Program Structure

This course will provide students with an understanding of statistical designs and inference with a focus on computational statistics. The course will expose students to useful classical statistics including various experimental designs and sampling, the likelihood, principles of estimation and hypothesis testing. Students will also learn about more modern variants including areas of computational statistics such as Bayesian statistics, resampling, and Gibbs sampling, simulation, and methods for missing data.

This course will expose students to the theory and applications of linear models from a statistical paradigm. A review of basic multiple regression and diagnostics will be followed by the theory and applications of mixed models and generalized linear models. Advanced regression including nonparametric regression and penalized regression will be covered.

This course is a comprehensive survey of concepts related to the management and manipulation of databases for data science endeavors. Core topics related to the theory and nature of working with data and databases, as well as contemporary and advanced methods for working with complex and/or large amounts of data will be covered. This course is designed to prepare data science professionals and researchers to key concerns in data management and approaches to address them.

This course will study the theory and applications of many foundational machine learning methods. Several supervised, semi-supervised and unsupervised learning approaches will be explored, including Bayesian methods, decision trees, kernel-based methods and neural networks methods, as well as areas of clustering and dimension reduction. We will also discuss how to model problems as machine learning problems. Methods discussed will be applicable to natural language processing, speech recognition, computer vision, data mining, adaptive computer systems and other areas.

The overall goal of this course is to enable students to build mathematical models of real-world systems, analyse them and make predictions about the behaviour of these systems. A variety of modelling techniques will be discussed with examples taken from physics, social science, life science, economics and other fields. The focus of the course will be on establishing connections between mathematics and physical systems, studying and applying various modeling techniques to describe these systems mathematically, and using this analysis to make predictions about the behaviour of the systems.

In this course, we introduce discrete optimization, exposing students to some of the most fundamental concepts, techniques and algorithms in the field. This includes linear optimization, integer and mixed programming, network optimization, goal programming, multi-criteria decision analysis, constraint programming and game theory. The techniques and algorithms will be applied to complex practical problems such as scheduling, network security, social network, vehicle routing, supply-chain optimization and resource allocation. Students will also be expected to do a project on an application of their choice.

This course will provide students with applications of data science in business and economics. Students learn to integrate personal judgment and intuition in realistic business situations with the most widely applicable methodologies of decision and risk analysis, probability and statistics, competitive analysis, and management science. Topics include an introduction to decision analysis and modelling; spreadsheet engineering and error reduction; framing decision analysis problems; framework for analyzing risk; data analysis; resource allocation with optimization models; multi-period deterministic models; multi-factor deterministic models; regression modelling; strategic interactive decisions; and interpreting models, data, and decisions. 

This course focuses on the development of research skills required for framing strong hypotheses and performing robust experiments using large biological and biochemical data sets. Beginning with an introduction to genome evolution, organization and regulation, the major goal of the course is to develop skills for framing important biological hypotheses and deploying appropriate tools for testing those hypotheses. Approaches for data quality assessment and evaluation of computational tools is a major theme, and laboratory time will provide hands-on experience with analysis of DNA, RNA and protein sequence data, and the regulatory networks controlling gene expression and metabolic activity. Focus will be placed on experimental design, interacting with data in local and public databases, version control, documentation, and conducting reproducible research.

Students explore various topics related to data science. Course topics vary to ensure a timely coverage of new techniques, software, theories, and trends.

In this independent study course, students investigate a specific topic of interest in data science. The instructor and the student mutually determine course content.

Hands-on experience undertaken by a student is an integral part of data science program. Work experience provide opportunities for the program and its community to combine resources to further the student’s knowledge, personal interest, career path and employability skills through activities at work sites. Therefore, students taking a paid job (e.g., paid internship) related to data analysis can earn work experience credits. The typical work includes a research assistant job in statistical analysis, or data analyst in a financial, IT or industrial organization. Usually the minimum length of employment to qualify for three credits is 12 weeks. Students may earn up to maximum six credits (e.g., one eight-month job or two four-month jobs).

To cope with the rapid-changes in knowledge, software, techniques and directions in data science, it is important for students and instructors to stay on top of the growth and progress in this fast-moving discipline. The interdisciplinary nature of data science also demands that students are aware of the methods and applications from a wide range of backgrounds and learn beyond the course content of the program. To serve this purpose, the seminar and colloquium series will invite scientists and technology leaders to present current developments and trends in big data and data analytics, and to showcase the successful real-world applications. This is also the opportunity for students and faculty to share their research ideas and results.

Students in this option are required to develop an applied project that addresses a major data analytics problem with a real-world application (preferably a problem identified by industry partner or internship company). Students are expected to apply the techniques, skills and knowledge gained through the course work of the program to the data analytic problem. Through the project, students will engage in designing, developing, implementing and testing of a data analytic algorithm/system to achieve pre-defined objectives.

Students in the Graduate Thesis Option in the MSc in Data Science program undertake an independent research project of relevance to data science, generating original theoretical contributions that advance the body of literature in this field, prepare and defend a thesis in accordance with the policies established by the Research, Innovation, and Graduate Studies Office at TRU. The thesis is completed under the supervision of a faculty member and a thesis supervisory committee and evaluated by a thesis defense/examining committee.