39 courses with the subject BST, each shown exactly as we captured it from the college's catalog, with every element we hold. Where the wording looks broken, that is our reading of the catalog, not the college's text.
BST 522Introduction to Probability for Biostatistics3.0
Probability for biostatistics is a course designed to introduce students to the concepts of probability, uncertainty, and randomness. The course covers probability topics, including, but not limited to: discrete and continuous distributions, expectations, generating functions, limit theorems, transformations, and sampling theory. In addition to the theoretical aspects of these topics, there will also be an emphasis on applying these concepts to applications within the field of biostatistics and public health studies more broadly.
The objective of this course is to introduce students to the fundamental concepts and methods of statistical inference. Topics include: point and interval estimation, methods of moments, maximum likelihood estimation, Bayes estimates, hypothesis testing, Neyman-Pearson lemma, likelihood ratio tests and large sample approximation.
Longitudinal data measure characteristics on the experimental units repeatedly over time. It is an essential design to study temporal change and to establish causal relationships. The analysis of longitudinal data requires sophisticated methodologies due to the correlation introduced by repeated measurements. This course covers modern statistical techniques for longitudinal data from an applied perspective.
Research projects often involve the management and manipulation of complicated sets of data. This course is designed to introduce the student to practical issues in the management and analysis of health and pharmaceutical data using the SAS programming language. Data from a variety of public health and biomedical applications will be used throughout the course to illustrate the principles of data management and analysis for addressing biomedical and health-related hypotheses.
This course covers the basic techniques of survival analysis. These approaches are useful in analyzing cohort data, which are common in health studies, when the main interest outcome is the onset of event and time to event is known. The response is often referred to as failure time, survival time, or event time, and this course will introduce students to methods necessary for analyzing this type of data.
This course introduces students to statistical methods for describing and analyzing multivariate data. Topics to be covered include basic matrix algebra, multivariate normal distribution; linear models with multivariate response, multivariate analysis of variance; profile analysis, dimension reduction techniques, including principle component analysis, factor analysis, canonical correlation, multidimensional scaling; discriminate/cluster analysis; and classification/regression trees.
This course is designed to teach students the art of data management. The focus of the course is the application of prior coursework, specifically methodological courses in epidemiology and biostatistics, to issues in data management and analysis. Issues in data management are typically specific to study design and analysis and, as such, methods to handle data will focus on the many ways variables may be operationalized to answer research questions. The course will cover a number of topics and aims to provide a language of data that will allow the students who complete the course to tackle any methodological data issue they may encounter in the future.
This course is an overview of statistical models and analysis tools commonly used in epidemiological and public health studies. Topics include simple and multiple linear regression, diagnostics, model-building and remedial measures for regression models, analysis of variance, logistic and conditional logistic regression, and models for multi-category outcome data. Statistical software SAS will be an integral part of the course. Familiarity with SAS (or other statistical software) is expected.
In this course, we will introduce the process of performing a clinical trial, including introducing the different phases of study, the approaches to data management for trials, interim analyses and adaptive clinical trials, sample size calculations for clinical trials, and issues of safety in trials. Students will have the opportunity to learn the process of designing, implementing, running and analyzing a clinical trial using real examples.
This course introduces students to the fundamental aspects of statistical consulting and provides training on being an effective statistical consultant and collaborator. This course will provide strategies to help students translate their technical training and knowledge to the ‘statistical expert’ role often required/assumed in collaborative settings. Topics for the course will include, but are not limited to: understanding roles and responsibilities of biostatisticians in collaboration with scientists, practicing oral and written communication skills, understanding sample size and power calculations research, exploring how study design informs the statistical analytic plan, and developing strategies for helping researchers formulate scientific questions into quantifiable measures.
The objective of this course is to introduce students to the fundamental concepts and applicable techniques of non-parametric and semi-parametric models, in particular, nonlinear functional relationships in regression analyses. Topics tentatively selected include: Density estimation, smoothing, non-parametric regression, additive models, semi-parametric mixed models, and generalized additive models.
The objective of this course is to introduce students to linear regression models (computation, theoretical properties, model interpretation and application). Topics include: Review of basic concepts of matrix algebra that are particularly useful in linear regression, and basic R programing features; (weighted) least square estimation, inference and testing; regression diagnostics, outlier influence; and variable selection and robust regression. Knowledge of calculus 1, calculus 2, and linear algebra required.
The objective of this course is to introduce students to generalized linear regression models (theoretical properties, model interpretation and application). Topics include: 1) Review of categorical data and related sampling distributions; 2) Two/Three-way contingency tables; 3) logistic regression and Poisson regression; 4) loglinear models for contingency tables; 5) generalized linear mixed models for categorical responses; 6) principles of MLE in generalized linear model.
Introduction to Biostatistics provides students with an understanding of the methods of biostatistics, applicable to epidemiological and clinical studies. It emphasizes concepts and application of statistical and epidemiological thinking. Basic statistical theory, parametric statistics, correlation, regression, ANOVA, non-parametric statistics, and methods in discrete statistical analysis, along with other quantitative methods including screening tests, will be introduced. This course will emphasize hands-on experience in statistical analysis and interpretation of data from epidemiological studies.
The course provides a practical introduction to Bayesian statistical inference, which is now at the core of many advanced methods. The course will compare traditional frequentist estimation, which relies on maximization methods, to Bayesian estimation of the posterior distribution. Students will learn numerical integration methods, such as Markov chain Monte Carlo, to obtain these various distributions and ultimately make inference in a Bayesian framework. The course will also use the freely available statistical software packages, R (http://cran.r-project.org/) and WinBUGS (https://www.mrc-bsu.cam.ac.uk/software/bugs/the-bugs-project-winbugs/).
The course builds on material from Intermediate Biostatistics I, introducing additional core biostatistical methods such as Poisson and negative binomial regression, random and mixed effects models, survival analysis techniques, and nonparametric methods. We will focus on exploratory data analysis, model building, model checking, and diagnostics, developing a flexible, critical approach to statistical data analysis.
This course builds on the knowledge gained in BST 561, in order to develop a more thorough understanding of the basic methodology behind important statistical concepts used in the design and analysis of large, randomized clinical trials. The class will involve discussions of publications dealing with current topics of interest in clinical trials. Each student will also be asked to conduct, summarize, and present a course project based on a more in-depth exploration of one of the topics BST 561.
The course provides an overview of the underlying theory of and some advanced applications of Bayesian statistical inference. In particular, the course will cover topics such as Bayesian model selection while emphasizing modern computing techniques. The course will use the freely available statistical software package, R (http://cran.r-project.org/).
This course is a continuation of Biostatistics Theory I. The objective of this course is to introduce students to the fundamental concepts and methods of statistical inference. Topics include: point and interval estimation, methods of moments, maximum likelihood estimation, Bayes estimates, hypothesis testing, Neyman-Pearson lemma, likelihood ratio tests and large sample approximation; Bayesian analysis.
This course prepares students to collaborate as biostatisticians for public health and biomedical projects with non-statisticians. Students will learn the practical aspects of statistical collaboration through various hands-on experiences that facilitate student’s understanding of the roles and responsibilities of biostatisticians in the context of collaborating with interdisciplinary scientists. Students will engage in stages of proposal development by refining quantitative aims for a grant proposal, developing the data management and analysis plans, and conducting the power analysis. They will also develop a scope of work and billing for the biostatistician's participation if/once the grant is funded. Students will be exposed to IRB, data use agreements, human protection training, and data privacy.
This course builds on the skillset and knowledge presented in BST 567/867 and BST 675/875 by creating an experience(s) that nurture critical thinking and interpersonal skills combined with understanding interdisciplinary content and applying statistical knowledge to excel as a biostatistician collaborator. Students will become members of the Biostatistics Scientific Collaboration Center (BSC) and work in close collaboration with BSC personnel and a non-statistician investigator. True to real-life experiences in interdisciplinary collaboration, types of student experiences (e.g. power analysis, development of analysis plan, execute analysis plan) will vary depending on the BSC deliverables for each investigator’s project.
Subject
BST
Credits (min)
3
Credits (max)
3
Credit unit
Credits
Type
course
Repeatable
Can be repeated multiple times for credit Prerequisites: BST 675 [Min Grade: CR]
Provides the student with experience completing a substantive data analysis in either an academic or applied setting. The project will be performed over a full term under the supervision of the advisor. Projects based in settings outside the Department are jointly-supervised by the advisor and a doctorally prepared host organization researcher.
This course expands on computational methods used in biostatistics. It covers numerical techniques, programming, and simulations and will connect these to fundamental concepts in probability and statistics. The course will use the statistical software, R, to apply these concepts and enable the practical application of biostatistical models to real-world problems.
The objective of this course is to introduce students to the fundamental concepts and methods of statistical inference. Topics include: point and interval estimation, methods of moments, maximum likelihood estimation, Bayes estimates, hypothesis testing, Neyman-Pearson lemma, likelihood ratio tests and large sample approximation.
The course provides a practical introduction to Bayesian statistical inference, which is now at the core of many advanced methods. The course will compare traditional frequentist estimation, which relies on maximization methods, to Bayesian estimation of the posterior distribution. Students will learn numerical integration methods, such as Markov chain Monte Carlo, to obtain these various distributions and ultimately make inference in a Bayesian framework. The course will also use the freely available statistical software packages, R (http://cran.r-project.org/) and WinBUGS (https://www.mrc-bsu.cam.ac.uk/software/bugs/the-bugs-project-winbugs/).
BST 819Statistical Machine Learning for Biostatistics3.0
This course is a survey of statistical learning methods and will cover major techniques and concepts for both supervised and unsupervised learning. Topics include penalized regression and classification, support vector machines, kernel methods, model selection, clustering, boosting, CART and random forests, and ensemble learning. Students will learn how and when to apply statistical learning techniques, their comparative strengths and weaknesses, how to critically evaluate the performance of learning algorithms, and principles for appropriate application to health science problems. The statistical programming language R will be used throughout.
The course builds on material from Intermediate Biostatistics I, introducing additional core biostatistical methods such as Poisson and negative binomial regression, random and mixed effects models, survival analysis techniques, and nonparametric methods. We will focus on exploratory data analysis, model building, model checking, and diagnostics, developing a flexible, critical approach to statistical data analysis.
BST 823Theory of Generalized Linear and Mixed Models3.0
This course is an advanced doctoral course, intended to familiarize students with both the theory and applications of the generalized linear and mixed models. The first third of the course will be devoted to the study of the generalized linear model. The remainder of the course will be devoted to the study of models for correlated data; in particular, we will discuss the theory and applications of the linear mixed model. If time permits, generalized estimating equations (GEEs) and generalized linear mixed models (GLMM) will be introduced.
BST 825Probability Models and Stochastic Processes3.0
This course introduces basic concepts of stochastic processes. The focus of the course is on the principal stochastic or random processes most commonly used in applications as mathematical models of random phenomena that evolve over time. Topics tentatively selected include: Review of conditional probability, conditional expectation, and generating functions; Markov chains in discrete time; Poisson processes; renewal processes; Markov chains in continuous time; Brownian motion and Gaussian processes. These types of processes are fundamental to modeling time-dependent random phenomena in many areas of medical and health sciences. The emphasis will be on developing a sound understanding of the material, and many of the examples of the methods will be in the area of public health and bioinformatics.
This course introduces doctoral students in Biostatistics to research skills necessary for writing and defending a dissertation, and more generally, for a career in research. The format and topics will vary from week-to-week. Students will be given assignments to reinforce skills presented in the class.
This course introduces doctoral students in Biostatistics to research skills necessary for writing and defending a dissertation, and more generally, for a career in research. The format and topics will vary from week-to-week. Students will be given assignments to reinforce skills presented in the class.
This course introduces doctoral students in Biostatistics to research skills necessary for writing and defending a dissertation, and more generally, for a career in research. The format and topics will vary from week-to-week. Students will be given assignments to reinforce skills presented in the class.
This course is a continuation of Biostatistics Theory I. The objective of this course is to introduce students to the fundamental concepts and methods of statistical inference. Topics include: point and interval estimation, methods of moments, maximum likelihood estimation, Bayes estimates, hypothesis testing, Neyman-Pearson lemma, likelihood ratio tests and large sample approximation; Bayesian analysis.
This course introduces students to the fundamental aspects of statistical consulting and provides training on being an effective statistical consultant and collaborator. This course will provide strategies to help students translate their technical training and knowledge to the ‘statistical expert’ role often required/assumed in collaborative settings. Topics for the course will include, but are not limited to: understanding roles and responsibilities of biostatisticians in collaboration with scientists, practicing oral and written communication skills, understanding sample size and power calculations research, exploring how study design informs the statistical analytic plan, and developing strategies for helping researchers formulate scientific questions into quantifiable measures.
The objective of this course is to introduce students to linear regression models (computation, theoretical properties, model interpretation and application). Topics include: Review of basic concepts of matrix algebra that are particularly useful in linear regression, and basic R programing features; (weighted) least square estimation, inference and testing; regression diagnostics, outlier influence; and variable selection and robust regression. Knowledge of calculus 1, calculus 2, and linear algebra required.
The objective of this course is to introduce students to generalized linear regression models (theoretical properties, model interpretation and application). Topics include: 1) Review of categorical data and related sampling distributions; 2) Two/Three-way contingency tables; 3) logistic regression and Poisson regression; 4) loglinear models for contingency tables; 5) generalized linear mixed models for categorical responses; 6) principles of MLE in generalized linear model.
This course prepares students to collaborate as biostatisticians for public health and biomedical projects with non-statisticians. Students will learn the practical aspects of statistical collaboration through various hands-on experiences that facilitate student’s understanding of the roles and responsibilities of biostatisticians in the context of collaborating with interdisciplinary scientists. Students will engage in stages of proposal development by refining quantitative aims for a grant proposal, developing the data management and analysis plans, and conducting the power analysis. They will also develop a scope of work and billing for the biostatistician's participation if/once the grant is funded. Students will be exposed to IRB, data use agreements, human protection training, and data privacy.
This course builds on the skillset and knowledge presented in BST 567/867 and BST 675/875 by creating an experience(s) that nurture critical thinking and interpersonal skills combined with understanding interdisciplinary content and applying statistical knowledge to excel as a biostatistician collaborator. Students will become members of the Biostatistics Scientific Collaboration Center (BSC) and work in close collaboration with BSC personnel and a non-statistician investigator. True to real-life experiences in interdisciplinary collaboration, types of student experiences (e.g. power analysis, development of analysis plan, execute analysis plan) will vary depending on the BSC deliverables for each investigator’s project.
Subject
BST
Credits (min)
3
Credits (max)
3
Credit unit
Credits
Type
course
Repeatable
Can be repeated multiple times for credit Prerequisites: BST 875 [Min Grade: CR]
Directed guidance of dissertation research, preparation for presenting dissertation research to colleagues at the dissertation seminar and preparation for the final defense.
