Higher-Order Asymptotic Properties of Kernel Density Estimator with Global Plug-In and Its Accompanying Pilot Bandwidth
Shunsuke Imai, Yoshihiko Nishiyama

TL;DR
This paper analyzes how the plug-in bandwidth selection affects the asymptotic properties of kernel density estimators, extending previous results and providing precise convergence rates and conditions for the effect of the plug-in method.
Contribution
We generalize existing asymptotic results for kernel density estimators with plug-in bandwidths, derive exact convergence rates, and weaken conditions on pilot kernel order, supported by Monte Carlo experiments.
Findings
Plug-in method has no effect on asymptotic structure up to a certain order when pilot kernel order is high.
Derived the exact convergence rate of the deviation between deterministic and plug-in bandwidth estimators.
Monte Carlo experiments support the theoretical findings and improvements over previous results.
Abstract
This study investigates the effect of bandwidth selection via a plug-in method on the asymptotic structure of the nonparametric kernel density estimator. We generalise the result of Hall and Kang (2001) and find that the plug-in method has no effect on the asymptotic structure of the estimator up to the order of for a bandwidth and any kernel order when the kernel order for pilot estimation is high enough. We also provide the valid Edgeworth expansion up to the order of and find that, as long as the is high enough , the plug-in method has an effect from on the term whose convergence rate is . In other words, we derive the exact achievable convergence rate of the deviation between the distribution functions of the estimator with a…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsStatistical Methods and Inference · Mathematical Approximation and Integration · Markov Chains and Monte Carlo Methods
