Health-related statistical applications. Descriptive statistics, probability, confidence intervals, hypothesis testing, regression, correlation, ANOVA. May not be used as part of a degree program in epidemiology or biostatistics. Three lecture hours and one laboratory hour per week.

Descriptive and inferential statistical applications to public health. Probability, interval estimation, hypothesis testing, measures of association. Three lecture hours and one laboratory hour per week. Intended for those who will be involved in research applications of biostatistics.

Working with public health data using statistical software. Effective ways to store, clean, merge, and format public health data for analysis.

Statistical data management techniques. Microcomputer applications, communication between microcomputers and mainframe, tape and disk storage, access of large health-related databases.

Students will learn the software program R for performing data management. The course covers basic to advanced commands for properly formatting output, merging data, working with functions, graphing, using programming loops for preparing data for analysis for public health data.

Students will learn the software program Stata for performing data management. The course covers basic to advanced commands for properly formatting output, merging data, working with functions, graphing, using programming loops for preparing data for analysis for public health data.

This course focuses the uses of Microsoft Access for data management in public health. The course takes the student through building tables, forms, queries, reports and finishes with automated scripts for each of use with Access.

This course focuses on advanced programming for managing and analyzing data using SAS. Building upon skills learned in BIOS 709 (Introduction to SAS), students will learn data management using PROC SQL. Students will also become familiar with the SAS Macro Language which prepares data for conducting efficient statistical analysis.

This course teaches advanced techniques for creating and using large data sets. Students will learn advanced techniques for working with data, cleaning data, and preparing it for analysis using three software packages (SAS, STATA, MS Access) for data entry, data management, and presentation. For statistical analysis, students will learn advanced SAS, the primary statistical package used for data analysis in other biostatistics and epidemiology courses.

This course introduces the fundamental concepts and applications of machine learning (ML) in the context of public health, biostatistics, and related fields (e.g., epidemiology, psychology, neuroscience, genetics). Students will learn how to prepare data, select and implement appropriate machine learning methods, and evaluate model performance—all using R. Emphasis will be placed on conceptual understanding, practical implementation, and interpretation of results rather than on mathematical derivations. By the end of the course, students will be prepared to incorporate ML techniques into their own research projects, with a special focus on the unique challenges and ethical considerations inherent in analyzing public health data.

Analysis of current and prospective issues in biostatistics, including historical foundations. Includes student exploration of unsolved problems and examination of central issues in biostatistics.

Students will learn the basics of data collection methods, sampling design for linear, logistic, and survival analysis complex models using survey data. Students will also learn about weight adjustments, imputation methods with an emphasis on both applied models and the theory behind them.

Process, skills, and management of undertaking health studies in the human community.

Analysis of discrete data in public health studies. Relative risk, odds ratio, rates and proportions, contingency tables, logistic regression, introduction to other advanced topics. Not for biostatistics majors.

Introduction to principles and methods for longitudinal & multi-level modeling. Focus on data analysis and interpretation.

Public health applications of correlation, regression, multiple regression, single and multi-factor analysis of variance and analysis of covariance.

Public health applications of correlation, regression, multiple regression, single and multi-factor analysis of variance and analysis of covariance. Additional topics in analysis of health data including regression diagnostics, multi-collinearity of observational data, ridge/nonlinear regression, principal components, random/mixed effects, unbalanced designs, repeated measures and sampling and design effects.

The concepts, principles, and biostatistical techniques necessary to analyze categorical epidemiological data including dose response curves, life tables, and discrete measures of association. Estimation of parameters for logistic and other commonly used epidemiological models.

The basic and advanced statistical techniques necessary for the design, conduct, analysis, and interpretation of results of clinical trials.

Methods for the analysis of survival data in the biomedical setting. Underlying concepts; standard parametric and nonparametric methods for one or several samples; concomitant variables and the proportional hazards model.

This course is an introduction to important topics and key concepts in statistical genetics, with emphasis on statistics methods and their applications to human complex diseases. The course will cover major concepts and classical statistical methods for the analysis of family and population based human genetic data.

Fundamentals of constructing, analyzing, and interpreting biomedical studies; internal and external validity, sample size determination, completely random designs, blocking crossover designs, factorial designs, confounding, nested designs, repeated measure designs.

Spatial statistics methods commonly used in public health including mapping, tests for spatial correlation, hypothesis tests for spatial clustering, and regression models with spatial random effects.

Modern methods for the analysis of repeated measures, correlated outcomes, and longitudinal data, including repeated measures ANOVA, generalized linear models, random effects, and generalized estimating equations.

Bioinformatics analyses related to public health and biomedical research. Gene-gene and gene-environment interaction, phylogeny analysis in disease classification, and clustering for expression data. Data analyses, simulation studies, algorithms, and interpretation of health data.

Principles and methods of quantile regression, a robust and distribution-free statistical approach that extends the classical mean regression to the analysis of complex treatment effects.

Directed research on a topic to be developed by M.P.H. or M.S.P.H. student and instructor. May be repeated.

Content varies by title. Course may be repeated for a total of 6 credit hours.

Parametric survival analysis, accelerated failure time model, frailty model, competing risk mode and multi-state model. Techniques motivated by applications in epidemiology and clinical medicine research, applications demonstrated using public health data sets.

Statistical theory and applications extending regression and analysis of variance to non-normal data. An integrated treatment encompassing logistic and other binary regressions, log-linear models, and gamma regression models.

R is a free and open source software environment for statistical computing and graphics. This course provides the principles and techniques to efficiently design, implement, and execute simulation and data analysis routines in quantitative fields like biostatistics, statistics, engineering, finance, and data science.

An overview of advanced computational statistics for signal and network analysis with a wide variety of social, genomic and neuroscientific applications. All course modules include a hands-on component.

Bayesian statistical methods including hierarchical modeling and the use of the Markov Chane Monte Carlo (MCMC) methods.

A comprehensive introduction to the statistical methods used in the analysis of geo-referenced spatial health data. Topics range from disease mapping to prospective surveillance.

Analysis of multivariate data as found in biomedical studies: multivariate linear models, principal component analysis, factor analysis, discriminant and cluster analysis. Other special multivariate topics such as principal component regression.

The focus of this course will be on using biostatistical models to predict and provide information on complex public health datasets. We will focus more on prediction of outcome(s) than estimation of the impact of a risk factor. However, some interferential methods for risk factors will be reviewed and (for all methods) techniques to measure variable importance will be discussed. Further, unsupervised learning methods (e.g., clustering) will be discussed. Prediction and predictive inference will be main themes in the course along with learning how to implement the methods in R software. See the syllabus course schedule for a full list of topics.

May be repeated for credit.

Threshold, mass action and target theory; empirical dose response functions; methods in current use among health science researchers.

Directed research on a topic to be developed by doctoral student and instructor. May be repeated.

Discussion on current and emerging issues in biostatistics.

Students are required to conduct applied public health methods and strategies as a part of their practicum experience. In particular, the student should successfully implement and interpret the results of biostatistical methods in the organization.

Prerequisite: one full year (18 hours) of graduate study beyond the master’s level.