Statistics and Data Science

SDS 164: Data Science 1

Data is the currency of the modern world. At the intersection between statistics and computer science, data science is about gleaning information and making decisions from data. Using data from a variety of contexts and disciplines, students learn to summarize and extract insight from data, create compelling data visualizations, wrangle data, practice literate programming, and explore ethical issues in data science. Offered annually during fall and spring semesters. No prior experience with programming is expected. This course cannot be taken after SDS 264.

SDS 172: Statistics 1

A first course in statistical methods, this course addresses study design and its implications as well as exploratory and inferential techniques for analyzing and modeling data. Topics include exploratory graphics, descriptive techniques, randomization tests, statistical designs, hypothesis testing, confidence intervals, and simple/multiple regression. Offered each semester. Enrollment limited for seniors. STAT 110, SDS 172, and ECON 260 all provide an introduction to statistics and students should not take more than one; they all can serve as a prerequisite for further courses.

SDS 232: Spatial Data Analysis

Data collected over space - including county level health information, satellite derived maps of glacier ice, or locations of hawk nests - require special methods for data cleaning, visualization, and modeling. In this course, students build upon foundational concepts of hypothesis testing, regression modeling, and data visualization from prior Statistics and Data Science (SDS) courses, adapting them to the particularities of spatial data using examples from a broad variety of fields. Offered alternate years during January term.
Prerequisite: SDS 164 and SDS 172.

SDS 250: Principles of Data Visualization

This course explores the history, foundational principles, and theory of data visualization. By designing and creating visualizations with a focus on the iterative process, students learn how to clearly and effectively communicate a story with data. The course utilizes multiple forms of visualization, from sketches to static plots to interactive web -based dashboards using professional visualization software. Offered alternate years during spring semester.
Prerequisites: SDS 164, SDS 172, AP Statistics, or permission of instructor.

SDS 264: Data Science 2

After mastering the foundations of data science - especially data wrangling and visualization - in SDS 164, data science students are ready to explore impactful applications and deeper fundamentals. Programming fundamentals may include iteration, functions, conditions, data types, SQL, regular expressions, version control, and simulation - all in the context of real data. New applications may include text as data, geospatial mapping, networks, and web scraping to produce dynamic graphics - presented with attention to data ethics and reproducible research. Offered annually.
Prerequisite: SDS 164: Data Science 1.

SDS 272: Statistics 2

This course takes a case-study approach to the fitting and assessment of statistical models with application to real data. Specific topics include multiple regression, model diagnostics, logistic regression, experimental design and ANOVA. The approach focuses on problem-solving tools, interpretation, model assumptions underlying analysis methods, and written statistical reports. Offered each semester.
Prerequisite: SDS 172, ECON 260 or equivalent preparation (STAT 110 and SDS 164) or (AP Stat and SDS 164), or permission of instructor.

SDS 280: Topics in Data Science

Students work intensively on a special topic in data science. Topics may vary from year to year. May be repeated if topics are different. Offered periodically.
Prerequisites: permission of instructor.

SDS 282: Topics in Statistics

Students explore special topics in statistics. Topics vary from year to year. May be repeated if topic is different. Offered periodically.

SDS 284: Biostatistics: Design and Analysis

The course investigates issues in health-related settings using a quantitative, research-oriented perspective. Course material focuses on global and public health issues, study design, methods for analyzing health data, and communication of research findings. Design topics include controlled trials, case-control, cohort and other observational studies. Methods include survival analysis and causal inference for observational studies. Communication emphasizes writing up findings and interpreting published research. Offered alternate years during January term.
Prerequisite: completion of SDS 272 or permission of the instructor.

SDS 294: Academic Internship

SDS 298: Independent Study

SDS 316: Advanced Statistical Modeling

This course extends and generalizes methods introduced in SDS 272 by introducing generalized linear models (GLMs) and correlated data methods. GLMs cover logistic and Poisson regression, and more. Correlated data methods include longitudinal data analysis and multi level models. Applications are drawn from across the disciplines. Offered annually.
Prerequisite: SDS 272.

SDS 322: Statistical Theory

This course is an investigation of modern statistical theory along with classical mathematical statistics topics such as properties of estimators, likelihood ratio tests, and distribution theory. Additional topics include Bayesian analysis, bootstrapping, Markov Chain Monte Carlo, and other computationally intensive methods. Offered alternate years.
Prerequisite: SDS 272 and MATH 262.

SDS 333: High-Dimensional Data Analysis

Data with thousands of dimensions or columns is commonplace across multiple disciplines, including image analysis, natural language processing, genomics, time series, and recommendation systems. In this class students learn, understand, and apply principles and techniques to gain insights from high-dimensional data. Topics include clustering, principal component analysis, multidimensional scaling, non-negative matrix factorization, missing-value imputation for recommendation systems, topic modeling, word embeddings, object recognition using "eigenfaces", non-linear embedding techniques, multiple hypothesis testing, and false discovery rate adjustments. Offered periodically during fall and spring semesters.
Prerequisites: MATH 220 and SDS 164.

SDS 341: Algorithms for Decision Making

This course introduces students to the subject of machine learning. The primary focus is the development and application of powerful machine learning algorithms applied to complex, real-world data. Topics covered include linear regression, nearest neighbor models, k-means clustering, shrinkage methods, decision trees and forests, boosting, bagging, support vector machines, and hierarchical clustering. Applications are taken from a wide variety of disciplines, including biology, economics, public policy, public health, and sports. Offered annually during fall and spring semester.
Prerequisite: SDS 164 or SDS 264 or permission of the instructor.

SDS 380: Advanced Topics in Data Science

Students work intensively on a special topic in data science. Topics may vary from year to year. May be repeated if topics are different. Offered periodically.
Prerequisites: SDS 264 and permission of the instructor.

SDS 382: Advanced Topics in Statistics

Students work intensively on a special topic in statistics. Topics may vary from year to year. May be repeated if topics are different. Offered periodically.
Prerequisites: Permission of instructor.

SDS 389: Statistics and Data Science Research Methods (0.50)

Students focus on writing scientific papers, preparing scientific posters, and giving presentations in the context of a specific, year-long, interdisciplinary research project. In addition, this weekly seminar series builds collaborative research skills such as working in teams, performing reviews of math, statistics, and computer science literature, consulting effectively, and communicating proficiently. Exposure to post-graduate opportunities in statistics and data science disciplines is also provided. Open to students accepted into the Center for Interdisciplinary Research and by permission of the instructor only. This course does not count toward the SDS Major or SDS Concentration.

SDS 394: Academic Internship

SDS 396: Directed Undergraduate Research

This course provides a comprehensive research opportunity, including an introduction to relevant background material, technical instruction, identification of a meaningful project, and data collection. The topic is determined by the faculty member in charge of the course and may relate to their research interests. Offered based on department decision. May be offered as a 1.00 credit course or .50 credit course.
Prerequisite: determined by individual instructor.

SDS 398: Independent Research