IN IEEE TRANS . ON SIGNAL PROCESSING , JULY 1996 1 Exploring Estimator Bias - Variance
نویسنده
چکیده
We introduce a plane, which we call the delta-sigma plane, that is indexed by the norm of the estimator bias gradient and the variance of the estimator. The norm of the bias gradient is related to the maximum variation in the estimator bias function over a neighborhood of parameter space. Using a uniform Cramer-Rao (CR) bound on estimator variance a delta-sigma tradeoo curve is speciied which deenes an \unachievable region" of the delta-sigma plane for a speciied statistical model. In order to place an estimator on this plane for comparison to the delta-sigma tradeoo curve, the estimator variance, bias gradient, and bias gradient norm must be evaluated. We present a simple and accurate method for experimentally determining the bias gradient norm based on applying a bootstrap esti-mator to a sample mean constructed from the gradient of the log-likelihood. We demonstrate the methods developed in this paper for linear Gaussian and non-linear Poisson inverse problems.
منابع مشابه
IN IEEE TRANS . ON SIGNAL PROCESSING , JULY 1996 1 Exploring Estimator Bias - Varian e Tradeo
متن کامل
Exploring estimator bias-variance tradeoffs using the uniform CR bound
We introduce a plane, which we call the delta-sigma plane, that is indexed by the norm of the estimator bias gradient and the variance of the estimator. The norm of the bias gradient is related to the maximum variation in the estimator bias function over a neighborhood of parameter space. Using a uniform Cramer-Rao (CR) bound on estimator variance a delta-sigma tradeo curve is speci ed which de...
متن کاملExploring Estimator Bias-Variance Tradeoffs Using the Uniform CR Bound - Signal Processing, IEEE Transactions on
We introduce a plane, which we call the delta-sigma plane, that is indexed by the norm of the estimator bias gradient and the variance of the estimator. The norm of the bias gradient is related to the maximum variation in the estimator bias function over a neighborhood of parameter space. Using a uniform Cramer-Rao (CR) bound on estimator variance, a delta-sigma tradeoff curve is specified that...
متن کاملPerformance of time-delay estimation in the presence of room reverberation
In this correspondence, synthetic microphone signals generated with the image model technique are used to study the eeects of room reverberation on the performance of the maximum likelihood (ML) estimator of the time delay, in which the estimate is obtained by maximizing the cross-correlation between ltered versions of the microphone signals. The results underscore the adverse eeects of reverbe...
متن کاملUniformly Improving the Cramér-Rao Bound and Maximum-Likelihood Estimation
An important aspect of estimation theory is characterizing the best achievable performance in a given estimation problem, as well as determining estimators that achieve the optimal performance. The traditional Cramér-Rao type bounds provide benchmarks on the variance of any estimator of a deterministic parameter vector under suitable regularity conditions, while requiring a-priori specification...
متن کامل