Date of this Version
Since Stein’s 1956 seminal paper, shrinkage has played a fundamental role in both parametric and nonparametric inference. This article discusses minimaxity and adaptive minimaxity in nonparametric function estimation. Three interrelated problems, function estimation under global integrated squared error, estimation under pointwise squared error, and nonparametric confidence intervals, are considered. Shrinkage is pivotal in the development of both the minimax theory and the adaptation theory.
While the three problems are closely connected and the minimax theories bear some similarities, the adaptation theories are strikingly different. For example, in a sharp contrast to adaptive point estimation, in many common settings there do not exist nonparametric confidence intervals that adapt to the unknown smoothness of the underlying function. A concise account of these theories is given. The connections as well as differences among these problems are discussed and illustrated through examples.
The original published work is available at: https://projecteuclid.org/euclid.ss/1331729981#abstract
Adaptation, adaptive estimation, Bayes minimax, Besov ball, block thresholding, confidence interval, ellipsoid, information pooling, linear functional, linear minimaxity, minimax, nonparametric regression, oracle, separable rules, sequence model, shrinkage, thresholding, wavelet, white noise model
Cai, T. (2012). Minimax and Adaptive Inference in Nonparametric Function Estimation. Statistical Science, 27 (1), 31-50. http://dx.doi.org/10.1214/11-STS355
Date Posted: 27 November 2017