American Statistical Association, 1960