Some Results on Subset Selection Procedures for Double Exponential Populations.
Abstract
A subset selection procedure based on the sample medians for selecting the largest of the location parameters of k double exponential (Laplace) distributions is studied. These unknown location parameters also represent the medians or means of the double exponential populations. An indifference zone approach to the problem of selecting the populations with the t-largest unshown location parameters is discussed. For this distribution the problem of selection for the largest scale parameter is also investigated. A test of homogeneity is proposed which is based on the range of sample medians. Closed forms of the distribution of the statistic associated with the subset selection procedure for location parameters are obtained for some special cases. Tables of the upper percentage points of this statistic are computed. An example is given to illustrate the use of the selection procedure and the test of homogeneity for the location parameters. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Oct 01, 1976
- Accession Number
- ADA033391
Entities
People
- Shanti Gupta
- Yoon-kwai Leong
Organizations
- Purdue University