Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Grants Program - Individual

University of Calgary

$17,356.00

Statistical methods on complex survival data

EF 2017-18

Résumé
Modern survival data possess increasingly complex structures. The principal goal of this research proposal is to develop novel statistical methodologies to analyze two important types of complex survival data: (i). ""imperfect"" survival data; (ii). survival data with complex sampling structures. In this proposal, I will concentrate on the following three research topics. In Topic 1, I will develop goodness of fit tests for survival data with covariate measurement error. Standard model checking techniques cannot be directly applied to check the assumptions of the survival model and the measurement error model separately. This is because both models are built using the accurate measurements of the covariates, which are partly unavailable due to contamination by measurement error. I will propose test procedures to check the survival model and the measurement error model simultaneously. In addition, I will propose variable selection procedures for survival analysis with measurement error. In particular, I will propose a penalized least-square approach under the additive hazards model, and a penalized profile likelihood approach under the Cox model. Furthermore, I will extend the two penalized approaches to high-dimensional scenarios where the number of parameters is larger than the size of the sample. In Topic 2, I will propose an efficient weighted method to analyze data collected under a popular complex sampling design, called the case-cohort design, where multivariate failure times are the outcomes of interest. Furthermore, I will handle missing data and covariate measurement error in the case-cohort studies. In Topic 3, I will focus on analyzing survival data with sampling bias in the framework of quantile regression. I will first develop an estimating equation approach for uncensored biased-sampled survival data, and then will extend the method to accommodate censored survival data with sampling bias. Furthermore, covariate measurement error and missing data will be adjusted. This research proposal will make important contributions to statistical analysis of complex survival data. Undergraduate and graduate students will participate in these research topics and gain invaluable statistical training.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
Alberta, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
RGPIN-2016-04595
Name nom
Yan, Ying
Department département
Mathematics and Statistics - Mathematics and Statistics
Organization id
11
Institution établissement
University of Calgary
Province en
Alberta
Province fr
Alberta
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2017
Competition year année de concours
2016
Award amount
17356
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
1508
Committee name en
Mathematics and Statistics
Committee name fr
Mathématiques et statistique
Area of application code
1211
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Medical and health sciences
Area of application fr
Sciences médicales et de la santé
Research subject code
3001
Research subject group en
Statistics and probability
Research subject group fr
Statistique et probabilité
Research subject en
Statistical theory
Research subject fr
Théorie de statistique
Partie
2
Nb partie
5
Application title
Statistical methods on complex survival data
Keyword
NSERC
Application summary
Modern survival data possess increasingly complex structures. The principal goal of this research proposal is to develop novel statistical methodologies to analyze two important types of complex survival data: (i). ""imperfect"" survival data; (ii). survival data with complex sampling structures. In this proposal, I will concentrate on the following three research topics. In Topic 1, I will develop goodness of fit tests for survival data with covariate measurement error. Standard model checking techniques cannot be directly applied to check the assumptions of the survival model and the measurement error model separately. This is because both models are built using the accurate measurements of the covariates, which are partly unavailable due to contamination by measurement error. I will propose test procedures to check the survival model and the measurement error model simultaneously. In addition, I will propose variable selection procedures for survival analysis with measurement error. In particular, I will propose a penalized least-square approach under the additive hazards model, and a penalized profile likelihood approach under the Cox model. Furthermore, I will extend the two penalized approaches to high-dimensional scenarios where the number of parameters is larger than the size of the sample. In Topic 2, I will propose an efficient weighted method to analyze data collected under a popular complex sampling design, called the case-cohort design, where multivariate failure times are the outcomes of interest. Furthermore, I will handle missing data and covariate measurement error in the case-cohort studies. In Topic 3, I will focus on analyzing survival data with sampling bias in the framework of quantile regression. I will first develop an estimating equation approach for uncensored biased-sampled survival data, and then will extend the method to accommodate censored survival data with sampling bias. Furthermore, covariate measurement error and missing data will be adjusted. This research proposal will make important contributions to statistical analysis of complex survival data. Undergraduate and graduate students will participate in these research topics and gain invaluable statistical training.