Pivotal ouantities based on the conditional distribution function transform in models with accessory parameters |
| |
Authors: | C.J Lloyd |
| |
Affiliation: | Department of Statistics , Malbourne University , |
| |
Abstract: | A general formula for porducing pivotal quantities defined free of accessory paramelers is investigated. In addition to similarity, resulting tests often have exact or asymptotic optimal properties In other cases, the sample correlation with statistics sufficient for the accescory parameters produce a simple similar test and a consistent, asymptctically normal estimator. The latter mathod should perform best when the accessories are highly dispersed. |
| |
Keywords: | tests of independence partial ancillary similar test endomorphic model exomorphic model |
|
|