Estimation of a common parameter for pooled samples from the uniform distributions (Q1085541): Difference between revisions

The authors consider the problem of estimating an unknown real-valued parameter c based on m samples of size n from the uniform distributions on the interval \((c-a_ i,c+a_ i)\), \(i=1,2,...m\) with different nuisance parameters. The maximum likelihood estimator (MLE) and other estimators are compared. It is shown that the MLE based on pooled sample is not asymptotically efficient.