| More information can be found by looking at the syllabi for past classes. Updated 11/3/03. |
|
This course introduces SAS software in lab-based format. SAS is the world's most widely used statistical package for managing and analyzing data. The objective of this course is for the student to develop the skills necessary to address data management and analysis issues using SAS. This course includees a complete introduction to data management for scientific and industrial data, an overview of SAS statistical procedures including statistical graphics, an introduction to SAS's macro capabilities for automating repeated analyses, and an introduction to IML Plus, SAS's recently released interface to its interactive matrix language. Prerequisite: Some exposure to introductory statistics or instructor permission. |
|
Matlab and a programming language (C/Fortran) will be used. Floating point arithmetic, numeric matrix analysis, multiple regression analysis, nonlinear optimization, root finding, numerical integration, Monte Carlo sampling. Prerequisite: At least one previous coarse in statistics above STA 1013; some previous programming experience; or permission of the instructor. |
|
Matlab and a programming language (C/Fortran) will be used. A continuation of STA 5106 in computational techniques for linear and nonlinear statistics. Statistical image understanding, elements of pattern theory, simulated annealing, Metropolis-Hastings algorithm, Gibbs sampling. Prerequisite: STA 5106 or permission of the instructor. |
|
Data collection, sample variation, basic probability, confidence intervals, hypothesis testing, analysis of variance, contingency tables, correlation, regression, nonparametric statistics. Prerequisite: MAC 1105 Special Note: Graduate credit for non-statistics majors only. |
|
Comparison of two treatments, random sampling, and randomization and blocking with two comparisons, statistical inference for means, variances, proportions and frequencies, and analysis of variance. Prerequisite: MAC 2313 |
|
Special designs in analysis of variance, linear and nonlinear regression, least squares and weighted least squares, case analysis, model building, non least squares estimation. Prerequisite: STA 5166 |
|
Response surface methods, repeated measures and split-plot designs, basic log-linear and logit models for two-way and multiway tables, and multinomial response models. Prerequisite: STA 5167 |
|
This course introduces students to the statistical methods used in studying the prevention of disease in human populations. Prerequisite: A previous course in statistics or instructor permission. |
|
Maximum likelihood principle, missing data and EM algorithm; assessment tools such as bootstrap and cross-validation; Markov chain and hidden Markov models; classification and regression tress (CART); Bayesian models and Markov Chain Monte Carlo algorithms.. Prerequisite: STA 4442 or 5440 |
|
This course is an applied introduction to survival analysis, one of the most commonly used analytic tools in biomedical studies. Topics to be covered include censoring and time scale, descriptive methods, parametric methods, and regression methods, which stress the proportional hazards model. Prerequisite: STA 2171 or permission of the instructor. |
|
This course covers fundamental methods of epidemiology for statisticians. With a focus on identification of risk factors for disease, topics include exposure-disease association, design of cohort, matched and randomized studies; cross-sectional and longitudinal studies; statistical analysis of data arising from such studies, confounding, adjustment and causality; and evaluation of diagnostic and screening tests. Prerequisite: STA 5167 and STA 5327 or instructor permission |
|
One and two-way classifications, nesting, blocking, multiple comparisons, incomplete designs, variance components, factorial designs, confounding. Prerequisite: One of STA 2122, 4322, 5126 or 5354. Special Note: Graduate credit for non-statistics majors only. |
|
General linear hypothesis, analysis of covariance, multiple correlation and regression, response surface methods. Prerequisite: One of STA 2122, 4322, 5126, or 5354. Special Note: Graduate credit for non-statistics majors only. |
|
Prerequisite: STA 5327 |
|
Simple stratified, systematic, and cluster random sampling. Ratio and regression estimation. Multistage sampling. Prerequisite: A course in statistics above STA 1013 or consent of instructor. |
|
This course is an applied introduction to logistic regression, one of the most commonly used analytic tools in biomedical studies. Topics include fitting the model, interpretation of the model, model building, assessing model fit, model validation, and model uncertainty. Prerequisite: Prerequisite: STA 2171 |
|
This course offers an introduction to clinical trials. Topics to be covered include defining the research question, basic study designs, randomization, blinding, sample size, baseline assessment, data collection and quality control, monitoring, issues in data analysis, closing out a trial, reporting and interpreting results, and issues in multicenter trials. Prerequisite: 2171 or permission of instructor. |
|
Distributions of random variables, conditional probability and independence, multivariate distributions, sampling distributions, Bayes' rule, counting problems, expectations. Prerequisite: MAC 2313 or equivalent. |
|
Sufficiency, point estimation, confidence intervals, hypothesis testing, regression, linear models, Bayesian models. Prerequisite: STA 4442 or 5440 and either MAC 2313 or STA 5326. |
|
Introduction to Probability, random variables, distributions, limit laws, conditional distributions, and expectations. Prerequisite: MAC 2313; at least one previous course in statistics or probability. |
|
Preferred Description: Sufficient statistics, complete statistics, ancillary statistics, method of moments, maximum likelihood estimation, Bayesian estimation, minimum variance unbiased estimates, Fisher information, asymptotic behavior of maximum likelihood estimates, hypothesis testing, the Neyman-Pearson lemma, and likelihood ratio tests. (Current Bulletin description: Statistical Inference viewed at a measure-theoretic level.) Prerequisite: Preferred prerequisites: STA 5326 or equivalent. (Bulletin prerequisites: STA 5326,5446.) |
|
Convergence of distribution and random variables, laws of large numbers, central limit theorems, asymptotic distributions, asymptotic efficiency, rates of convergence, the weak invariance principle. Prerequisite: STA 5327 |
|
Random variables, probability of random variables, generating functions, central limit theorem, laws of large numbers. Prerequisite: MAC 2311 |
|
Classes of sets, probability measures, construction of probability measures, random variables, expectation and integration, independence and product measures. Prerequisite: MAA 4227, 5307, or the equivalent. |
|
Prerequisite: STA 5326, STA 5446 |
|
Applications of nonparametric tests, estimates, confidence intervals, multiple comparison procedures, multivariate nonparametric methods, and nonparametric methods for censored data. Prerequisite: A course in statistics above STA 1013 or consent of instructor. |
|
This course is a hands-on introduction to statistical methods for supervised, unsupervised, and semi-supervised learning. It explores fundamental techniques including but not limited to Support Vector Machines, Decision Trees, Linear Discriminant Analysis, Random Forests, Neural Networks, and different flavors of Boosting. Prerequisite: Prerequisite: STA 3032 or instructor permission |
|
Statistics for quality control and productivity; graphical methods; control charts; acceptance sampling; design and experiment for product and process improvement. Prerequisite: STA 5167 or instructor permission, and either STA 4322 or 5126. |
|
Prerequisite: A basic course in probability and statistics. |
|
Inference about mean vectors and covariance matrices, canonical correlation, principal components, discriminant analysis, cluster analysis, computer techniques. Prerequisite: One of STA 5167, 5207, or 5327. |
|
Prerequisite: STA 5327 |
|
Prerequisite: STA 5326 Special Note: May be repeated to a maximum of twelve (12) semester hours. |
|
Autoregressive, moving average and mixed models, autocovariance and autocorrelation functions, model identification, forecasting techniques, seasonal model identification estimation and forecasting, intervention and transfer function model identification, estimation and forecasting. Prerequisite: STA 5126, QMB 3200, or equivalent. |
|
Special Note: (S/U grade only). May be repeated. |
|
Special Note: (S/U grade only.) May be repeated to a maximum of twelve (12) semester hours. A maximum of three (3) hours may apply to the master's degree |
|
Special Note: (S/U grade only.) May be repeated to a maximum of twelve (12) semester hours. |
|
Special Note: May be repeated to a maximum of twelve (12 )semester hours. |
|
This is a "hands-on" course in consulting. Two to four reasonably complex problems are identified each time the course is offered, the investigators present the problem to the class. Statistical topics covered in class are those identified by the class as required to solve the problems presented. Prerequisite: STA 2171 or permission of instructor. |
|
Formulation of statistical problems from client information; the analysis of complex data sets by computer; practical consulting experience. Prerequisite: STA 5167 or 5327. Special Note: (S/U grade only.) |
|
Special Note: (S/U grade only.) May be repeated to a maximum of twelve (12) semester hours. A maximum of three (3) hours may apply to the master's degree. |
|
(S/U grade only.) May be repeated to a maximum of five semester hours. A maximum of three hours may apply to the master’s degree. |
|
This course presents advanced methods for describing, analyzing, and modeling data from observational studies. The initial offering includes introductions to meta-analytic methods, bootstrap methods, and randomization tests. Topics vary with each offering. May be repeated up to a maximum of six semester hours. Prerequisite: STA 5167 and 5325 or permission of instructor. |
|
|
|
The course covers the basics of the probability theory, random elements, and stochastic processes; characteristic functions and probability inequalities; central limit theorems; elements of Markov dependence and martingale theory; common scholastic processes arising in biostatistics; advanced treatment of sufficient statistics, exponential families, estimation, and testing; as well as elements of asymptotic theory of statistical inference.
Prerequisite: STA 5326 and STA 5327 |
|
The course covers unbiased and locally most powerful tests (including the multiparameter case); envelope power function; best average power test; Bayes and empirical Bayes procedures; likelihood, quasi likelihood, and profile likelihood; order statistics and empirical distributions; general central limit theorems; variance stabilizing transformations; U-statistics; least squares, weighted least squares, and generalized least squares estimation; generalized estimating equations; asymptotic theory for BAN estimators; asymptotic theory for likelihood ratio, Wald, and score tests; log-linear models; asymptotics for linear inference; as well as robust statistical inference.
Prerequisite: STA5326 and STA5327 |
|
Prerequisite: STA 5447. |
|
Special Note: May be repeated to a maximum of twelve (12) semester hours. |
|
Estimation of regression and density functions and their derivatives where no parametric model is assumed. Kernel, local polynomial, spline, and wavelet methods. Emphasis on analysis and applications of the smoothing techniques, and data-based smoothing parameter selectors. Prerequisite: STA 5327 or consent of instructor. |
|
This course covers the most inclusive type of data analysis known in statistics; examples of such data in astronomy, biology, digital imagery, medical imaging, computer vision, pattern recognition, astrophysics, learning, Earth sciences including meteorology and geology; introduction to abstract manifolds, tangent bundles, embedding, Riemannian structures; sample spaces with a manifold structure; foundations of nonparametric statistics on manifolds: location and spread parameters for distributions on manifolds; large sample theory on manifolds, density, and function estimation on manifolds; nonparametric inference on manifolds; statistical analysis on special manifolds arising in statistics: directional and axial data analysis, projective, affine, and similarity shape data analyses, size-and-shape data analysis, diffusion tensor image analysis; concrete case studies in astronomy, image analysis, medical imaging: MRI, CT, Confocal Laser Tomography, eye imaging, brain imaging, bioinformatics, computer vision, and 3D scene recognition.
Prerequisite: One of STA 5707, STA 5327, STA 5746. |
|
Familiarity with S-Plus or SAS software. Methods for the analysis of spatial data, including geostatistical data, lattice data, and point patterns. Theory and applications of basic principles and techniques. Prerequisite: STA 5208, 5327. |
|
Special Note: (S/U grade only.) May be repeated. |
|
|
|
|
|
|
|
|