SmoothnessPenalized Deconvolution (SPeD) of a Density Estimate
Abstract
This paper addresses the deconvolution problem of estimating a squareintegrable probability density from observations contaminated with additive measurement errors having a known density. The estimator begins with a density estimate of the contaminated observations and minimizes a reconstruction error penalized by an integrated squared $m$th derivative. Theory for deconvolution has mainly focused on kernel or waveletbased techniques, but other methods including splinebased techniques and this smoothnesspenalized estimator have been found to outperform kernel methods in simulation studies. This paper fills in some of these gaps by establishing asymptotic guarantees for the smoothnesspenalized approach. Consistency is established in mean integrated squared error, and rates of convergence are derived for Gaussian, Cauchy, and Laplace error densities, attaining some lower bounds already in the literature. The assumptions are weak for most results; the estimator can be used with a broader class of error densities than the deconvoluting kernel. Our application example estimates the density of the mean cytotoxicity of certain bacterial isolates under random sampling; this mean cytotoxicity can only be measured experimentally with additive error, leading to the deconvolution problem. We also describe a method for approximating the solution by a cubic spline, which reduces to a quadratic program.
 Publication:

arXiv eprints
 Pub Date:
 May 2022
 DOI:
 10.48550/arXiv.2205.09800
 arXiv:
 arXiv:2205.09800
 Bibcode:
 2022arXiv220509800K
 Keywords:

 Mathematics  Statistics Theory
 EPrint:
 Revisions: added new theorem in Section 6