# Curriculum

Department of Biostatistics and Computational Biology Course Schedules (BST courses)

University of Rochester Course Schedules (All course offerings, including IND courses)

## BST Course Offerings

The following is a complete listing of courses offered by the Department of Biostatistics and Computational Biology.

• BST 461 Biostatistical Methods I
• BST 462 Biostatistical Methods II
• BST 463 Introduction to Biostatistics
• BST 465 Design of Clinical Trials
• BST 467 Applied Statistics in the Biomedical Sciences
• BST 479 Generalized Linear Models
• BST 487 Seminar in Statistical Literature
• BST 491 Reading Course at the Master's Level
• BST 493 Capstone Project
• BST 495 Research at the Master's Level
• BST 511 Topics in Statistical Inference I
• BST 512 Topics in Statistical Inference II
• BST 513 Analysis of Longitudinal and Dependent Data

## BST Course Descriptions

Unless otherwise noted all courses carry four credit hours.

### BST 401 Probability Theory

Prerequisite: MTH 265 or equivalent (or permission).

Probability spaces; random variables; independence; distributions; expectation; characteristic functions and inversion theorems; convergence; laws of large numbers; central limit theorem.

### BST 402 Stochastic Processes

Prerequisite: BST 401.

Markov chains; birth-death processes; random walks; renewal theory; Poisson processes; Brownian motion; branching processes; martingales; with applications.

### BST 411 Statistical Inference I

Prerequisite: STT 203 or equivalent.

Probability distributions, transformations and sampling distributions; statistical models; estimation, hypothesis testing, and confidence intervals for parametric models; introduction to large-sample methods.

### BST 412 Statistical Inference II

Prerequisites: BST 401 and BST 411.

Types of convergence; asymptotic linearity; influence functions; consistency and asymptotic normality; large sample estimation, maximum likelihood estimation; Wald, likelihood ratio, and score tests; generalized Neyman-Pearson lemma; nuisance parameters; efficiency; alternative methods for estimation (M-estimation, GEE, generalized method of moments); resampling methods (bootstrap, permutation tests); decision-theoretic inference.

### BST 413 Bayesian Inference

Prerequisite: BST 411.

Posterior distributions for single and multiple parameter models under conjugacy; hierarchical models; noninformative and informative prior distributions; modern computational techniques, including Markov chain Monte Carlo; model checking; posterior predictive checks; sensitivity analysis.

### BST 426 Linear Models

Prerequisites: STT 203 and MTH 235.

Theory of least-squares; point estimation in the general linear model; projection operators, estimable functions and generalized inverses; tests of general linear hypotheses; power; confidence intervals and ellipsoids; simultaneous inference; linear and polynomial regression; analysis of variance and analysis of covariance models; fixed, random, and mixed effects; correlation; prediction.

### BST 430 Introduction to Statistical Computing

Prerequisite: BST 411 (or co-enrollment).

Basic/intermediate R programming; statistical analysis in R; visualization in R; reproducible research and collaborative coding; command line tools and BlueHive. Introduction to SAS programming; statistical analysis in SAS. Topics in statistical analysis provide working examples.

### BST 432 High Dimensional Data Analysis

Prerequisites: BST 401 and BST 411.

Application of statistical theory to the analysis of high throughput data; introduction to Bioconductor; molecular profiles (mRNA, cDNA, microRNA, proteomics); platforms (Affymetrix and other microarrays, PCR, RNA seq); quality control (quality assessment, batch-effects); exploratory methods (graphical methods, clustering, principal component analysis and other dimension reduction techniques); differential expression and multiple hypothesis testing; classification (feature selection, multivariate methods, machine learning, cross-validation).

### BST 433 Computational Systems Biology

Prerequisites: BST 401 and BST 411.

Overview of the relevant molecular and cellular biology; overview of bioinformatic data, including high-throughput platforms, annotation, ontology, and pathway databases; introduction to Bioconductor; gene set enrichment analysis; supervised and unsupervised machine learning; network models (including Bayesian networks and Boolean networks); protein-protein interaction networks; dynamic models and time-course data.

### BST 434 Genomic Data Analysis

Prerequisite: BST 411.

Introduction to techniques used in modern genomic experimentation and the corresponding statistical methods and software available to visualize, analyze, and interpret these data. Specific topics include mRNA/microRNA expression, protein abundance, protein-DNA binding, copy number variants, single nucleotide variants, DNA methylation, and microbial abundance.

### BST 450 Data Analysis

Prerequisites: BST 426 and BST 430.

Statistical analysis of data under nonstandard conditions; examination of adequacy of model assumptions; goodness-of-fit testing; transformations; robust inference.

### BST 452 Design of Experiments

Prerequisites: BST 426 and BST 430.

Completely randomized designs; replication; covariate adjustment; randomized block designs; fixed vs. random effects; Latin and Graeco-Latin squares; confounding; nesting; factorial and fractional factorial designs; split-plot designs; incomplete block designs; response surfaces.

### BST 461 Biostatistical Methods I

Prerequisite: BST 463 or equivalent.

Study designs; inference regarding proportions; contingency table analysis; diagnostic testing; one-way and two-way analysis of variance; multiple comparisons involving means; simple and multiple linear regression; analysis of covariance; interactions; logistic and Poisson regression; introduction to survival analysis; multicollinearity; variable selection; model checking; sample size determination.

### BST 462 Biostatistical Methods II

Prerequisite: BST 461 or equivalent.

Linear mixed effects models; intraclass correlation; advanced logistic regression; generalized estimating equations; missing data; extensions of the Cox proportional hazards model; shrinkage estimation in regression; nonparametric methods; bootstrap methods; scatterplot smoothing; nonparametric regression (trees, forests, generalized additive models).

### BST 463 Introduction to Biostatistics

Credits: 3

Introduction to statistical techniques with emphasis on applications in the health sciences. Summarizing and displaying data; introduction to probability; Bayes’ theorem and its application in diagnostic testing; binomial, Poisson, and normal distributions; sampling distributions; estimation, confidence intervals, and hypothesis testing involving means and proportions; simple correlation and regression; contingency tables; use of statistical software.

### BST 465 Design of Clinical Trials

Prerequisite: BST 463 or equivalent.

Introduction to the principles of clinical trials; clinical trial protocols; overview of the drug development process; hypotheses/objectives; specification of response variables; defining the study population; randomization; blinding; ethical issues; factorial designs; crossover designs; equivalence trials; trial monitoring and interim analyses; sample size and power; issues in data analysis and reporting; evaluating clinical trial reports.

### BST 467 Applied Statistics in the Biomedical Sciences

Credits: 3

Introduction to statistical techniques with emphasis on applications in the biomedical sciences. Introduction to probability and probability distributions; sampling distributions; estimation, confidence intervals, and hypothesis testing in small and large samples; analysis of categorical data; analysis of variance; correlation and linear and nonlinear regression analysis; use of statistical software; illustrations using published articles in the biomedical sciences.

### BST 479 Generalized Linear Models

Prerequisites: BST 411 and BST 426.

Generalized linear models; computational techniques for model fitting; logistic and conditional logistic regression; Poisson and negative binomial regression; log-linear models; models for nominal and ordinal categorical data; quasi-likelihood functions; model checking; nonlinear regression models.

### BST 487 Seminar in Statistical Literature

Credits: 1

Provides an introduction to the process of searching the statistical literature, opportunities to acquire knowledge of a focused area of statistical research, experience in organizing, preparing, and delivering oral presentations, and an introduction to the research interests of members of the faculty.

### BST 491 Reading Course at the Master’s Level

Credits: Varies

Special work, arranged individually.

### BST 493 Capstone Project

Credits: 8

As required for completion of the MS degree in biostatistics, the student works on a medical research project under the guidance of department faculty. The student should have contact with medical investigators as well as statisticians. The work should be coherently summarized in a written document. Oral presentation of the work is required.

Credits: Varies

### BST 511 Topics in Statistical Inference I

Prerequisite: Varies by topic.

Advanced topics in statistical inference and/or decision theory.

### BST 512 Topics in Statistical Inference II

Prerequisite: Varies by topic.

Advanced topics in statistical inference and/or decision theory.

### BST 513 Analysis of Longitudinal and Dependent Data

Prerequisites: BST 401, BST 411, and BST 426.

Modern approaches to the analysis of longitudinal and dependent data; random and mixed effects models; marginal models; generalized estimating equations; models for continuous and discrete outcomes.

### BST 514 Survival Analysis

Prerequisites: BST 401, BST 411, and BST 412.

Parametric, nonparametric, and semiparametric methods for the analysis of survival data; right censoring; Kaplan-Meier curves; log-rank and weighted log-rank tests; survival distributions; accelerated life and proportional hazards regression models; time-dependent covariates; partial likelihood; models for competing risks and multiple events.

### BST 516 Causal Inference

Prerequisites: BST 401, BST 411, and BST 412.

Statistical methods for the design and analysis of observational studies; potential outcomes framework for causal inference; randomized experiments; matching, propensity score and regression methods for controlling confounding in observational studies; tests of hidden bias; sensitivity analysis; instrumental variables.

### BST 523 Advanced Bayesian Inference

Prerequisite: BST 413.

Computational aspects of Bayesian Inference, with a focus on the Metropolis-Hastings (MH) algorithm and its extensions; convergence diagnostics; missing data and data augmentation; simulation design; Hamiltonian Monte Carlo; hierarchical models; use of R and Stan software.

### BST 531 Nonparametric Inference

Prerequisites: BST 411, BST 412, and BST 426.

Nonparametric estimation and inference for one-sample location and paired data, two-sample location and/or dispersion, one- and two-way layouts with and without order restrictions, tests of independence, and regression; exact and large-sample results for some commonly used procedures, including the sign test and the sample median, the Mann-Whitney-Wilcoxon test and the Hodges-Lehmann location measure, and some generalizations to more complex data structures; density estimation; nonparametric regression; generalized additive models (GAM); cross-validation; bandwidth selection; exact and asymptotic bias, variance, and mean squared error (MSE).

### BST 536 Sequential Analysis

Prerequisite: BST 412.

The Wald sequential probability ratio test and generalizations; tests of composite hypotheses; nonparametric sequential procedures; sequential estimation and confidence intervals; Brownian-motion based sequential methods, with applications to clinical trials; group sequential methods; optimal stopping rules.

### BST 541 Multivariate Analysis

Prerequisites: BST 411 and BST 426.

Multivariate normal and Wishart distributions and associated distributions; estimation; invariance reduction; Hotelling’s T2; multivariate general linear model; simultaneous confidence bounds; step down procedures; optimality properties; classification; discrimination; principal components.

### BST 550 Topics in Data Analysis

Restriction: Permission of instructor.

Advanced statistical methods for data analysis.

### BST 570 Topics in Biostatistics

Restriction: Permission of instructor.

### BST 582 Introduction to Statistical Consulting

Restriction: Permission of instructor.

Formal instruction on developing and managing consulting relationships.

### BST 590 Supervised Teaching

Credits: Varies

One to two classroom hours per week of discussion and problem solving with University of Rochester students, under the guidance of a member of the faculty.

### BST 591 Reading Course at the PhD Level

Credits: Varies

Special work for doctoral candidates, arranged individually.

### BST 592 Supervised Statistical Consulting

Credits: Varies

Supervised consulting with medical and other scientific researchers under the guidance of a member of the faculty.

Credits: Varies