Comparison of experiments for selection and censored data models
[For the entire collection see Zbl 0758.00011.] The point of departure of this paper is the following result by the first author [Statistical Decision Theory and Related Topics IV, Pap. 4th Purdue Symp.; West Lafayette/Indiana 1986, Vol. 2, 335-349 (1988; Zbl 0681.62012)] concerning experiments involving randomly right-censored data: For two such experiments, one with a stochastically larger censoring time than the other is also more informative (for any decision problem). This paper is devoted to comparison of selection models data, i.e. data which are restricted to a specific subset of the time domain. Strong comparison results as the one cited above are not available in this situation. For the family of distributions with the monotone likelihood ratio property, a necessary and sufficient condition is established for the pairwise-sufficiency of one selection experiment and for the other.
- scientific article; zbMATH DE number 4115722
- scientific article; zbMATH DE number 1057990
- A subset selection procedure for exponential populations under random censoring
- On selection procedures for positive exponential family distributions based on type-I censored data
- scientific article; zbMATH DE number 4147297
This page was built for publication: Comparison of experiments for selection and censored data models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4694163)
