Department of Statistics and Actuarial Science
Simon Fraser University
Phone: (778) 782 4919
Messages: (778) 782 3803
Fax: (778) 782 4368
Office: TLX 10563
Email: dean at stat dot sfu dot ca
Teaching PhilosophyRead more
Co-ordinator: Victoria WanOn Lab Mtgs Lab Notes
Information for New Graduate StudentsGetting settled ESL
Remarks on Climate Change Studies in ForestryRead more
SFU's Climate Change Impacts Research ConsortiumCCIRC
Accommodations for visitorsRead more
On Statistical Collaborative WorkRead more
Brief Comments On Mentorship - A Learning ProcessRead more
Longitudinal and Life-History Analysis
Biostatistical studies are often concerned with the analysis of lifetimes of individuals, and there is a large body of work developed to deal with the various problems which manifest in such analyses. Some clinical trials monitor events which are non-fatal and recurring, for example: skin cancer recurrences, epileptic seizures or migraine headaches, and specialized statistical techniques are required for analyses of such data. This work considers the development of statistical methods for analyses of data arising from longitudinal studies of recurrent events.
Derivation of Methods for Mapping Disease/Mortality Rates
This involves the development of smoothing methods for describing the geographic distribution of mortality/incidence rates. Maps displaying mortality rates are used in epidemiological research to suggest factors which may be linked to various causes of mortality. From a health administrative perspective, they provide an overall description of mortality, which is used by policy makers to allocate health funding. This work focuses on developing new methods which compute reliable rate estimates by pooling information over geographic regions, while at the same time taking into account the spatial aspect of the data, and also isolates time trends which manifest in sequences of maps of mortality rates or disease incidences produced over time.
Long- and Short- term Survival after Coronary Bypass Surgery
Typical analyses of lifetime data treat the time to death or failure as the response variable and use a variety of modeling strategies such as proportional hazards or fully parametric, to investigate the relationship between the response and covariates. In certain circumstances, it may be more natural to view the distribution of the response variable as consisting of two or more parts since the survival curve appears segmented. This work addresses such a scenario. The application is central to the development and is concerned with survival after coronary artery bypass surgery.
Climate Change Impacts on Forest Fires
The potential effect of climate change on forest fire risk is of significant concern, especially in determining whether fire ignition risk is increasing, as measured by annual trends and/or the lengthening of the "fire season" within each year. Public concern has been heightened by high profile wildfire events, such as the many fires that burned across the southern interior of the province of British Columbia in 2003, including the Okanagan Mountain Park forest fire that burned parts of the city of Kelowna, and the fires of 2009. Could such events be attributed to climate change? This project examines historical trends in fire activity and assesses hypotheses concerning climate change.
Forests, Fires, and Stochastic Modelling
John Braun, Dave Martell and I have been focussing on establishing a national network for the development of statistical methods for forest fire management and forest ecology over the last few years. The website http://www.stat.sfu.ca/~dean/forestry/ provides details on the scope of our activities, our partners, and the impact to date of our research.