Courses
The descriptions below are taken from the Berkeley campus General Catalog and include courses given in Biostatistics at the School of Public Health. Not every course listed here is given in each academic year.
Descriptions of courses in Statistics are viewable from the Department of Statistics web site.
Public Health (PB HLTH) 140
Introduction to Risk and Demographic Statistics (4 units)
Course Format: 3 hours of lecture & 1 hour of discussion per week.
Prerequisites: One year of calculus.
Statistical and evaluation methods in studies of human mortality, morbidity, and natality. History of statistical terminology and notation, critical appraisal of registry and census data, measurement of risk, and introduction to life tables. Computational systems and the analysis of mass data. (Fall) Tarter
Public Health (PB HLTH) 141
Introduction to Biostatistics (5 units)
Course Format: 12 1/2 hours of lecture & 7 1/2 hours of lab per week.
An intensive introductory course in statistical methods used in applied research. Emphasis on principles of statistical reasoning, underlying assumptions, and careful interpretation of results. Topics covered: descriptive statistics, graphical displays of data, introduction to probability, expectations and variance of random variables, confidence intervals and tests for means, differences of means, proportions, differences of proportions, chi-square tests for categorical variables, regression and multiple regression, an introduction to analysis of variance. Statistical software will be used to supplement hand calculation. Offered through Berkeley Summer Sessions. (Summer) Lahiff
Public Health (PB HLTH) 142
Introduction to Probability and Statistics in Biology and Public Health
(4 units)
Course Format: 3 hours of lecture & 2 hours of discussion per week
Prerequisites: High school algebra
Descriptive statistics, probability, probability distributions, point and interval estimation, hypothesis testing, chi-square, correlation and regression with biomedical applications. (Fall) Selvin
Public Health (PB HLTH) C143
Introduction to Statistical Methods in
Computational and Genomic Biology (4 units)
Course Format: 3 hours of lecture & 1 hour of lab per week.
Prerequisites: PH 142, Stat 134, Stat 135 or consent of instructor.
This course provides an introduction to statistical and computational methods for the analysis of biomedical and genomic data. Statistical topics, introduced in a biological context, include numerical and graphical summaries of data; basic notions in probability; loss-based estimation (e.g., least-squares regression, maximum likelihood estimation); model selection; multiple hypothesis testing; Markov chains; hidden Markov models, resampling; simulation studies. Biological questions considered include, but are not limited to, modeling meiosis; genetic mapping; nucleotide and protein-sequence analysis; molecular evolution; computational gene finding; and DNA microarray experiments. The course also introduces statistical computing resources for the analysis of biological data, with emphasis on the R language and environment (www.r-project.org) and bioconductor packages (www.bioconductor.org). In addition, the course introduces basic notions in genetics and molecular biology and involves the critical reading of articles related to statistical analyses in the biological and medical sciences. Also listed as Statistics C143. (Spring) Dudoit
Public Health (PB HLTH) 145
Statistical Analysis of Continuous Outcome data (4 units)
Course Format: 3 hours of lecture & 2 hours of lab/discussion per week
Prerequisites: PH 142 or equivalent
Regression models for continuous outcome data: least squares estimates and their properties, interpreting coefficients, prediction, comparing models, checking model assumptions, transformations, outliers, and influential points. Categorical explanatory variables: interaction and analysis of covariance, correlation and partial correlation. Appropriate graphical methods and statistical computing. Analysis of variance for one- and two-factor models: F tests, assumption checking, multiple comparisons. Random effects models and variance components. Introduction to repeated measures models. (Spring) Lahiff
Public Health (PB HLTH) C240A
Biostatistical Methods: Advanced Categorical Data Analysis (4 units)
Course Format: 3 hours of lecture & 2 hours of lab per week.
Prerequisites: Statistics 200A (may be taken concurrently)
This course focuses on statistical methods for discrete data collected in public health, clinical and biological studies. Lectures topics include proportions and counts, contingency tables, logistic regression models, Poisson regression and log-linear models, models for polytomous data and generalized linear models. Computing techniques, numerical methods, simulation and general implementation of biostatistical analysis techniques with emphasis on data applications. Also listed as Statistics C245A. Offered odd-numbered years. (Fall) Staff
Public Health (PB HLTH) C240B
Biostatistical Methods: Survival Analysis and Causality (4 units)
Course Format: 3 hours of lecture & 2 hours of lab per week.
Prerequisites: Statistics 200B (may be taken concurrently)
Analysis of survival time data using parametric and non-parametric models, hypothesis testing, and methods for analyzing censored (partially observed) data with covariates. Topics include marginal estimation of a survival function, estimation of a generalized multivariate linear regression model (allowing missing covariates and/or outcomes), estimation of a multiplicative intensity model (such as Cox proportional hazards model) and estimation of causal parameters assuming marginal structural models. General theory for developing locally efficient estimators of the parameters of interest in censored data models. Computing techniques, numerical methods, simulation and general implementation of biostatistical analysis techniques with emphasis on data applications. Also listed as Statistics C245B.
Offered odd-numbered years. (Spring) van der Laan
Public Health (PB HLTH) C240C
Biostatistical Methods: Computational Techniques with Applications to Observational Survival Data (4 units)
Course Format: 3 hours of lecture & 2 hours of lab per week.
Prerequisites: Statistics 200A or equivalent (may be taken concurrently)
An introduction to computational techniques commonly used in a variety of biostatistical applications: Newton, scoring, and EM algorithms for maximization; smoothing methods; bootstrapping; trees and neural networks; clustering; isotonic regression; Markov chain Monte Carlo methods. Lecture topics illustrated on simple data structures that arise in observational survival analysis and genomics, and other biostatistical applications. Also listed as Statistics C245C.
Offered even-numbered years. (Fall) Staff
Public Health (PB HLTH) C240D
Biostatistical Methods: Applications of Statistics to
Genetics and Molecular Biology (4 units)
Course Format: 3 hours of lecture & 2 hours of lab per week.
Prerequisites: Statistics 200A,B (may be taken concurrently) or consent of instructor
This course surveys applications of probability and statistics to genetics and molecular biology. Biological questions of interest include modeling meiosis, genetic mapping, nucleotide and protein sequence analysis, DNA microarray experiments, and biological metadata analysis. Related statistical topics include numerical and graphical summaries of data, stochastic processes, experimental design, loss-based estimation, multiple hypothesis testing, resampling, and simulation studies. The course discusses statistical computing resources for the analysis of biological data, with emphasis on the R language and environment (www.r-project.org) and Bioconductor software packages (www.bioconductor.org). It also provides an introduction to basic notions in genetics and molecular biology and involves the critical reading of articles related to statistical analyses in the biological and medical sciences. Also listed as Statistics C245D.
Offered even-numbered years. (Spring) Dudoit
Public Health (PB HLTH) 241
Statistical Analysis of Categorical Data (4 units)
Course Format: 3 hours of lecture & 2 hours of discussion/lab per week.
Prerequisites: PH 142 or consent of instructor.
Biostatistical concepts and modeling relevant to the design and analysis of multifactor population-based cohort and case-control studies, including matching. Measures of association, causal inference, confounding interaction. Introduction to binary regression, including logistic regression. (SP) Staff
Public Health (PB HLTH) 242A
Biometrical Data Analysis:
Pathological Incomplete Data and Pattern Recognition (4 units)
Course Format: 3 hours of lecture & 2 hours of discussion per week.
Prerequisites: PH 142, PH 145 or equivalent, or consent of instructor.
Survey of classical methods; mixture, clustered, grouped, incomplete, Cox-model, and truncated data simulation and analysis.
Offered odd-numbered years. (Spring) Tarter
Public Health (PB HLTH) 242B
Biometrical Data Analysis--Model Free Curve Estimation (4 units)
Course Format: 3 hours of lecture & 2 hours of discussion per week.
Prerequisites: PH 142, PH 145 or equivalent or consent of instructor.
Generalized histograms and Gram-Charlier expansions; series inclusion and stopping rules, multiplier and weighting techniques, nonparametric regression, variance reduction, smoothing, and equiprobability contour estimation methods and other graphical methods.
Offered even-numbered years. (Spring) Tarter
Public Health (PB HLTH) C242C
Longitudinal Data Analysis (4 units)
Course Format: 3 hours of lecture & 2 hours of discussion per week.
Prerequisites: PH 142, PH 145, PH241 or equivalent courses in
basic statistics, linear and logistic regression.
The course covers the statistical issues surrounding estimation of effects using data on subjects followed through time. The course emphasizes a regression model approach and discusses disease incidence modeling and both continuous outcome data/linear models and longitudinal extensions to nonlinear models (e.g., logistic and Poisson). The primary focus is from the analysis side, but mathematical intuition behind the procedures will also be discussed. The statistical/mathematical material includes some survival analysis, linear models, logistic and Poisson regression, and matrix algebra for statistics. The course will conclude with an introduction to recently developed causal regression techniques (e.g., marginal structural models). Time permitting, serially correlated data on ecological units will also be discussed. Also listed as Statistics C247C.
Offered even-numbered years. (Spring) Hubbard/Jewell
Public Health (PB HLTH) 243A
Special Topics in Biostatistics (1-3 units)
Course Format: 1~3 hours of lecture/discussion per week.
Current issues in biostatistics research. Topics will vary from term to term depending on student demand and faculty availability. Possible topics are bioassay, meta-analysis, compartmental models, biostatistical consulting, covariance structure models, bootstrap and jackknife methods, artificial intelligence techniques in biostatistics.
(Fall, Spring) Staff
Public Health (PB HLTH) 243B
Special Topics in Biostatistics (1-3 units)
Course Format: 1~3 hours of lecture/discussion per week.
Current issues in biostatistics research. Topics will vary from term to term depending on student demand and faculty availability. Possible topics are multivariate methods in genomics, bioassay, meta-analysis, compartmental models, biostatistical consulting, covariance structure models, bootstrap and jackknife methods, artificial intelligence techniques in biostatistics. (Fall, Spring) Staff
Public Health (PB HLTH) 243C
Information Systems in Public Health (2 units)
Course Format: 2 hours of lecture/discussion per week
An introduction to new information systems, such as the Internet and interactive television, and how they may be used to improve human health. The course has three objectives: first, to familiarize students with new information technologies; second, to review how these technologies will be used by public health professionals, consumers, health care providers, and others; and third, to study related ethical and legal issues such as privacy, access, and liability. The course is designed for people with minimal understanding of interactive technologies. (Spring) Van Brunt
Public Health (PB HLTH) 243D
Special Topics in Biostatistics: Adaptive Designs (3 units)
Course Format: 3 hours of lecture per week
This course examines the theory and statistical methods for analyzing data generated by adaptive group sequential designs. It also considers the construction of targeted adaptive group sequential designs that adapt in a way that is optimal for the estimation of a particular target feature of the data generating experiment (i.e., causal effect of the treatment). Topics to be covered include: sequential testing, adaptive sample size, martingale estimating functions to construct estimators, targeted maximum likelihood estimation for adaptive designs, targeted Bayesian learning for adaptive designs, martingale theory for the analysis of estimators for adaptive designs.
Offered even-numbered years. (Fall) Van der Laan
Public Health (PB HLTH) 244A
Stochastic Processes in Biology and Health (3 units)
Course Format: 3 hours of lecture per week.
Prerequisites: A course in linear algebra, or consent of instructor.
Discrete time processes. Topics include probability generating functions; branching process, random walk, and ruin problem; Markov chains; renewal processes and applications in biology and health. Offered odd-numbered years. (Fall) Chiang
Public Health (PB HLTH) 244B
Stochastic Processes in Biology and Health (3 units)
Course Format: 3 hours of lecture per week.
Prerequisites: PH 244A, a course in differential equations, or consent of instructor.
Continuous time processes. Topics include the Poisson processes; birth processes, death processes, migration processes, a general birth process; a stochastic model of epidemics; birth-death processes; queueing processes; Neyman-Fix processes; survival and stages of disease; finite Markov processes; and illness-death processes.
(Spring) Chiang
Public Health (PB HLTH) 245
Introduction to Multivariate Statistics (4 units)
Course Format: 3 hours of lecture & 2 hours of lab per week.
Prerequisites: PH 145 or equivalent or consent of instructor.
The following topics are discussed in the context of biomedical and biological application: multiple regression, loglinear models, discriminant analysis, principal components. Instruction in statistical computing is given in the laboratory session. (Fall) Lahiff
Public Health (PB HLTH) 246A
Censored Longitudinal Data and Causality (4 units)
Course Format: 3 hours of lecture & 2 hours of lab per week.
Prerequisites: Statistics 200A&B and PH 240B or consent of instructor
This course examines optimal robust methods for statistical inference regarding causal and non-causal parameters based on longitudinal data in the presence of informative censoring and informative confounding of treatment. Models presented include multivariate regression models, multiplicative intensity models for counting processes and causal models such as marginal structural models and structural nested models. Methods will be illustrated with data sets of practical interest and analyzed in the laboratory section. This course, appropriate for advanced masters and Ph.D. students, provides exposure to a number of ongoing research topics. Offered even-numbered years.
(Sp) van der Laan
Public Health (PB HLTH) 248
Statistical/Computer Analysis Using R (3 units)
Course Format: 2 hours of lecture per week.
Prerequisites: Stat 200A (may be taken concurrently) or
PH 142, PH 145, & PH 245.
The material presented will focus on learning the programming language R, which will be taught in the context of reviewing and introducing a number of statistical methods. Four topic areas will be presented with the focus on implementation; these are descriptive methods, simulation techniques, linear models, and estimation. The goal of the course is to provide a package of statistical techniques along with new and advanced computer tools for implementation. (Fall) Selvin
