A Smirnov-Bickel-Rosenblatt theorem for compactly-supported wavelets
This provides a theoretical foundation for inference using wavelet estimators in nonparametric statistics, extending classical results from histograms and kernels to wavelets.
The paper proves a Smirnov-Bickel-Rosenblatt theorem for wavelet estimators with compact support, showing that the supremum norm of the variance term converges to a Gumbel distribution. The result is verified for Daubechies wavelets and symlets with 6 to 20 vanishing moments.
In nonparametric statistical problems, we wish to find an estimator of an unknown function f. We can split its error into bias and variance terms; Smirnov, Bickel and Rosenblatt have shown that, for a histogram or kernel estimate, the supremum norm of the variance term is asymptotically distributed as a Gumbel random variable. In the following, we prove a version of this result for estimators using compactly-supported wavelets, a popular tool in nonparametric statistics. Our result relies on an assumption on the nature of the wavelet, which must be verified by provably-good numerical approximations. We verify our assumption for Daubechies wavelets and symlets, with N = 6, ..., 20 vanishing moments; larger values of N, and other wavelet bases, are easily checked, and we conjecture that our assumption holds also in those cases.