Fall 2016 SFU/UBC Joint Statistical Seminar
Saturday October 22nd, 2016
Room 7000 in the Harbour Centre
 Presented by PIMS and the Simon Fraser Graduate Student Society
PIMS logo                       GSS logo

Overview
The SFU-UBC Joint Graduate Student Workshop in Statistics is going into its 12nd year. This is the first of two seminars to take place this school year; the one in Fall is organized by graduate students from SFU and the one in Spring is organized by graduate students from UBC. The idea of this event is to offer graduate students in Statistics and Actuarial Science with an opportunity to attend a seminar with accessible talks providing them an introduction to active areas of research in the field. For two students from each university the seminar allows them to present on their work, as well as to offer them an opportunity to develop their presentation skills with their peers.

A new format this year consists of talks given by four students (two from UBC and two from SFU) and one professor (from SFU in the Fall and UBC in the spring). This change is being done to expand the networking aspect of the event, in order to allow students more time to meet their peers from the other institution. There will be time dedicated to an ice breaker event and a social trivia game with prizes at the end of the event. The seminar also contains the traditional important social components, namely the morning coffee and the lunch where students get more opportunity to network with each other and foster a mutually beneficial relationship between the departments.

Information on previous seminars can be found on the UBC statistics department website (here).

Sponsorship
This seminar could not take place without the generous help of our sponsors: The Pacific Institute for the Mathematical Sciences (PIMS) and the Department of Statisctis and Actuarial Science at Simon Fraser University (StatSFU).

Agenda For Saturday October 24th
8:30 - 9:00
 Coffee and Pastries at Blenz's Coffee (508 West Hastings Street)
Across the street from the Harbour Centre
9:00 - 9:20
 Networking Event: Icebreaker
9:20 - 9:50
 Student Talk: Nate Sandholtz
Bayesian Factor Analysis with Spatio-Temporal Dependence Abstract
9:50 - 10:20
 Student Talk: Sonja Surjanovic
Using Computer Model Uncertainty to Inform the Design of Physical Experiments: An Application in Glaciology Abstract
10:30 - 11:00 Student Talk: Trevor Thomson
A Family of Distributions in Stochastic Processes with Applications to Spot Fires Abstract
11:00 - 11:50
 Faculty Talk: Tim Swartz
Swartz on Sports Abstract
11:50 - 12:00
 Networking Event: Break and photo time
12:00 - 12:30
 Student Talk: Guangyu Zhu
Sparse Envelop Model: Efficient Estimation and Response Variable Selection in Multivariate Linear Regression Abstract
12:30 pm - 12:40 pm
 Networking Event: Walk

12:40 pm - 2:00 pm
 Lunch at Steamworks (375 Water St).




Directions and Accessibility
The seminar conveniently takes place in room 7000 on the SFU downtown campus in the Harbour Centre in downtown Vancouver (map). From SFU, the 135 bus will take you directly to the seminar location. From UBC, the 044 and 14 bus provide direct access. It is also near Waterfront station, which allows access from all Skytrain lines: Canada Line, Expo Line and Millenium Line.

Link to last year's Fall Joint Seminar Agenda here


X

Response variable selection arises naturally in many applications, but has not been studied as thoroughly as predictor variable selection. In this talk, I will firstly introduce the envelope model which allows efficient estimation in multivariate linear regression. Then I will introduce the sparse envelope model we proposed to perform variable selection on the responses and preserve the efficiency gains offered by the envelope model. We established consistency and the oracle property and obtain the asymptotic distribution of the sparse envelope estimator.

X

For many regions throughout the world, wildland fires are regular year-round occurrences that can potentially devour communities. As a result, numerous wildland fire management teams are employed to try and control these fires before they pose a heavy risk to human life and property. A spot fire is a term used to describe a newly-ignited fire caused by airborne embers, that is separated from the main fire front. These spot fires are extremely dangerous, can spread rapidly, and prevents fire fronts from being manageable. In this talk, we will examine the methodology in modelling the occurrence of a spot fire, which includes simulating a fire growth model based on Huygens' Principle. The result is a family of distributions to be utilized in modelling the time of a successful spot fire.

X

Computer models are used as surrogates for physical experiments in many areas of science. They can allow the researchers to gain a better understanding of the processes of interest, in situations where it would be overly costly or time-consuming to obtain sufficient physical data. In this project, we give an approach for using a computer model to obtain designs for a physical experiment. The designs are optimal for modelling the spatial distribution of the response across the region of interest. An additional consideration is the presence of several tuning parameters to the computer model, which represent physical aspects of the process but whose values are not precisely known. In obtaining the optimal designs, we account for this uncertainty in the parameters governing the system. The project is motivated by an application in glaciology, where computer models are often used to model the melt of snow and ice across a glacier surface. The methodology is applied to obtain optimal networks of stakes, which researchers use to obtain measurements of summer mass balance (the difference between the amount of snow/ice before and after the melt season).

X

Rising sea levels pose potentially serious consequences for coastal populations around the world. This highlights the importance of understanding how sea levels vary over time and space. We examine a set of residuals after de-trending the seasonal and annual variation in a three decade time series of sea level measures at 33 locations along the Atlantic Coast of the United States. We fit a spatio-temporal confirmatory factor analysis (CFA) model in a Bayesian framework, which offers a more favorable structure to implement spatio-temporal dependence than a maximum likelihood setting. We model temporal dependence through the latent factors while modeling the spatial dependence in the factor loadings. This dependence scheme enables us to make smooth predictions at unobserved locations along the entire East Coast of the United States with corresponding estimates of uncertainty. We compare the spatio-temporal model to the independent CFA model using a set of five locations that we will exclude when fitting the model, and through a small simulation study.

X

This talk surveys some problems that I have worked on in sports analytics. Although there is a technical aspect to the work, the presentation will be non-technical and can be understood by those in middle school. Some of the sports that I may touch upon include bowling, basketball, hockey, cricket, highland dance, golf, soccer and baseball. I think that two messages that I want to get across are these: (1) there are some interesting datasets in sports analytics and (2) there are some interesting problems in sports analytics..