Biostatistics

• SPH BS 704: Introduction to Biostatistics
  This course provides an overview of biostatistical methods, and gives students the skills to perform, present, and interpret basic statistical analyses. Topics include the collection, classification, and presentation of descriptive data; the rationale of estimation and hypothesis testing; analysis of variance; analysis of contingency tables; correlation and regression analysis; multiple regression, logistic regression, and the statistical control of confounding; sample size and power considerations; survival analysis. Special attention is directed to the ability to recognize and interpret statistical procedures in articles from the current literature. Students will use the R statistical package to analyze public health related data. * Can't be taken together for credit with SPH PH 717
• SPH BS 722: Design and Conduct of Clinical Trials
  Graduate Prerequisites: (SPHPH717) or consent of instructor. - This course covers the development, conduct, and interpretation of clinical trials. It is suitable for concentrators in any department. Topics include principles and practical features such as choice of experimental design, choice of controls, sample size determination, methods of randomization, adverse event monitoring, research ethics, informed consent, data management, and statistical analysis issues. Students write a clinical trial protocol during the semester.
• SPH BS 723: Introduction to Statistical Computing
  Graduate Prerequisites: SPH PH 717 or SPH BS 704 or SPH BS 700 or SPH BS 800; or consent of instructor. Can't be taken together for credit with SPH PH 760 or BS 730 This course introduces students to statistical computing with focus on the SAS package. Emphasis is on manipulating data sets and basic statistical procedures such as t-tests, chi-square tests, correlation and regression. Conditions underlying the appropriate use of these statistical procedures are reviewed. Upon completion of this course, the student will be able to use SAS to: read raw data files and SAS data sets, subset data, create SAS variables, recode data values, analyze data and summarize the results using the statistical methods enumerated above. This course includes hands-on exercises and projects designed to facilitate understanding of all the topics covered in the course. Students use equipment and software available through the Boston University Medical Center. This course is a prerequisite for these SPH courses: BS805, BS820, BS821, BS851, BS852, BS853 and BS858.
• SPH BS 728: Public Health Surveillance,a Methods Based Approach
  Graduate Prerequisites: (SPHBS723 OR SPHBS730) consent of instructor - Thacker wrote, "Surveillance is the cornerstone of public health practice." This course will provide an introduction to surveillance and explore its connections to biostatistics and public health practice. Topics will include complex survey design, weighted sampling, capture-recapture methods, time series analyses and basic spatial analyses. Students will learn about available surveillance data, how to analyze these data, and how to write about their findings. This class carries Epidemiology concentration credit.
• SPH BS 730: Introduction to R: software for statistical computing
  Graduate Prerequisites: (SPHPH717 OR SPHBS704 OR SPHBS700 OR SPHBS800) or consent of instructor. - Students will learn how to conduct statistical analysis using the public domain and free statistical software, R. Many public, private, and international organizations use R to conduct analysis, thus experience with R is a great skill to add to one's credentials. R offers flexibility, ranging from ease of writing code for simple tasks (e.g. using R as a calculator) to implementing complex analyses using cutting-edge statistical methods and models. Additionally, the R language provides a rich environment for working with data, especially for statistical modeling, graphics, and data visualization. This course will emphasize data manipulation and basic statistical analysis including exploratory data analysis, classical statistical tests, categorical data analysis, and regression. Students will be able to identify appropriate statistical methods for the data or problems and conduct their own analysis using the R environment. This hands-on and project-based course will enable students to develop skills to solve statistical problems using R. R can be used as an alternative or in addition to SAS (BS723). R is compatible with Apple OS, Windows, and Unix environments.
• SPH BS 750: Essentials of Quantitative Data Management
  Graduate Prerequisites: SPH BS723 or consent of instructor - Any data analysis is only as good as the data on which it is based. This course will focus on the importance of high quality data and the skills required for effective data management, including collection, cleaning, auditing, and merging. Students will have hands-on experience with data sets. Examples of what can go wrong and how research can be complicated by or produce erroneous results due to poor quality data will be provided.
• SPH BS 755: Linear Models
  Graduate Prerequisites: (CASMA214 & CASMA242 & CASMA581) or consent of instructor. - * Post-introductory course on linear models. Topics to be covered include simple and multiple linear regression, regression with polynomials or factors, analysis of variance, weighted and generalized least squares, transformations, regression diagnostics, variable selection, and extensions of linear models. Effective Fall 2023, this course fulfills a single unit in the following BU Hub area: Quantitative Reasoning II, Teamwork/Collaboration.
  BU Hub Learn More

  • Quantitative Reasoning II
  • Teamwork/Collaboration
• SPH BS 800: Accelerated Statistical Training
  Graduate Prerequisites: One year of college-level calculus, including multivariable calculus, and linear algebra to cover matrix operations, matrix functions, and s ingular value decomposition. - This course is designed for the MS in Applied Biostatistics program and will cover concepts of descriptive statistics and exploratory data analysis, measures of association in epidemiological studies, probability, statistical inference and computing in R and SAS. It is intended to equip students enrolling in the MS in Applied Biostatistics program with sufficient probability, statistics and computing background to enter 800 levels courses and finish the MS program within a year. The course will be offered during 2 weeks preceding the Fall semester, and will involve 10 day-long modules. Modules will generally run from 10am to 5pm, combining a traditional lecture (10am to 12pm), a practice session in which students will practice the notions learned in class through exercises (1pm to 2:30pm), and a computer lab (3pm to 5pm) in which the students will learn basic computing in R and SAS and also apply the notions learned in class to real data. Allowing a student to waive this course is at the discretion of the MS in Applied Biostatistics program directors.
• SPH BS 803: Statistical Programming for Biostatisticians
  Graduate Prerequisites: ((SPH PH 717 or SPH BS 704) and BS723) or SPH BS 800; or consent of instructor. - This course will focus on skills required for advanced computing applications in biostatistics. Students will learn statistical programming and methods such as loops, functions, macros as well as data visualization techniques in SAS and R. Furthermore, the course will provide and introduction to Linux and basic statistical programming in Python. Lab sessions S will also provide students with basic computing skills to enroll to more advanced statistical classes such as BS830 and BS857.
• SPH BS 805: Intermediate Statistical Computing and Applied Regression Analysis
  Graduate Prerequisites: (SPHBS723) consent of instructor. It is not recommended that BS805 and BS852 be t aken concurrently. * Can't be taken together for credit with SPH BS 8 06 - This course is a sequel to BS723. Emphasis is placed on the use of intermediate-level programming with the SAS statistical computer package to perform analyses using statistical models with emphasis on linear models. Computing topics include advanced data file manipulation, concatenating and merging data sets, working with date variables, array and do-loop programming, and macro construction. Statistical topics include analysis of variance and covariance, multiple linear regression, principal component and factor analysis, linear models for correlated data, and statistical power. Includes a required lab section.
• SPH BS 806: Multivariable Analysis for Biostatisticians
  Graduate Prerequisites: One year of college-level calculus, including multivariable calculus, and linear algebra to cover matrix operations, matrix functions and singular value decomposition. Can't be taken together for credit with BS 805. - This course will focus on skills required for effective conduct of data analysis with statistical packages, primary with R. This course will focus on the multiple regression modeling and multivariate analysis to cover multi-way ANOVA, multiple linear regression, classification and regression trees, automated model search, model fit and diagnostic, and multivariate analysis (PCA and cluster analysis) with particular emphasis on applications in medicine and public health.
• SPH BS 807: Applied Causial Inference in Health Research
  Graduate Prerequisites: (SPHBS723 OR SPHBS730) and BS852 or EP854 or consent of instructor. The course requires expe rience with logistic regression and survival analysis, and SAS or R co ding. - * This is an advanced statistics course, focused on application of causal inference methods in medical research. Topics covered include counterfactual outcomes, causal diagrams, mediation analysis, instrumental variable, and g- methods to deal with time-varying confounding. This course includes lectures, computer instructions, and discussion of reading material.
• SPH BS 810: Meta-Analysis for Public Health & Medical Research
  Graduate Prerequisites: (SPHBS723 OR SPHBS730) or consent of instructor. - Meta-analysis is the statistical analysis of research findings and is widely used in public health and medical research. Typically meta-analysis is employed to provide summary results of the research in an area, but other uses include exploratory analyses to find types of subjects who best respond to a treatment or find study-level factors that affect outcomes. The course will cover the theory and use of the most common meta-analytic methods, the interpretation and limitations of results from these methods, diagnostic procedures, and some advanced topics with a focus on public health application. Grading will be based on homework, an exam and a project.
• SPH BS 820: Logistic Regression and Survival Analysis
  Graduate Prerequisites: (SPHPH717) and BS723 or BS852; or consent of instructor - This course provides basic knowledge of logistic regression and analysis of survival data. Regression modeling of categorical or time-to-event outcomes with continuous and categorical predictors is covered. Checking of model assumptions, goodness of fit, use of maximum likelihood to determine estimates and test hypotheses, use of descriptive and diagnostic plots are emphasized. The SAS statistical package is used to perform analyses. Grading will be based on homework and exams.
• SPH BS 821: Categorical Data Analysis
  Graduate Prerequisites: (SPHBS723 OR SPHBS730) or consent of instructor. - This course focuses on the statistical analysis of categorical outcome data. Topics include the binomial and Poisson distributions, logistic and Poisson regression, nonparametric methods for ordinal data, smoothed regression modeling, the analysis of correlated categorical outcome data, cluster analysis, missing data and sample size calculations. The course emphasizes practical application and makes extensive use of the SAS and R programming languages.
• SPH BS 825: Advanced Methods in Infectious Disease Epidemiology
  Graduate Prerequisites: (SPHEP755) and BS730 or BS723; or consent of instructor - This course aims to introduce students to statistical and mathematical methods used in infectious disease epidemiology. Students will be able to evaluate and appraise the literature in this field, be able to select which methods to use in different circumstances, implement some methods in simple situations and we will provide sufficient background reading that students can further examine methods that are of particular interest. This will be a hands-on course involving class discussions, computer lab sessions and a class debate on a controversial topic in infectious disease epidemiology.
• SPH BS 831: Genomics Data Mining and Statistics
  Graduate Prerequisites: Knowledge of basic statistics techniques (SPHBS704 or SPHPH717 or equi valent) and basic statistical computing skills using R (SPHBS730 or e quivalent) or consent of instructor - The goal of this course is for the students to develop a good understanding and hands-on skills in the design and analysis of 'omics' data from microarray and high-throughput sequencing experiments, including data collection and management, statistical techniques for the identification of genes that have differential expression in different biological conditions, development of prognostic and diagnostic models for molecular classification, and the identification of new disease taxonomies based on their molecular profile. These topics will be taught using real examples, extensively documented hands- on work, class discussion and critical reading. Students will be asked to analyze real gene expression data sets in their homework and final project. Principles of reproducible research will be emphasized, and students will become proficient in the use of the statistical language R (an advanced beginners knowledge of the language is expected of the students entering the class) and associated packages (including Bioconductor), and in the use of R markdown (and/or electronic notebooks) for the redaction of analysis reports.
• SPH BS 835: Applied Intermediate Biostatistics
  Graduate Prerequisites: (SPHBS723 OR SPHBS730) or consent of instructor * Can't be taken together for credit with SPH BS 852 - Students with a strong interest in statistical programming and a strong mathematical background are encouraged to take BS805 and BS852 rather than BS835, as students cannot take both BS835 and BS852 for credit. This course covers intermediate-level statistical methods commonly used in epidemiologic and public health research. The course has an applied focus, with emphasis on understanding research questions addressed by these methods, key assumptions these analyses rely on, and the presentation and interpretation of results. Students will use either the SAS or R statistical package to carry out analyses. Topics include multivariable regression models for continuous, binary, survival, and longitudinal outcome data, stratified and matched analyses of epidemiologic data, and analysis of survival data. This course will provide the student with training in intermediate level biostatistical analyses and the use of biostatistical software.
• SPH BS 845: Data Science and Statistical Modeling in R
  Graduate Prerequisites: (SPHBS730) or consent of instructor. - This course covers applications of modern statistical methods using R, a free and open source statistical computing package with powerful yet intuitive graphic tools. R is under more active development for new methods than other packages. We will first review data manipulation and programming in R, then cover theory and applications in R for topics such as linear and smooth regressions, survival analysis, mixed effects model, tree based methods, multivariate analysis, boot strapping and permutation.
• SPH BS 849: Bayesian Modeling for Biomedical Research & Public Health
  Graduate Prerequisites: At least one course of statistics to cover principles of probability a nd statistical inference, linear and logistic regression. Knowledge of R. - The purpose of this course is to present Bayesian modeling techniques in a variety of data analysis applications, including both hypothesis and data driven modeling. The course will start with an overview of Bayesian principles through simple statistical models that will be used to introduce the concept of marginal and conditional independence, graphical modeling and stochastic computations. The course will proceed with the description of advanced Bayesian methods for estimation of odds and risk in observational studies, multiple regression modeling, loglinear and logistic regression, hierarchical models, and latent class modeling including hidden Markov models and application to model-based clustering. Applications from genetics, genomics, and observational studies will be included. These topics will be taught using real examples, class discussion and critical reading. Students will be asked to analyze real data sets in their homework and final paper.