Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Discovery Grants Program - Individual

University of Manitoba

$27,000.00

Stochastic Modeling and Semiparametric Inference for Complex Data

FY 2024-25

Summary
The proposed research program aims to develop novel theories and methods for statistical analysis of complex data. The research will focus in two areas of statistics and applied probability. The first area is the regularized estimation and variable selection in high-dimensional regression models. Massive and high-dimensional data are common in many scientific fields, such as medical and health, astronomy and physics, computer science and engineering, economics and finance. A challenging task in high-dimensional data analysis is to select a few most relevant predictors among a large number of candidate variables to accurately predict an outcome of interest. The variable selection problem has drawn much attention in statistics. Most research assume that all predictor variables are measured precisely. However, real data applications always involve variables that are not directly observable or cannot be measured precisely. Therefore, it is important to study the problem in measurement error models. A novel approach employing the instrumental variables will be developed for generalized linear and other nonlinear models. In addition, the regularized second-order least squares approach will be used to simultaneously estimate the mean and variance parameters. The second area is stochastic modeling approach to reliability and lifetime data analysis, which plays an important role in many disciplines such as medical and health science, physical sciences and engineering, business and economics. It is well recognized in the literature that the traditional parametric and semiparateric models have limitations in real applications. An alternative approach is based on the first passage time of a certain underlying stochastic process (such as disease progress of a patient or degradation of a mechanical system). The first passage time has applications in many other disciplines including biology, physics, epidemiology, finance and risk management. Although this approach has many appealing and desirable properties, it has been under investigated in statistics. So far most existing methods and applications are limited to a few special instances where closed form distributions are available. The proposed research aims to develop novel methods and algorithms to calculate the first passage time distributions for diffusion processes and flexible boundaries, which allow us to model the underlying processes and obtain the corresponding lifetime distribution. The proposed research will provide opportunities for the training of highly qualified personnel at all levels. They will be trained to be the experts in the areas that are currently very active and in the research fronts in statistics. Moreover, they will learn modern statistical theories and methodologies, and computational skills to deal with large scale and high-dimensional data. They will also learn to apply these methodologies and skills to solve real life problems.
Program
Discovery Grants Program - Individual
Location
Manitoba, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
RGPIN-2023-04924
Name nom
Wang, Liqun
Department département
Department of 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
2024
Competition year année de concours
2023
Award amount
27000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR 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
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
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Stochastic Modeling and Semiparametric Inference for Complex Data
Keywords
measurement error models; instrumental variables method; high-dimensional regression models; variable selection; regularized regression; frist passage time; brownian motion and diffusion processes; boundary crossing probablity; lifetime data analysis; survival distribution
Application summary
The proposed research program aims to develop novel theories and methods for statistical analysis of complex data. The research will focus in two areas of statistics and applied probability. The first area is the regularized estimation and variable selection in high-dimensional regression models. Massive and high-dimensional data are common in many scientific fields, such as medical and health, astronomy and physics, computer science and engineering, economics and finance. A challenging task in high-dimensional data analysis is to select a few most relevant predictors among a large number of candidate variables to accurately predict an outcome of interest. The variable selection problem has drawn much attention in statistics. Most research assume that all predictor variables are measured precisely. However, real data applications always involve variables that are not directly observable or cannot be measured precisely. Therefore, it is important to study the problem in measurement error models. A novel approach employing the instrumental variables will be developed for generalized linear and other nonlinear models. In addition, the regularized second-order least squares approach will be used to simultaneously estimate the mean and variance parameters. The second area is stochastic modeling approach to reliability and lifetime data analysis, which plays an important role in many disciplines such as medical and health science, physical sciences and engineering, business and economics. It is well recognized in the literature that the traditional parametric and semiparateric models have limitations in real applications. An alternative approach is based on the first passage time of a certain underlying stochastic process (such as disease progress of a patient or degradation of a mechanical system). The first passage time has applications in many other disciplines including biology, physics, epidemiology, finance and risk management. Although this approach has many appealing and desirable properties, it has been under investigated in statistics. So far most existing methods and applications are limited to a few special instances where closed form distributions are available. The proposed research aims to develop novel methods and algorithms to calculate the first passage time distributions for diffusion processes and flexible boundaries, which allow us to model the underlying processes and obtain the corresponding lifetime distribution. The proposed research will provide opportunities for the training of highly qualified personnel at all levels. They will be trained to be the experts in the areas that are currently very active and in the research fronts in statistics. Moreover, they will learn modern statistical theories and methodologies, and computational skills to deal with large scale and high-dimensional data. They will also learn to apply these methodologies and skills to solve real life problems.