Marginal information for expectation parameters
نویسندگان
چکیده
The authors consider a special case of inference in the presence of nuisance parameters. They show that when the orthogonalized score function is a function of a statistic S, no Fisher information for the interest parameter is lost by using the marginal distribution of S rather than the full distribution of the observations. Therefore, no information for the interest parameter is recovered by conditioning on an ancillary statistic, and information will be lost by conditioning on an approximate ancillary statistic. This is the case for regular multivariate exponential families when the interest parameter is a subvector of the expectation parameter and the statistic is the maximum likelihood estimate of the interest parameter. Several examples are considered, including the 2× 2 table.
منابع مشابه
On robust input design for nonlinear dynamical models
We present a method for robust input design for nonlinear state-space models. The method optimizes a scalar cost function of the Fisher information matrix over a set of marginal distributions of stationary processes. By using elements from graph theory we characterize such a set. Since the true system is unknown, the resulting optimization problem takes the uncertainty on the true value of the ...
متن کاملA marginal mixture model for discovering motifs in sequences
In this study we present a marginal mixture model for discovering probabilistic motifs in categorical sequences. The proposed method is based on a general framework for developing, extending and marginalizing expressive motif models that encapsulates spatial information. Two alternative schemes for constructing expressive models are described, the extend and the marginal approach. The EM algori...
متن کاملGradient Flow of the Stochastic Relaxation on a Generic Exponential Family
We study the natural gradient flow of the expected value Ep [ f ] of an objective function f for p in an exponential family. We parameterize the exponential family with the expectation parameters and we show that the dynamical system associated to the natural gradient flow can be extended outside the marginal polytope.
متن کاملEmpirical Bayesian Change Point Detection
This paper explores a Bayesian method for the detection of sudden changes in the generative parameters of a data series. The problem is phrased as a hidden Markov model, where change point locations correspond to unobserved states, which grow in number with the number of observations. Our interest lies in the marginal change point posterior density. Rather than optimize a likelihood function of...
متن کاملGeneralized Expectation Criteria for Semi-Supervised Learning with Weakly Labeled Data
In this paper, we present an overview of generalized expectation criteria (GE), a simple, robust, scalable method for semi-supervised training using weakly-labeled data. GE fits model parameters by favoring models that match certain expectation constraints, such as marginal label distributions, on the unlabeled data. This paper shows how to apply generalized expectation criteria to two classes ...
متن کامل