scientific article; zbMATH DE number 3879899
In this paper, two concepts, restricted range and spacings, are discussed in relation to the exponential distribution. A sample of size n is drawn from a population, where this sample is censored both above and below by s and r, respectively. Then the restricted range R is defined as the difference between the largest and the smallest available observations in this censored sample. That is \(R=x_{(n-s)}-x_{(r+1)}=u_{n-s}- u_{r+1}\), where \(x_{(i)}\) denotes the i-th order statistics in this sample of size n. Next consider the spacings \(v_ i=u_ i-u_{i- 1}=x_{(i)}-x_{(i-1)}.\) In this paper, these ideas of R and \(v_ i\) are dealt with in relation to k independent exponential populations. First, a linear combination of spacings (LCOS) is considered for a population and then the distribution of the sum of k LCOS from k populations is obtained. The variance of this sum is minimized subject to certain conditions, and some related problems are discussed.
This page was built for publication:
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3345575)