A note on marginal likelihood for Gaussian models

نویسنده

  • Peter McCullagh
چکیده

For a vector y ∈ Rn and a model subspace X ⊂ Rn, the residual configuration statistic is what remains of y when translations in the model space and scalar multiplication are ignored. The configuration statistic for a linear Gaussian model has a distribution that depends only on variance-component ratios, or similar ratio parameters in the covariance function of a spatial model. The marginal likelihood based on the configuration statistic is derived analytically. Ordinarily, if the number of nuisance parameters is not too large, the profile likelihood is approximately equal to the marginal likelihood when both are well defined. But it is extremely unusual for these to be identical. The residual configuration statistic is one such example, in which the marginal likelihood coincides with Diggle’s (1988) hybrid profile REML likelihood.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Parameter Estimation in Spatial Generalized Linear Mixed Models with Skew Gaussian Random Effects using Laplace Approximation

 Spatial generalized linear mixed models are used commonly for modelling non-Gaussian discrete spatial responses. We present an algorithm for parameter estimation of the models using Laplace approximation of likelihood function. In these models, the spatial correlation structure of data is carried out by random effects or latent variables. In most spatial analysis, it is assumed that rando...

متن کامل

A comparison of algorithms for maximum likelihood estimation of Spatial GLM models

In spatial generalized linear mixed models, spatial correlation is assumed by adding normal latent variables to the model. In these models because of the non-Gaussian spatial response and the presence of latent variables the likelihood function cannot usually be given in a closed form, thus the maximum likelihood approach is very challenging. The main purpose of this paper is to introduce two n...

متن کامل

Conditional Dependence in Longitudinal Data Analysis

Mixed models are widely used to analyze longitudinal data. In their conventional formulation as linear mixed models (LMMs) and generalized LMMs (GLMMs), a commonly indispensable assumption in settings involving longitudinal non-Gaussian data is that the longitudinal observations from subjects are conditionally independent, given subject-specific random effects. Although conventional Gaussian...

متن کامل

Optimization of Gaussian Process Models with Evolutionary Algorithms

Gaussian process (GP) models are non-parametric, blackbox models that represent a new method for system identification. The optimization of GP models, due to their probabilistic nature, is based on maximization of the probability of the model. This probability can be calculated by the marginal likelihood. Commonly used approaches for maximizing the marginal likelihood of GP models are the deter...

متن کامل

A New Algorithm for Maximum Likelihood Estimation in Gaussian Graphical Models for Marginal Independence

Graphical models with bi-directed edges (↔) represent marginal independence: the absence of an edge between two vertices indicates that the corresponding variables are marginally independent. In this paper, we consider maximum likelihood estimation in the case of continuous variables with a Gaussian joint distribution, sometimes termed a covariance graph model. We present a new fitting algorith...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2003