Bandwidth selection for kernel density estimation with length-biased data

Gonzalez-Manteiga, W, Borrajo, MI & Martinez-Miranda, M. D. (2017). Bandwidth selection for kernel density estimation with length-biased data. Journal of Nonparametric Statistics, 29(3), pp. 636-668. doi: 10.1080/10485252.2017.1339309

Text - Accepted Version
Download (605kB) | Preview


Length-biased data are a particular case of weighted data, which arise in many situations: biomedicine, quality control or epidemiology among others. In this paper we study the theoretical properties of kernel density estimation in the context of length-biased data, proposing two consistent bootstrap methods that we use for bandwidth selection. Apart from the bootstrap bandwidth selectors we suggest a rule-of-thumb. These bandwidth selection proposals are compared with a least-squares cross-validation method. A simulation study is accomplished to understand the behaviour of the procedures in finite samples.

Item Type: Article
Additional Information: This is an Accepted Manuscript of an article published by Taylor & Francis Group in Journal of Nonparametric Statistics on 23/06/2017, available online:
Uncontrolled Keywords: Bootstrap, Rule-of-thumb, Cross-validation, Non-parametric, Weighted data
Subjects: H Social Sciences > HA Statistics
Divisions: Cass Business School > Faculty of Actuarial Science & Insurance

Actions (login required)

View Item View Item


Downloads per month over past year

View more statistics