Graduate Course Directory and Schedules

The methods students learned in the biostatistical applied and theoretical sequences were based on the “frequentist” method of statistical reasoning, where probability is understood to be the long-run frequency of a ‘repeatable’ event, and statistics that are computed are based on a specific study only. Bayesian methods are based on a different philosophy – that probability of an event is based on ALL information known at the time. Bayesian methods for data analysis enable one to combine information from previous similar and independent studies (prior information), with information from a new study, yielding updated inference for model parameters. This course will cover the concept of Bayesian analysis, posterior distribution, Bayesian inference and prediction, prior determination, one parameter and two parameter models, Bayesian hierarchical models, Bayesian computation, model criticism and selection as well as basic comparison of Bayesian and Frequentist Inferences. Real life examples in medical and health science will be used to explain the concept and application of Bayesian models.

This course is designed for students who want to develop and expand their skills in data management, statistical analyses and graphics for the real world applications using SAS. After brief introduction, the course will cover intermediate to early advanced level programming skills in SAS. The class will be taught in a computer lab in order to give the student hand on experience using SAS to manage data, perform analyses and produce graphs. Class sessions and homework will be oriented around particular data management and analysis tasks. Health-related data sets will be provided for students to use. This course could be extremely helpful in preparation for thesis, capstone or other research projects.

Prerequisites:

1. BSTA 511/611 Estimation & Hypothesis Testing for Applied Biostatistics
2. BSTA 512/612 Linear Models

This course covers an experimental design and statistical analysis of biological/clinical data from various experiments. This course provides not only theoretical aspect of experimental design but also hand-on experience in designing and analyzing experiments. The course begins design principles that include concepts of replication, randomization, blocking, multifactor studies, and confounding. Basic matrix algebra concepts will be explored to establish the basis for linear models. Students, then, are introduced to various experimental designs including analysis of variance (ANOVA) in both single and multi-factorial setting, experiments to study variances, complete/incomplete block designs (CBD), split plot design, repeated measures ANOVA, analysis of covariance (ANOCOVA), response surface design, and diagnosing agreement between the data and model. The course also provides experience in analyzing unbalanced experimental. Computer application is included as part of the course to introduce students to data management, reading output, interpreting and summarizing results.

Prerequisites: BSTA 511/611 Estimation & Hypothesis Testing for Applied Biostatistics or equivalent.

This course is designed to introduce histroy, concepts and distributions in probability, Monte Carlo simulation techniques, and Markov chains. Students will also learn how to write R codes for various statistical computations and plots. Previous experience in R is not required. R is free software available from http://www.r-project.org.

Prerequisites: One year of calculus (2 semesters or 3 quarters).

This course introduces students to analysis of survival (i.e. time-to-event) data, covering methods for estimation, hypothesis testing, and regression methods for censored data with covariates.  Methods widely used in the health sciences are covered, including Kaplan-Meier (empirical) estimate of the survival function and its associated statistical tests. The Cox proportional hazards regression model is presented in detail, along with some extensions of this model. As time allows, other topics will be introduced including parametric survival models, frailty models and/or models incorporating competing risks.  Power and sample size computations for time-to-event data will also be introduced.  Most assignments will be completed using statistical computing software.  Contextualizing results in the context of health sciences problems and research questions is stressed throughout the course.

Prerequisites: 

A standard pre-calculus course in probability & statistics (e.g. BSTA 511)
A course in applied linear regression models (e.g. BSTA 512)
Calculus is preferred

The objectives of the two term sequence are to (1) provide students with fundamental principles for conducting statistical inference both via estimation and hypothesis testing and (2) develop the mathematical skills for applying these principles in new situations. In the first term we focus on principles of data reduction and estimation, but will also introduce hypothesis testing if time permits. In the second term we focus on hypothesis testing, interval estimation, and asymptotic results.

Prerequisites:

• BSTA 551 Statistical Inference I
• BSTA 550 Introduction to Probability
• Differential and integral calculus