Welcome to the Department of Statistics and Actuarial Science

The Department of Statistics and Actuarial Science is among the top academic units for statistical and actuarial science in the world and is home to more than 40 research active full-time faculty working in diverse and exciting areas. The Department is also home to over 900 undergraduate students and about 150 graduate students in programs including Actuarial Science, Biostatistics, Quantitative Finance, Statistics, and Statistics-Computing.

We are located on University of Waterloo main campus, which is located at the heart of Canada's Technology Triangle about 100 kilometers west of Toronto.

  1. Sep. 28, 2017David Sprott Distinguished Lecture by Susan A. MurphyDavid Sprott Distinguished lecture poster

  2. Aug. 10, 2017Pengfei Li is a 2017 recipient of the Faculty of Mathematics Award for Distinction in Teaching Pengfei Li

    The selection committee announced that Pengfei Li of the Department of Statistics and Actuarial Science is one of the two 2017 recipiants of the Faculty of Mathematics Award for Distinction.  Pengfei shares this honor with David Jao from the Department of Combinatorics and Optimization.

  3. July 12, 2017Samuel Eckler Medal in Actuarial ScienceAward winner Kieran Hendrickson-Gracie

    This prize was established to recognize the contribution of Samuel Eckler to the actuarial profession and is provided by Eckler Partners. The medal, which is cast in gold, is awarded each year to the outstanding graduating student of the Honours Actuarial Science Program.

    This year’s recipient is Kieran Hendrickson-Gracie who not only graduated as the top Actuarial Science major, but also has completed the five preliminary Society of Actuaries (SOA) exams, and earned three Cherry awards, in STAT 443, STAT 430, and STAT 431.

    Kieran's brother Aaron Hendrickson-Gracie, was awarded the Samuel Eckler Medal in 2013.

Read all news
  1. Jan. 10, 2018Department seminar by Peijun Sang, Simon Fraser University

    Sparse Estimation for Functional Semiparametric Additive Models

    In the context of functional data analysis, functional linear regression serves as a fundamental tool to handle the relationship between a scalar response and a functional covariate. With the aid of  Karhunen–Loève expansion of a stochastic process, a functional linear model can be written as an infinite linear combination of functional principal component scores. A reduced form is fitted in practice for dimension reduction; it is essentially converted to a multiple linear regression model.

    Though the functional linear model is easy to implement and interpret in applications, it may suffer from an inadequate fit due to this specific linear representation. Additionally, effects of scalar predictors which may be predictive of the scalar response are neglected in the functional linear model.

    Prediction accuracy can be enhanced greatly by incorporating effects of these scalar predictors.

    In this talk, we propose a functional semiparametric additive model, which models the effect of a functional covariate nonparametrically and models several scalar covariates in a linear form. We develop the method for estimating the functional semiparametric additive model by smoothing and selecting non-vanishing components for the functional covariate. We show that the estimation method can consistently estimate both nonparametric and parametric parts in the model. Numerical studies will be presented to demonstrate the advantage of the proposed model in prediction.

  2. Jan. 22, 2018Department seminar by Xing Wang, Georgia State University

    Nonparametric Inference for Sensitivity of Haezendonck-Goovaerts Risk Measure

    Recently Haezendonck-Goovaerts (H-G) risk measure has been popular in actuarial science. When it is applied to an insurance or a financial portfolio with several loss variables, sensitivity analysis becomes useful in managing the portfolio, and the assumption of independent observations may not be reasonable. This paper first derives an expression for computing the sensitivity of the H-G risk measure, which enables us to estimate the sensitivity nonparametrically via the H-G risk measure. Further, we derive the asymptotic distributions of the nonparametric estimators for the H-G risk measure and the sensitivity by assuming that loss variables in the portfolio follow from a strictly stationary ↵-mixing sequence. A simulation study is provided to examine the finite sample performance of the proposed nonparametric estimators. Finally, the method is applied to a real data set. Key words and phrases: Asymptotic distribution, Haezendonck-Goovaerts risk measure, Mixing sequence, Nonparametric estimate, Sensitivity analysis

  3. Jan. 24, 2018Department seminar by Krishnakumar Balasubramanian, Princeton University

    Parametric and Nonparametric Models for Higher-order Interactions.

    In this talk, I will discuss about parametric and nonparametric models for higher-order interactions with a focus on the statistical and computational aspects.  ​In fields like social, political and biological sciences, there is a clear need ​for analyzing higher-order interactions as opposed to pairwise interactions, which has been the main focus of statistical networks analysis recently. ​Generalized ​Block models and hypergraphons ​are powerful tools for modeling ​higher-order interactions. ​ T​he talk will introduce the models, highlight the theoretical challenges and differences that arise when analyzing higher-order interactions compared to pairwise interactions, and discuss applications and numerical results.

All upcoming events

Meet our people

Cecilia Cotton

Cecilia Cotton

Associate Professor

Contact Information:
Cecilia Cotton

Research interests

The underlying theme of my research interests is using longitudinal data to solve problems in public health:

Inference for comparing survival across multiple dynamic treatment regimens based on observational longitudinal data. Applications to epoetin dosing strategies for hemodialysis subjects with chronic kidney disease. Joint modeling of longitudinal and survival data in the context of causal inference.