Optimal Shrinkage Estimation in Heteroscedastic Hierarchical Models
نویسنده
چکیده
Hierarchical models are powerful statistical tools widely used in scientific and engineering applications. The homoscedastic (equal variance) case has been extensively studied, and it is well known that shrinkage estimates, the James-Stein estimate in particular, offer nice theoretical (e.g., risk) properties. The heteroscedastic (the unequal variance) case, on the other hand, has received less attention, even though it frequently appears in real applications. It is not clear of how to construct ”optimal” shrinkage estimate. In this talk, we study this problem. We introduce a class of shrinkage estimates, inspired by Stein’s unbiased risk estimate. We will show that this class is asymptotically optimal in the heteroscedastic case. We apply the estimates to real examples and observe excellent numerical results. This talk is based on joint work with Lawrence Brown and Xianchao Xie.
منابع مشابه
Shrinkage estimates for multi-level heteroscedastic hierarchical normal linear models
Empirical Bayes approach is an attractive method for estimating hyperparameters in hierarchical models. But, under the assumption of normality for a multi-level heteroscedastic hierarchical model, which involves several explanatory variables, the analyst may often wonder whether the shrinkage estimators have efficient asymptotic properties in spite of the fact they involve numerous hyperparamet...
متن کاملSURE Estimates for a Heteroscedastic Hierarchical Model.
Hierarchical models are extensively studied and widely used in statistics and many other scientific areas. They provide an effective tool for combining information from similar resources and achieving partial pooling of inference. Since the seminal work by James and Stein (1961) and Stein (1962), shrinkage estimation has become one major focus for hierarchical models. For the homoscedastic norm...
متن کاملEmpirical estimates for various correlations in longitudinal-dynamic heteroscedastic hierarchical normal models
In this paper, we first define longitudinal-dynamic heteroscedastic hierarchical normal models. These models can be used to fit longitudinal data in which the dependency structure is constructed through a dynamic model rather than observations. We discuss different methods for estimating the hyper-parameters. Then the corresponding estimates for the hyper-parameter that causes the association...
متن کاملExperimental Designs for Estimation of Hyperparameters in Hierarchical Linear Models ?
Optimal design for the joint estimation of the mean and covariance matrix of the random effects in hierarchical linear models is discussed. A criterion is derived under a Bayesian formulation which requires the integration over the prior distribution of the covariance matrix of the random effects. A theoretical optimal design structure is obtained for the situation of independent and homoscedas...
متن کاملHeteroscedastic Treed Bayesian Optimisation
We propose new hierarchical models and estimation techniques to solve the problem of heteroscedasticity in Bayesian optimisation. Our results demonstrate substantial gains in a wide range of applications, including automatic machine learning and mining exploration.
متن کامل