Une approche intrinsèque de l'estimation non paramétrique de la densité
✍ Scribed by Gérard Derzko
- Publisher
- Elsevier Science
- Year
- 1998
- Tongue
- English
- Weight
- 281 KB
- Volume
- 327
- Category
- Article
- ISSN
- 0764-4442
No coin nor oath required. For personal study only.
✦ Synopsis
Nous considerons un Cchantillon X1 ? . . . . X,, connu par les indicatrices des evenements {X, E ((M -1 + r)h,(M + r)h]}, 1 5 i 5 n, 1 < r 2 N. Now estimons la densite f des observations par des moyennes d'histogrammes bases sur des intervalles d'extremites dam {kh : k E N}. Nous montrons que ces estimateurs possedent des propriCk% de convergence et de simplicite a m&me de justifier leur utilisation en analyse statistique. 0 Academic des Sciences/Elsevier, Paris An intrinsic approach to nonparametric density estimation We consider samples Xl, . . . . X,, partially observed through the indicators of the events {X, E ((M -1 + r)h, (A4 + r)h]}, 1 5 % 5 76.1 < r 5 N. We estimate the underlying density f by averaging a class of histograms based upon intervals with endpoints in {kh : k E N}. We show that the resulting estimators are easy to use and have limiting properties which are bound to justify their use in statistical analysis. 0 Academic des Sciences/Elsevier. Paris
📜 SIMILAR VOLUMES
## Abstract By studying the molecular weights of various solutions of __cis__‐1,4‐polyisoprene the authors arrived at the formula \documentclass{article}\pagestyle{empty}\begin{document}$$\left[ \eta \right] = \sqrt {2/c} \sqrt {\eta \_{sp} - {\rm l}n\eta } \_{rel} $$\end{document} which allowed th