STATISTICS (STA) COURSE DESCRIPTIONS
5073 Methods of Statistics I
(3-0) 3 hours credit. Prerequisite: STA 1053.
Emphasis on methods and applications of statistics. Measure of location, variability, and association. Interpretation of categorical data, hypothesis testing, and use of SAS programs and applications. Cannot be applied to a Master of Science degree in Applied Statistics.
5083 Methods of Statistics II
(3-0) 3 hours credit. Prerequisite: STA 5073.
A continuation of STA 5073, with emphasis on linear statistical models. Use of SAS programs and applications. Topics in applied statistics may include maximum likelihood estimation and its properties, and likelihood ratio tests. Procedures in regression and model fitting, transformations of data, analysis of variance, and others. Cannot be applied to a Master of Science degree in Applied Statistics.
5093 Introduction to Statistical Inference
(3-0) 3 hours credit. Prerequisite: Admission to the M.S. program or consent of instructor.
Statistical concepts in estimation and hypothesis testing; methods for one-sample, two-sample, and categorical data problems. Probability distributions, random variables, expectation, and independence; point estimation and confidence intervals, with small and large-sample procedures; hypothesis testing and statistical decision; goodness-of-fit tests and nonparametric tests.
5103 Applied Statistics
(3-0) 3 hours credit. Prerequisite: STA 5093 or consent of instructor.
Simple linear model, correlation, multiple regression, one-way analysis of variance, fixed effects model, random effects model, mixed effects model, model selection, and analysis of covariance.
5133 Advanced Programming and Data Management in SAS
(3-0) 3 hours credit. Prerequisite: Admission to the M.S. program or consent of instructor.
Essential programming concepts using SAS software will be discussed, with a focus on data management and the preparation of data for statistical analysis. Efficient programming techniques including macros and arrays will be introduced. Topics include reading raw data, creating temporary and permanent data sets, manipulating data sets, summarizing and displaying data using tables, charts, and plots. A final presentation will be required. (Formerly titled “Data Analysis with Statistical Software.”)
5213 Advanced Statistical Quality Control
(3-0) 3 hours credit. Prerequisite: EGR 5093 or consent of instructor.
Methods and techniques for process control, process and gage capability analyses, inspection plans, American National Standards, and recent advanced techniques. Use of statistical software including JMP. Tour of manufacturing industry. Case studies in process control outgoing quality and costs. A required project, assigned by a manufacturing company, must be presented. This course is designed for technology managers and engineers and cannot be applied to a Master of Science degree in Applied Statistics.
5233 Product and Manufacturing Reliability
(3-0) 3 hours credit. Prerequisite: EGR 5093 or consent of instructor.
Topics include product and manufacturing reliability from managerial, engineering, and statistical perspectives. Emphasis on component and system reliability estimation, testing, and demonstration. Advanced topics such as accelerated life tests, Bayesian procedures, system availability, system maintainability, and compliance with international standards are addressed. Methods and theory are supported through data analytic packages such as JMP, SAS, and S-Plus. This course is designed for technology managers and engineers and cannot be applied to a Master of Science degree in Applied Statistics.
5253 Applied Time Series Analysis
(3-0) 3 hours credit. Prerequisite: STA 5093 or consent of instructor.
Modern techniques for time series analysis and their applications. Principles of model building. Regression methods, moving averages, and autoregressive integrated moving average models. Practical examples drawn from various application environments. Use of software such as MINITAB, SAS, and S-Plus in time series analysis.
5313 Theory of Sample Surveys with Applications
(3-0) 3 hours credit. Prerequisite: STA 5093 or consent of instructor.
Basic sampling techniques and their comparisons for finite populations. Topics include simple random sampling, stratified sampling, ratio and regression estimates, systematic sampling, cluster sampling, multistage and double sampling, and bootstrap and other sampling plans.
5413 Nonparametric Statistics
(3-0) 3 hours credit. Prerequisite: STA 5093 or consent of instructor.
Order statistics, test of goodness of fit, rank-order statistics, linear rank statistics for problems involving location and scale, association in multiple classifications, and asymptotic relative efficiency.
5503 Mathematical Statistics I
(3-0) 3 hours credit. Prerequisite: Admission to the M.S. program or consent of instructor.
Axioms of probability, random variables and probability distributions, sampling distributions, and stochastic convergence.
5513 Mathematical Statistics II
(3-0) 3 hours credit. Prerequisite: STA 5503.
Sufficient statistics, unbiased estimation, likelihood ratio test, sequential probability ratio test, and decision theory.
5803 Process Control and Acceptance Sampling
(3-0) 3 hours credit. Prerequisite: STA 5093 or consent of instructor.
Introduction to statistical process control and product inspection plans. Topics include control charts by attributes and variables, special control charts, specification limits, process capability, and acceptance sampling plans by attributes and variables. Use of statistical software.
5813 Applied Multivariate Statistics
(3-0) 3 hours credit. Prerequisites: MAT 2233 and either STA 5093 or consent of instructor.
Principal components, factor analysis, cluster analysis, multidimensional scaling, discriminant analysis, multivariate normal distribution, estimation of mean vector and covariance matrix, Hotelling’s T2, and tests concerning covariance matrices.
5853 Analysis of Categorical Data
(3-0) 3 hours credit. Prerequisite: STA 5093 or consent of instructor.
Types of categorical data, cross-classification of tables, tests for independence, measures of association, loglinear models for multidimensional tables. Logit models and analogies with regression. Specialized methods for ordinal data.
5903 Survival Analysis
(3-0) 3 hours credit. Prerequisite: STA 5093 or consent of instructor.
This course introduces both parametric and nonparametric methods for analyzing censored survival data. Topics include Kaplan-Meier estimator, inference based on standard lifetime distributions, regression approach to survival analysis including the proportional hazards model. Emphasis on application and data analysis using SAS and S-Plus.
5973 Directed Research
3 hours credit. Prerequisites: Graduate standing and permission in writing (form available) of the instructor and the student’s Graduate Advisor of Record.
The directed research course may involve either a laboratory or a theoretical problem. May be repeated for credit, but not more than 6 hours, regardless of discipline, will apply to the Master’s degree.
6013 Regression Analysis
(3-0) 3 hours credit. Prerequisite: STA 5103 or consent of instructor.
Model selection methods, model validation, diagnostics, outlier detection, autocorrelated data, multicollinearility, cross validation, transformation of data, and generalized linear regression models.
6023 Mathematical Methods in Statistics
(3-0) 3 hours credit. Prerequisite: Admission to the M.S. program or consent of instructor.
Topics include concepts of limits, sequences and series, order and rates of convergence, various modes of convergence, large sample properties of maximum likelihood estimators and Delta method. Topics in Matrix Theory include elementary matrix algebra, vector spaces, eigenvalues and eigenvectors, matrix factorizations, generalized inverses, systems of linear equations and quadratic forms.
6113 Applied Bayesian Statistics
(3-0) 3 hours credit. Prerequisite: STA 5503 or consent of instructor.
Probability and uncertainty, conditional probability and Bayes’ Rule, posterior analysis for commonly used distributions, prior distribution elicitation, Bayesian methods in linear models, Bayesian computation using software, and applications.
6133 Simulation and Statistical Computing
(3-0) 3 hours credit. Prerequisite: STA 5093 or consent of instructor.
Random variable generation, Monte Carlo integration, Markov chain Monte Carlo simulation, Monte Carlo optimization, Gibbs sampling and Metropolis-Hastings algorithm.
6233 Advanced Statistical Programming Using SAS Software
(3-0) 3 hours credit. Prerequisite: STA 5133 or consent of instructor.
Methods for analyzing continuous and categorical data will be discussed using procedures from Base SAS, SAS/GRAPH and SAS/STAT software. Discussion will include both implementation of methods and interpretation of results. Examples will be drawn from regression analysis, analysis of variance, categorical data analysis, multivariate methods, simulation and resampling. Techniques for efficient programming will be stressed. Students are expected to adopt a public dataset for use throughout the semester, and a final presentation will be required.
6713 Linear Models
(3-0) 3 hours credit. Prerequisite: STA 5103 or consent of instructor.
Distribution of quadratic forms, multivariate normal and theory for the full rank and less than full rank models, analysis of repeated measures, random and mixed effects models, topics in longitudinal data analysis, and generalized linear models. (Formerly STA 5713. Credit can be earned for only one of the following: STA 5713, STA 6713, or STA 7723.)
6833 Design and Analysis of Experiments
(3-0) 3 hours credit. Prerequisite: STA 5093, STA 5103, or consent of instructor.
Introduction to experimental design and data analysis in scientific and engineering settings. Topics include one-factor experiments, randomized block designs, factorials, two- and three-level factorial and fractional factorial designs, nested and split-plot designs, response surface methods, and Taguchi methods. Use of statistical software. (Formerly STA 5833. Credit cannot be earned for both STA 6833 and STA 5833.)
6843 Response Surface Methodology
(3-0) 3 hours credit. Prerequisite: STA 6833 or consent of instructor.
Factorial designs, first and second order models, process improvement with steepest ascent, experimental designs for fitting response surfaces, use of model diagnostics for finding optimum operating conditions, and robust parameter designs.
6913 Bioinformatics and Data Mining I: Microarray Data Analysis
(3-0) 3 hours credit. Prerequisite: STA 5103 or consent of instructor.
This course provides a detailed overview of statistical methods used in microarray and proteomics data analysis and exploits the design of such experiments. The topics include introduction to genome biology and microarray technology, R programming and Bioconductor, pre-processing, normalization, microarray experimental design and analysis, multiple testing, LIMMA, dimension reduction in microarray, cluster analysis, and classification in microarray experiments. (Formerly STA 5913. Credit cannot be earned for both STA 6913 and STA 5913.)
6953 Independent Study
3 hours credit. Prerequisites: Graduate standing and permission in writing (form available) of the instructor and the student’s Graduate Advisor of Record.
Independent reading, research, discussion, and/or writing under the direction of a faculty member. For students needing specialized work not normally or not often available as part of the regular course offerings. May be repeated for credit, but not more than 6 hours, regardless of discipline, will apply to the degree.
6961 Comprehensive Examination
1 hour credit. Prerequisite: Approval of the appropriate Graduate Program Committee to take the Comprehensive Examination.
Independent study course for the purpose of taking the Comprehensive Examination. May be repeated as many times as approved by the Graduate Program Committee. Enrollment is required each term in which the Comprehensive Examination is taken if no other courses are being taken that term. The grade report for the course is either “CR” (satisfactory performance on the Comprehensive Examination) or “NC” (unsatisfactory performance on the Comprehensive Examination).
6971-3 Special Problems
(1-0, 2-0, 3-0) 1 to 3 hours credit. Prerequisite: Consent of instructor.
An organized course offering the opportunity for specialized study not normally or not often available as part of the regular course offerings. Special Problems courses may be repeated for credit when topics vary, but not more than 6 hours, regardless of discipline, will apply to the degree.
6983 Master’s Thesis
3 hours credit. Prerequisites: Permission of the Graduate Advisor of Record and thesis director.
Thesis research and preparation. May be repeated for credit, but not more than 6 hours will apply to the Master’s degree. Credit will be awarded upon completion of the thesis. Enrollment is required each term in which the thesis is in progress.
6991 Statistical Consulting
(1-0) 1 hour credit. Prerequisite: Background in regression analysis and experimental design.
The principles dealing with the basic art and concepts of consulting in statistics. This course discusses the role and responsibilities of applied statisticians, relationship between clients and consultants, and effective report writing, etc. Each student is assigned at least one consulting problem and is required to submit a comprehensive final report. May be repeated for credit, but not more than 3 hours can be applied to the Doctoral degree.
7013 Advanced Applied Business Statistical Methods
(3-0) 3 hours credit. Prerequisite: Consent of instructor.
Methods and applications of statistics. Topics include basic probability theory, probability distributions of both discrete and continuous random variables, expectations, moments, distributions of functions of random variables, sampling distributions, estimations of population parameters, and hypothesis testing. Nonparametric statistical techniques and their applications to business research will also be covered in the course. Statistical computer software such as SAS or SPSS will be used in the course for data analysis. This course is designed for doctoral students in Business and cannot be applied to a Master of Science degree in Applied Statistics without consent of the instructor and prior approval from the Graduate Advisor of Record.
7023 Applied Linear Statistical Models
(3-0) 3 hours credit. Prerequisite: Consent of instructor.
An in-depth study of regression and analysis of variance models. Topics include multiple regression and model building, multiple and partial correlation, analysis of residuals, analysis of variance, multivariate analysis of variance, analysis of variance as regression analysis, generalized linear model, and applications of statistical models to problems in business. Computer software packages such as SAS or SPSS will be used for data analysis. This course is designed for doctoral students in Business and cannot be applied to a Master of Science degree in Applied Statistics without consent of the instructor and prior approval from the Graduate Advisor of Record.
7033 Multivariate Statistical Analysis
(3-0) 3 hours credit. Prerequisite: Consent of instructor.
An advanced treatment of multivariate statistical techniques. Topics include multivariate normal distribution, multivariate tests of hypotheses, confidence regions, principal component analysis, factor analysis, discrimination and classification analysis, and clustering. Computer software packages such as SAS or SPSS will be used for data analysis. This course is designed for doctoral students in Business and cannot be applied to a Master of Science degree in Applied Statistics without consent of the instructor and prior approval from the Graduate Advisor of Record.
7083 Time Series Analysis
(3-0) 3 hours credit. Prerequisite: Consent of instructor.
Univariate and multivariate time series analysis of economic and financial data, autoregressive integrated moving average (ARIMA) models and vector autoregression, out-of-sample forecasting using computer software. Unit roots, conintegration and error correction, and ARCH models. This course is designed for doctoral students in Business and cannot be applied to a Master of Science degree in Applied Statistics without consent of the instructor and prior approval from the Graduate Advisor of Record. (Credit cannot be earned for both STA 7083 and STA 7043.)
7113 Bayesian Statistics
(3-0) 3 hours credit. Prerequisite: STA 5513 or consent of instructor.
Topics include single parameter Bayesian analysis, prior distribution: informative and noninformative priors, multiple parameter Bayesian analysis, Bayesian computation, Bayesian hierarchical models and empirical models, Bayesian model checking, Bayesian applications to generalized linear models, and Bayesian decision theory.
7211-6 Doctoral Research
1 to 6 hours credit.
May be repeated for credit, but not more than 12 hours may be applied toward the Doctoral degree.
7311-6 Doctoral Dissertation
1 to 6 hours credit. Prerequisite: Admission to candidacy for Doctoral degree in Applied Statistics.
May be repeated for credit, but not more than 12 hours may be applied toward the Doctoral degree.
7503 Advanced Inference I
(3-0) 3 hours credit. Prerequisites: STA 5503 and STA 5513 or equivalent and Doctoral standing.
Topics include probability and measure, sufficiency, invariance, unbiased and equivariant estimators, decision theory; efficiency and other small sample properties of estimators; asymptotic properties of estimators, maximum likelihood estimation, and computational methods.
7513 Advanced Inference II
(3-0) 3 hours credit. Prerequisite: STA 7503.
The advanced theory of statistical inference, including the general decision problem; Neyman-Pearson theory of testing hypotheses; the monotone likelihood ratio property; asymptotic properties of likelihood ratio tests (LRT).
7813 Advanced Multivariate Analysis
(3-0) 3 hours credit. Prerequisite: STA 5813 or consent of instructor.
Multivariate analysis of variance, discriminant functions for group separation, classification of observations into groups, multivariate regression, canonical correlation, principal component analysis, factor analysis, and multivariate longitudinal data analysis.
7853 Advanced Categorical Data Analysis
(3-0) 3 hours credit. Prerequisite: STA 5503, STA 5853, or consent of instructor.
Models for multinomial responses, models for matched pairs and more complex repeated categorical response data, generalized linear mixed models for categorical responses. Asymptotic theory for parametric models, alternative estimation theory for parametric models.
7903 Advanced Survival Analysis: Counting Process Approach
(3-0) 3 hours credit. Prerequisite: STA 5903 or consent of instructor.
This course extends the Cox model to multiple event data using a counting process approach. The topics include counting processes, estimation of the survival and hazard functions, Cox model, residual and influence analysis, testing proportional hazard, multiple events model, frailty models, and S-Plus and SAS programming.
7923 Bioinformatics and Data Mining II: Data Mining
(3-0) 3 hours credit. Prerequisite: STA 5103 or consent of instructor.
This course provides an overview of machine learning (data mining) tools in analyzing the vast amounts of data found in biology, business, and other high-tech industries. The topics include introduction to Machine Learning and Data Mining, R Programming, data gathering and cleansing, Linear Methods, Additive Models, Model Assessment, Classification and Regression Trees (CART), Boosting and Random Forest, Neural Networks, Support Vector Machines, Nearest-Neighbor Classification, Cluster Analysis, Association Rules, visualization, and Applications to Microarray data analysis. (Formerly STA 5923. Credit cannot be earned for both STA 7923 and STA 5923.)
