摘要:

Different sorts of bilinear models (models with bilinear interaction terms) are currently used when analyzing contingency tables: association models, correlation models... All these can be included in a general family of bilinear models: power models. In this framework, Maximum Likelihood (ML) estimation is not always possible, as explained in an introductory example. Thus, Generalized Least Squares (GLS) estimation is sometimes needed in order to estimate parameters. A subclass of power models is then considered in this paper: separable reduced-rank (SRR) models. They allow an optimal choice of weights for GLS estimation and simplifications in asymptotic studies concerning GLS estimators. Power 2 models belong to the subclass of SRR models and the asymptotic properties of GLS estimators are established. Similar results are also established for association models which are not SRR models. However, these results are more difficult to prove. Finally, 2 examples are considered to illustrate our results.

ISSN:0233-1888    

DOI:10.1080/02331880008802719

出版商:Gordon & Breach Science Publishers    

年代:2000

数据来源: Taylor

摘要:

In this paper we establish almost sure consistency of the jackknife estimate of variance and covariance for Koziol–Green integrals. These are asymptotically Gaussian estimates of the form, where we putfor the MLE of the distribution function under the Koziol-Green proportional censorship model. Confidence sets for functions of general integralsmay be constructed from our results.

ISSN:0233-1888    

DOI:10.1080/02331880008802720

出版商:Gordon & Breach Science Publishers    

年代:2000

数据来源: Taylor

摘要:

A median-unbiased estimator of the characteristic exponent of a symmetric stable distribution is constructed.

ISSN:0233-1888    

DOI:10.1080/02331880008802721

出版商:Gordon & Breach Science Publishers    

年代:2000

数据来源: Taylor

ISSN:0233-1888    

DOI:10.1080/02331880008802718

出版商:Gordon & Breach Science Publishers    

年代:2000

数据来源: Taylor