Grant: Discovery Grants Program - Individual
University of Toronto
$29,000.00
Statistical inference of non-stationary time series
FY 2013-14
Summary
The proposed research program is aimed at establishing a unified statistical theory for the estimation, inference and prediction of non-stationary time series whose characteristics change slowly in time. We shall model non-stationary time series from a nonlinear systems point of view, and utilize modern Martingale theory, Gaussian approximation theory and empirical process theory for dependent data to investigate various asymptotic behaviors of non-stationary time series.The proposed research will mainly focus on locally stationary time series; the physical mechanism generating such time series changes smoothly in time. This type of data structure appears frequently in areas such as environmental sciences, bioengineering, economics, and telecommunications, where data with slowly changing properties are collected over time. On the other hand, however, the scientific questions involving such time series generally cannot be solved by traditional stationary time series approaches. At the current stage, the area of locally stationary time series analysis is in its infancy and much innovative statistical methodology and theory is to be developed. We believe that our unified framework will provide an important theoretical and methodological basis for non-stationary time series analysis in many scientific disciplines; such as assessing patterns of climate change and predicting financial risks, among others.
Program
Discovery Grants Program - Individual
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
387336-2010
Name nom
Zhou, Zhou
Department département
Statistics (St. George Campus)
Organization id
31
Institution établissement
University of Toronto
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2013
Competition year année de concours
2010
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
1508
Committee name en
Mathematics and Statistics
Committee name fr
Mathématiques et statistique
Area of application code
1205
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Mathematical sciences
Area of application fr
Sciences mathématiques
Research subject code
3002
Research subject group en
Statistics and probability
Research subject group fr
Statistique et probabilité
Research subject en
Time series analysis
Research subject fr
Analyse des séries chronologiques
Partie
4
Nb partie
5
Application title
Statistical inference of non-stationary time series
Keyword
NSERC
Application summary
The proposed research program is aimed at establishing a unified statistical theory for the estimation, inference and prediction of non-stationary time series whose characteristics change slowly in time. We shall model non-stationary time series from a nonlinear systems point of view, and utilize modern Martingale theory, Gaussian approximation theory and empirical process theory for dependent data to investigate various asymptotic behaviors of non-stationary time series.The proposed research will mainly focus on locally stationary time series; the physical mechanism generating such time series changes smoothly in time. This type of data structure appears frequently in areas such as environmental sciences, bioengineering, economics, and telecommunications, where data with slowly changing properties are collected over time. On the other hand, however, the scientific questions involving such time series generally cannot be solved by traditional stationary time series approaches. At the current stage, the area of locally stationary time series analysis is in its infancy and much innovative statistical methodology and theory is to be developed. We believe that our unified framework will provide an important theoretical and methodological basis for non-stationary time series analysis in many scientific disciplines; such as assessing patterns of climate change and predicting financial risks, among others.