Mathematics – Statistics Theory
Scientific paper
2004-06-22
Annals of Statistics 2004, Vol. 32, No. 2, 500-527
Mathematics
Statistics Theory
Scientific paper
10.1214/009053604000000076
We describe here a framework for a certain class of multiscale likelihood factorizations wherein, in analogy to a wavelet decomposition of an L^2 function, a given likelihood function has an alternative representation as a product of conditional densities reflecting information in both the data and the parameter vector localized in position and scale. The framework is developed as a set of sufficient conditions for the existence of such factorizations, formulated in analogy to those underlying a standard multiresolution analysis for wavelets, and hence can be viewed as a multiresolution analysis for likelihoods. We then consider the use of these factorizations in the task of nonparametric, complexity penalized likelihood estimation. We study the risk properties of certain thresholding and partitioning estimators, and demonstrate their adaptivity and near-optimality, in a minimax sense over a broad range of function spaces, based on squared Hellinger distance as a loss function. In particular, our results provide an illustration of how properties of classical wavelet-based estimators can be obtained in a single, unified framework that includes models for continuous, count and categorical data types.
Kolaczyk Eric D.
Nowak Robert D.
No associations
LandOfFree
Multiscale likelihood analysis and complexity penalized estimation does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Multiscale likelihood analysis and complexity penalized estimation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Multiscale likelihood analysis and complexity penalized estimation will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-669844