Statistics Program

(Offered as STAT 370 and MATH 370) This course examines the theory underlying common statistical procedures including visualization, exploratory analysis, estimation, hypothesis testing, modeling, and Bayesian inference. Topics include maximum likelihood estimators, sufficient statistics, confidence intervals, hypothesis testing and test selection, non-parametric procedures, and linear models.

Requisite: STAT 111 or STAT 135 and STAT 360, or consent of the instructor. Limited to 25 students. Spring semester. Professor Donges.

This course is an introduction to nonparametric and distribution-free statistical procedures and techniques. These methods rely heavily on counting and ranking techniques and will be explored through both theoretical and applied perspectives. One- and two-sample procedures will provide students with alternatives to traditional parametric procedures, such as the t-test. We will also investigate correlation and regression in a nonparametric setting. A variety of other topics may be explored in the nonparametric setting including resampling techniques (for example, bootstrapping), categorical data and contingency tables, density estimation, and the one-way and two-way layouts for analysis of variance. The course will emphasize data analysis (with appropriate use of statistical software) and the intuitive nature of nonparametric statistics.

Requisite: STAT 111 or STAT 135. Limited to 24 students.  Professor McShane. 

This course is an intermediate applied statistics course that builds on the statistical data analysis methods introduced in STAT 111 or STAT 135. Students will learn how to pose a statistical question, perform appropriate statistical analysis of the data, and properly interpret and communicate their results. Emphasis will be placed on the use of statistical software, data wrangling, model fitting, and assessment. Topics covered will include ethics, experimental design, resampling approaches, analysis of variance models, multiple regression, model selection, and logistic regression. No prior experience with statistical software is expected

Requisite: STAT 111 or 135. Limited to 24 students. Four spots reserved for incoming first-year students in each Fall section. Fall and Spring semester. Fall Professor Liao, Spring Professor Liao, Professor Matheson

Computational data analysis is an essential part of modern statistics and data science. This course provides a practical foundation for students to think with data by participating in the entire data analysis cycle. Students will generate statistical questions and then address them through data acquisition, cleaning, transforming, modeling, and interpretation. This course will introduce students to tools for data management, wrangling, and databases that are common in data science and will apply those tools to real-world applications. Students will undertake practical analyses of large, complex, and messy data sets leveraging modern computing tools

Requisite: STAT 111 or STAT 135 and COSC 111 or consent of the instructor. Limited to 24 students. Fall and Spring semesters. The Department. 

Computational data analysis is an essential part of modern statistics and data science. This course provides a practical foundation for students to think with data by participating in the entire data analysis cycle. Students will generate statistical questions and then address them through data acquisition, cleaning, transforming, modeling, and interpretation. This course will introduce students to tools for data management, wrangling, and databases that are common in data science and will apply those tools to real-world applications. Students will undertake practical analyses of large, complex, and messy data sets leveraging modern computing tools

Requisite: STAT 111 or STAT 135 and COSC 111 or consent of the instructor. Limited to 24 students. Fall and Spring semesters. The Department. 

(Offered as STAT 370 and MATH 370) This course examines the theory underlying common statistical procedures including visualization, exploratory analysis, estimation, hypothesis testing, modeling, and Bayesian inference. Topics include maximum likelihood estimators, sufficient statistics, confidence intervals, hypothesis testing and test selection, non-parametric procedures, and linear models.

Requisite: STAT 111 or STAT 135 and STAT 360, or consent of the instructor. Limited to 25 students. Spring semester. Professor Donges.

Linear regression and logistic regression are powerful tools for statistical analysis, but they are only a subset of a broader class of generalized linear models. This course will explore the theory behind and practical application of generalized linear models for responses that do not have a normal distribution, including counts, categories, and proportions. We will also delve into extensions of these models for dependent responses such as repeated measures over time.

Requisite: STAT 230 and STAT 360. Limited to 20 students. Spring semester. Professor Bailey. 

This course is an intermediate applied statistics course that builds on the statistical data analysis methods introduced in STAT 111 or STAT 135. Students will learn how to pose a statistical question, perform appropriate statistical analysis of the data, and properly interpret and communicate their results. Emphasis will be placed on the use of statistical software, data wrangling, model fitting, and assessment. Topics covered will include ethics, experimental design, resampling approaches, analysis of variance models, multiple regression, model selection, and logistic regression. No prior experience with statistical software is expected

Requisite: STAT 111 or 135. Limited to 24 students. Four spots reserved for incoming first-year students in each Fall section. Fall and Spring semester. Fall semester: Professors Matheson and Horton. 

This course is an intermediate applied statistics course that builds on the statistical data analysis methods introduced in STAT 111 or STAT 135. Students will learn how to pose a statistical question, perform appropriate statistical analysis of the data, and properly interpret and communicate their results. Emphasis will be placed on the use of statistical software, data wrangling, model fitting, and assessment. Topics covered will include ethics, experimental design, resampling approaches, analysis of variance models, multiple regression, model selection, and logistic regression. No prior experience with statistical software is expected

Requisite: STAT 111 or 135. Limited to 24 students. Four spots reserved for incoming first-year students in each Fall section. Fall and Spring semester. Fall semester: Professors Matheson and Horton. 

Computational data analysis is an essential part of modern statistics and data science. This course provides a practical foundation for students to think with data by participating in the entire data analysis cycle. Students will generate statistical questions and then address them through data acquisition, cleaning, transforming, modeling, and interpretation. This course will introduce students to tools for data management, wrangling, and databases that are common in data science and will apply those tools to real-world applications. Students will undertake practical analyses of large, complex, and messy data sets leveraging modern computing tools.

Requisite: STAT 111 or STAT 135 and COSC 111 or consent of the instructor. Limited to 24 students. Fall and Spring semesters. The Department. 

Computational data analysis is an essential part of modern statistics and data science. This course provides a practical foundation for students to think with data by participating in the entire data analysis cycle. Students will generate statistical questions and then address them through data acquisition, cleaning, transforming, modeling, and interpretation. This course will introduce students to tools for data management, wrangling, and databases that are common in data science and will apply those tools to real-world applications. Students will undertake practical analyses of large, complex, and messy data sets leveraging modern computing tools.

Requisite: STAT 111 or STAT 135 and COSC 111 or consent of the instructor. Limited to 24 students. Fall and Spring semesters. The Department. 

Making sense of a complex, high-dimensional data set is not an easy task. The analysis chosen is ultimately based on the research question(s) being asked. This course will explore how to visualize and extract meaning from large data sets through a variety of analytical methods. Methods covered include principal components analysis and selected statistical and machine learning techniques, both supervised (e.g. classification trees and random forests) and unsupervised (e.g. clustering). Additional methods covered may include factor analysis, dimension reduction methods, or network analysis at instructor discretion. This course will feature hands-on data analysis with statistical software, emphasizing application over theory.

The course is expected to include small group work, interactive labs, peer interactions such as peer review and short presentations, and a personal project, to foster student engagement in the course and with each other.

Requisite: STAT 111 or 135. Limited to 24 students. Fall semester. Omitted 2021-22. Professor Wagaman.

(Offered as STAT 360 and MATH 360) This course explores the nature of probability and its use in modeling real world phenomena. There are two explicit complementary goals: to explore probability theory and its use in applied settings, and to learn parallel analytic and empirical problem-solving skills. The course begins with the development of an intuitive feel for probabilistic thinking, based on the simple yet subtle idea of counting. It then evolves toward the rigorous study of discrete and continuous probability spaces, independence, conditional probability, expectation, and variance. Distributions covered include the binomial, hypergeometric, Poisson, normal, Gamma, Beta, multinomial, and bivariate normal. Other topics include generating functions, order statistics, and limit theorems.

Requisite: MATH 121 or consent of the instructor. Limited to 24 students. Fall semester. Professor Horton.

(Offered as STAT 360 and MATH 360) This course explores the nature of probability and its use in modeling real world phenomena. There are two explicit complementary goals: to explore probability theory and its use in applied settings, and to learn parallel analytic and empirical problem-solving skills. The course begins with the development of an intuitive feel for probabilistic thinking, based on the simple yet subtle idea of counting. It then evolves toward the rigorous study of discrete and continuous probability spaces, independence, conditional probability, expectation, and variance. Distributions covered include the binomial, hypergeometric, Poisson, normal, Gamma, Beta, multinomial, and bivariate normal. Other topics include generating functions, order statistics, and limit theorems.

Requisite: MATH 121 or consent of the instructor. Limited to 24 students. Fall semester. Professor Horton.

Real world datasets are plagued by missing observations. Statistical software packages often ignore these cases by default, but there are better ways to approach the problem. This course will introduce students to the different missing data mechanisms and explore naive and modern methods for handling missing data. It will prepare students to read the current literature in this area and have broad appreciation for the implications of missing data. 

This course is intended for students who have experience with standard statistical methods for complete data and want to extend them to handle missing data in practice.

Requisite: STAT 230 and STAT 370, or equivalent experience by consent of the instructor. Fall semester: Prof. Correia.

Our world is awash in data. To allow decisions to be made based on evidence, there is a need for statisticians to be able to make sense of the data around us and communicate their findings. In this course, students will be exposed to advanced statistical methods and will undertake the analysis and interpretation of complex and real-world datasets that go beyond textbook problems. Course topics will vary from year to year depending on the instructor and selected case studies but will include static and dynamic visualization techniques to summarize and display high dimensional data, advanced topics in design and linear regression, ethics, and selected topics in data mining. Other topics may vary but might include nonparametric analysis, spatial data, and analysis of network data. Through a series of case studies, students will develop the capacity to think and compute with data, undertake and assess analyses, and effectively communicate their results using written and oral presentation.

Requisite: STAT 230, STAT 231, STAT 370, and at least one COSC course numbered 111 or higher, or other computing experience by consent of the instructor. Limited to 20 students. Fall semester. Professor Wagaman.