Titlebook: Quasi-Likelihood And Its Application; A General Approach t Christopher C. Heyde Book 1997 Springer Science+Business Media New York 1997 Est

Proponent

Bypassing the Likelihood,ver, allow such estimators (or estimating functions) to be obtained quite painlessly and under more general conditions. In this chapter we shall illustrate the power and simplicity of the approach through three quite different examples.

Foam-Cells

Asymptotic Quasi-Likelihood,mator, which enjoy the same kind of properties as ordinary quasi-likelihood estimators, such as having asymptotic confidence zones of minimum size, within a specified family, for the “parameter” in question.

污穢

大門在匯總

Consistency and Asymptotic Normality for Estimating Functions,the delicacy of the results as exercises in mathematics as distinct from the reality of practically relevant examples. Also, we have made it clear already that it is generally preferable to check directly, in any particular example, for consistency and asymptotic normality, rather than trying to check the conditions of a special purpose theorem.

遭遇

Asymptotic Confidence Zones of Minimum Size,nfidence zones that generalize classical results holding for maximum likelihood. However, some comments about maximum likelihood itself are appropriate as a prelude since, although it is one of the most widely used statistical techniques, it does suffer from various problems.

NEG

Infinite Dimensional Problems,rval 0 ≤ . ≤ . are important and the function needs to be estimated. Both the situation where . replica trajectories of {., 0 ≤ . ≤ . are observed and . → ∞ or one trajectory is observed and . → ∞ are of interest but most of the established results deal with the former case.

壓碎

Complements and Strategies for Application, estimating functions. It must be remembered that the general theory requires estimating functions which are at least square integrable and if the underlying variables of interest do not have finite second moments then transformations are required. A number of useful approaches are indicated below.

Discrete

Pessary

POWER

Book 1997s theory. The focus is on choice of families of estimating functions, rather than the estimators derived therefrom, and on optimization within these families. Only assumptions about means and covariances are required for an initial d- cussion. Nevertheless, the theory that is developed mimics that o