Grant: Discovery Grants Program - Individual
University of Manitoba
$29,000.00
Nonlinear statistical inference and boundary crossing probabilities
EF 2010-11
Résumé
The proposed research is concerned with finding relationships between a response variable and other predictor variables, some of which are either not directly observable or measured with error. Examples include personal exposure to air pollutants, long-term systolic blood pressure, social ability and wealth. It is known that statistical methods ignoring the measurement error result in biased and inconsistent estimates. The goal of the proposed research is to develop novel methods to accurately estimate relationships in the presence of measurement error, which do not rely on restrictive assumptions and are therefore applicable to a wide range of problems. The anticipated results will advance statistical theory and methodology, as well as provide better tools for real data analysis.
Another research area is stochastic modeling and analysis of time when a random process first reaches a threshold. For example, the time when the population of an endangered species falls below a certain critical level, or the time when the number of infected individuals with a disease reaches a limit. The computation of such first passage time distributions is crucial in many scientific fields. The problem is particularly challenging, when the threshold varies with time. I propose to tackle this problem using my previously developed boundary crossing probability approach for Brownian motion process. Compared with other existing methods, this approach has demonstrated theoretical and practical advantages.
Many modern research activities in science and engineering involve numerical optimization and integration. Moreover, complex data structures require highly sophisticated statistical modeling and inference procedures. The problems become very challenging when the dimension of unknown parameters is high. The goal of the research in this area is to develop efficient methods for random sample generation and statistical computation. Graphical methods will be developed to aid data visualization and exploration. Another goal is to develop user-friendly computer software packages to make these methods publicly available.
Programme
Discovery Grants Program - Individual
Bénéficiaire
Emplacement
Manitoba, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
227197-2009
Name nom
Wang, Liqun
Department département
Statistics
Organization id
19
Institution établissement
University of Manitoba
Province en
Manitoba
Province fr
Manitoba
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2010
Competition year année de concours
2009
Award amount
29000
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
14
Committee name en
Statistical Sciences
Committee name fr
Statistique
Area of application code
405
Area of application group en
Environment
Area of application group fr
Environnement
Area of application en
Modelling and mathematical simulation of natural processes
Area of application fr
Modélisation et simulation mathématique des processus naturels
Research subject code
3009
Research subject group en
Statistics and probability
Research subject group fr
Statistique et probabilité
Research subject en
Parametric inference
Research subject fr
Inférence paramétrique
Partie
2
Nb partie
5
Application title
Nonlinear statistical inference and boundary crossing probabilities
Keyword
NSERC
Application summary
The proposed research is concerned with finding relationships between a response variable and other predictor variables, some of which are either not directly observable or measured with error. Examples include personal exposure to air pollutants, long-term systolic blood pressure, social ability and wealth. It is known that statistical methods ignoring the measurement error result in biased and inconsistent estimates. The goal of the proposed research is to develop novel methods to accurately estimate relationships in the presence of measurement error, which do not rely on restrictive assumptions and are therefore applicable to a wide range of problems. The anticipated results will advance statistical theory and methodology, as well as provide better tools for real data analysis.
Another research area is stochastic modeling and analysis of time when a random process first reaches a threshold. For example, the time when the population of an endangered species falls below a certain critical level, or the time when the number of infected individuals with a disease reaches a limit. The computation of such first passage time distributions is crucial in many scientific fields. The problem is particularly challenging, when the threshold varies with time. I propose to tackle this problem using my previously developed boundary crossing probability approach for Brownian motion process. Compared with other existing methods, this approach has demonstrated theoretical and practical advantages.
Many modern research activities in science and engineering involve numerical optimization and integration. Moreover, complex data structures require highly sophisticated statistical modeling and inference procedures. The problems become very challenging when the dimension of unknown parameters is high. The goal of the research in this area is to develop efficient methods for random sample generation and statistical computation. Graphical methods will be developed to aid data visualization and exploration. Another goal is to develop user-friendly computer software packages to make these methods publicly available.