On the weak convergence of kernel density estimators in Lp spaces |
| |
Authors: | Gilles Stupfler |
| |
Institution: | CERGAM, Aix Marseille Université, EA 4225, 13540 Puyricard, France |
| |
Abstract: | Since its introduction, the pointwise asymptotic properties of the kernel estimator f?n of a probability density function f on ?d, as well as the asymptotic behaviour of its integrated errors, have been studied in great detail. Its weak convergence in functional spaces, however, is a more difficult problem. In this paper, we show that if fn(x)=![/></span>(<i>f?</i><sub><i>n</i></sub>(<i>x</i>)) and (<i>r</i><sub><i>n</i></sub>) is any nonrandom sequence of positive real numbers such that <i>r</i><sub><i>n</i></sub>/√<i>n</i>→0 then if <i>r</i><sub><i>n</i></sub>(<i>f?</i><sub><i>n</i></sub>?<i>f</i><sub><i>n</i></sub>) converges to a Borel measurable weak limit in a weighted <i>L</i><sup><i>p</i></sup> space on ?<sup><i>d</i></sup>, with 1≤<i>p</i><∞, the limit must be 0. We also provide simple conditions for proving or disproving the existence of this Borel measurable weak limit.</td>
</tr>
<tr>
<td align=](/na101/home/literatum/publisher/tandf/journals/content/gnst20/2014/gnst20.v026.i04/10485252.2014.949707/20141110/images/medium/gnst_a_949707_ilg0001.gif) | |
Keywords: | kernel density estimator weak convergence Lp space |
|
|