PubMed Health⌕ Search
Home/Archive/PubMed

PubMed · 12182120

Smooth conditional distribution function and quantiles under random censorship.

Eve Leconte·Sandrine Poiraud-Casanova·Christine Thomas-Agnan
View original source ↗Export metadata ↓

Abstract

We consider a nonparametric random design regression model in which the response variable is possibly right censored. The aim of this paper is to estimate the conditional distribution function and the conditional alpha-quantile of the response variable. We restrict attention to the case where the response variable as well as the explanatory variable are unidimensional and continuous. We propose and discuss two classes of estimators which are smooth with respect to the response variable as well as to the covariate. Some simulations demonstrate that the new methods have better mean square error performances than the generalized Kaplan-Meier estimator introduced by Beran (1981) and considered in the literature by Dabrowska (1989, 1992) and Gonzalez-Manteiga and Cadarso-Suarez (1994).

Explore related subjects

Effect Modifier, EpidemiologicFranceHumansModels, StatisticalRandom AllocationRegression AnalysisStatistics, NonparametricSurvival AnalysisJournal Article

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Eve Leconte, Sandrine Poiraud-Casanova, Christine Thomas-Agnan. 2002. Smooth conditional distribution function and quantiles under random censorship.. https://doi.org/10.1023/a%3A1015897720112

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2002

Dose-effect modifying factors in radiation protection--a 1967 National Commission on Radiation Protection document revisited.

In 1967 Subcommittee M-4 of the National Commission on Radiation Protection proposed a system for evaluating, summing and reporting occupational exposures. It appears that some 30 years later these concepts could be implemented in a system of radiation protection based on Katz's cellular track structure model, which is able to quantify and predict the response of systems relevant to radiation protection, such as survival or oncogenic transformations in cell cultures, enzymes, bacteria or whole organisms. As a consequence of this approach, an m-power-law (with m ranging between 2 and 3.5) dependence of effect, or radiation risk, after doses of standard Co-60 radiation, would follow.

Effect Modifier, Epidemiologic↗
PubMed2002

Qualitative research and the problem of judgement: lessons from interviewing fellow professionals.

BACKGROUND: Qualitative research methods are recognized increasingly as valuable tools for primary care research, and add an extra dimension to quantitative work. OBJECTIVE: The aim of this study was to illustrate the benefits and problems attending the dual role of clinician/qualitative researcher. METHODS: As part of two studies employing semi-structured interviews of GPs in a North-West conurbation, about the topics of consultations on chronic low back pain and drug misuse in primary care, respondents' views on their interaction with a GP researcher were explored. RESULTS: Access to the GP by the interviewing GP was easier when the GP researcher was known to the respondent. Such prior knowledge, however, may then influence the content of the data and the manner in which the GP researcher is perceived. During the interview itself, where respondents recognized the researcher as a clinician, interviews were broader in scope and provided richer and more personal accounts of attitudes and behaviour in clinical practice. The GP was also identified as an expert and judge, not just of clinical decision making but also about moral judgements made by GPs in their work. This will impact on the data obtained at interview and must be taken into consideration when the data are interpreted and analysed. CONCLUSION: Qualitative research techniques increasingly are advocated as appropriate for research on and in general practice. The professional identity of the researcher plays an important part in constructing the kind of data obtained in such studies, and this must be made apparent in reporting and discussions of such qualitative work.

Effect Modifier, Epidemiologic↗