๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

A k-stage sequential sampling procedure for estimation of normal mean

โœ Scribed by Wei Liu

Publisher
Elsevier Science
Year
1997
Tongue
English
Weight
661 KB
Volume
65
Category
Article
ISSN
0378-3758

No coin nor oath required. For personal study only.

โœฆ Synopsis

We study a k-stage (k>~3) sequential estimation procedure which includes the three-stage procedure of Hall (1981) as a special case. With a suitable value of k, the k-stage procedure not only can be as efficient as the fully sequential procedure of Anscombe, Chow and Robbins in terms of sample size, but also requires at most k sampling operations. For the problem of constructing a fixed width confidence interval for the mean of a normal population with unknown variance, the three-stage procedure of Hall always needs a few more observations than the fully sequential procedure. The five-stage procedure, however, requires almost the same number of observations as the fully sequential procedure.

๐Ÿ“œ SIMILAR VOLUMES

Estimation of a common multivariate norm
Estimation of a common multivariate normal mean vector
โœ K. Krishnamoorthy ๐Ÿ“‚ Article ๐Ÿ“… 1991 ๐Ÿ› Springer Japan ๐ŸŒ English โš– 470 KB

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

Sequential Sampling Estimation for Finit
Sequential Sampling Estimation for Finite Populations of N = nr Objects
โœ B. C. Arnold; R. A. Groeneveld ๐Ÿ“‚ Article ๐Ÿ“… 1990 ๐Ÿ› John Wiley and Sons ๐ŸŒ English โš– 487 KB ๐Ÿ‘ 1 views

Random sampling from a finite population of size N =nr (r known) is considered. The statistic observed is !Z$d,=number of observations required until the kth set of size I from the n wta of r is obtained. An asymptotically unbiased estimator of n is obtained together with ita approximate variance. R