A two-sample estimate of a common mean
โ Scribed by Khursheed Alam
- Publisher
- Springer Japan
- Year
- 1967
- Tongue
- English
- Weight
- 344 KB
- Volume
- 19
- Category
- Article
- ISSN
- 0020-3157
No coin nor oath required. For personal study only.
๐ SIMILAR VOLUMES
We consider the problem of estimating a \(p\)-dimensional vector \(\mu_{1}\) based on independent variables \(X_{1}, X_{2}\), and \(U\), where \(X_{1}\) is \(N_{p}\left(\mu_{1}, \sigma^{2} \Sigma_{1}\right), X_{2}\) is \(N_{p}\left(\mu_{2}, \sigma^{2} \Sigma_{2}\right)\), and \(U\) is \(\sigma^{2} \
Let X1,..., XN be independent observations from Np(#, ~1) and Y1,..., YN be independent observations from Np(#, ~2). Assume that Xi's and Y~'s are independent. An unbiased estimator of/z which dominates the sample mean X for p \_> 1 under the loss function L(/z,/2) --(f~ -#)'~i-l(fL -/~) is suggeste