Graduate Faculty
701-231-7532
Fu-Chih Cheng, Ph.D.
North Dakota State University, 2003
Field:
Monte Carlo Simulations, Resampling Methods, and Design of Experiments
Qing Kang, Ph.D.
Kansas State University-Manhattan,2005
Field:
Generalized Linear Models, Sampling, Nonparametrics
Rhonda Magel, Ph.D.
University of Missouri-Rolla, 1982
Field:
Nonparametrics, Inference Under Order Restrictions, Regression
Jeffrey Terpstra, Ph.D.
Western Michigan University, 1997
Field:
Nonparametrics, Time Series, Robust Statistics
Christopher Vahl, Ph.D.
Kansas State University-Manhattan,2005
Field:
Linear and Mixed Models, Experimental Design, Sampling
|
 |
 
Program Description
The Department of Statistics offers programs
leading to a Ph.D. in statistics or a master's degree in
applied statistics. The program is flexible enough to be individually
planned around prior experience and in accord with professional
goals.
During the first year of the program, students are strongly encouraged
to meet with each faculty member to discuss possible research
topics. The student should select an advisory and examining committee
by the end of the first year.
A joint master's degree in computer science and statistics
may also be obtained.
A graduate certificate in Applied Statistics for nonmajors is also offered.
Admissions Requirements
- B.S. or equivalent degree from an accredited university,
- Knowledge of College Algebra,
- Twelve semester hours to include Stat 725, Stat 726, and two other pre-approved graduate level courses in statistics.
The Department of Statistics' graduate
program is open to qualified graduates of universities of recognized
standing. To be admitted with full status to the M.S. program,
the applicant must :
- Hold a baccalaureate degree from an educational
institution of recognized standing,
- Have had at least one year of calculus,
- Have had at least one course in statistics,
- Have had at least one programming language, and
- Must have at least a 3.0 or equivalent
cumulative grade point average (GPA) on all related courses
at the baccalaureate level.
To be admitted with full status into the
M.S. program in computer science and statistics, the applicant
must satisfy the admission requirements for both the M.S. program
in computer science and the M.S. program in applied statistics.
To be admitted with full status into the
Ph.D. program, the applicant must
- Hold a baccalaureate degree from an educational
institution of recognized standing,
- Have had four courses in math at the
university calculus level or above,
- Have had several courses in statistics,
- Have had at least one programming language, and
- Must have at least a 3.0 or equivalent
cumulative grade point average (GPA) on all related courses
at the baccalaureate level.
Students not holding a master's
degree in statistics or a closely related field will not be admitted
to the Ph.D. program in statistics. These students must first
apply to the M.S. program in applied statistics and complete the
M.S. degree.
Preferably, applications should be submitted directly to The Graduate
School before March 15 of the upcoming academic year.
Official transcripts (transcripts having an appropriate seal or
stamp) of all previous undergraduate and graduate records must
be received by The Graduate School before the application is complete.
When a transcript is submitted in advance of completion of undergraduate
or graduate studies, an updated transcript showing all course
credits and grades must be provided prior to initial registration
at NDSU.
Three letters of recommendation are required before action is
taken on any application. Personal reference report forms are
available from The Graduate School. The TOEFL examination is required
of international applicants. A minimum score of 550 (paper test), 213 (computer test), or 79-80 (internet test) must be achieved.
Financial Assistance
The student must first make application
to The Graduate School and be accepted in full or conditional
status before he/she is eligible for an assistantship in the Department
of Statistics.
Teaching assistantships are available. To be considered for an
assistantship, a completed Graduate School application, official
transcripts, and three letters of reference must be submitted
to The Graduate School no later than March 15. International students
must also submit a TOEFL score.
Degree Requirements
Requires 12 Semester credit hours consisting of Stat 725, Stat 726, and two other pre-approved graduate level courses in statistics.
The program for the M.S. degree in applied
statistics requires 32 semester credits with an overall GPA of
3.0 or higher. An oral defense of a research-based thesis or paper
is required. The program for the M.S. degree in computer science
and statistics requires 42 semester credits with an overall GPA
of 3.0 or higher. An oral defense of a research-based thesis or
paper is required.
All students must :
- Complete a set of core courses with a
grade of B or better, including Stat 661, 662, 767, 768, 764
or 774,
- Successfully complete 2 one-credit practicums
in consulting. Each statistical practicum will be listed as
Stat 794,
- Complete an additional 9-12 hours (depends
on number of research hours) of course work selected from the
following courses: Stat 650, 651, 660, 663, 664, 665, 670, 730,
732, 750, 761, 762, 770, 772, 777, 778, 780, 786, 796 (Special
Topics in Statistics). At most, two of the following courses
will count in the additional 9-12 hours: CSci 618, 654, 737;
Math 650, 688, 728. A plan of study must be submitted.
- Pass two written comprehensive exams.
Exam 1 covers Stat 767 and 768. Exam 2 covers Stat 661, 662,
and 764 or 774. Exam 1 is two hours, and Exam 2 is three hours.
These exams are offered approximately the fourth week of Fall
and Spring Semesters. A maximum of two attempts will be allowed, and
- Successfully complete and defend a research-based
thesis or paper.
All students must :
- Take a minimum of 42 semester credit
hours, including at least 18 graduate course credits in computer
science and at least 18 graduate course credits in statistics,
- Take CSci 708, 713, 724, 737, 765, and
one additional 600- or 700-level course in computer science,
- Take Stat 661, 662, 767, 768, 764 or
774, and one additional 600- or 700-level course in statistics
(does not include Stat 725 or Stat 726),
- Pass both the comprehensive exams for
the M.S. degree in computer science and the M.S. degree in statistics, and
- Successfully complete a research-based
thesis or paper. The supervisory committee must consist of at
least one faculty member from computer science and at least
one faculty member from statistics.
The program for the Ph.D. degree requires an additional 30 credits
of course work beyond the M.S. degree and 30 hours of research.
An oral defense of a dissertation is required.
All students must :
- Complete a set of core courses with a
grade of B or better, including Stat 661, 662, 767, 768, 764
or 774,
- Successfully complete 6 one-credit practicums
in Consulting/Presentation Practicum. Each statistical practicum
will be listed as Stat 794,
- Complete an additional 30 semester credits
of statistics courses at the 600- or 700-level (does not include
Stat 725 or Stat 726). At least 15 credits must be at the 700-level. All Ph.D. students must complete Stat 786,
- Complete 9 semester credits from the
following: Math 650, 651, 688, 689, 728; CSci 654, 737. This
requirement may be waived and additional courses in statistics
substituted upon approval by the adviser and advisory committee. A plan of study must be submitted,
- Pass a written comprehensive exam. This
exam consists of two sections. It is given twice a year during approximately the fifth
week of each Semester. A maximum of two attempts is allowed,
- Submit a research proposal and pass an
oral exam on the proposal and related topics, and
- Complete and successfully defend the
research dissertation.
*Some of these requirements may be satisfied
upon admittance into the program with an already existing M.S.
degree in Statistics.
Courses Offered
- 650 Stochastic Processes 3
- Discrete time Markov chains, Poisson
processes, continuous time Markov chains, birth and death processes,
renewal processes, branching processes, queuing systems, and
applications. Prereq: Stat 368.
651 Bayesian Statistical Decision Theory 3- Bayesian approach to statistics, including
utility and loss, prior and posterior densities, and Bayesian
inference. Comparisons with classical statistical methods. Prereq:
Stat 368 or 468.
660 Applied Survey Sampling 3- Simple random, stratified, systematic,
and cluster sampling; two-stage sampling. Estimation of population
means and variances. Ratio and regression estimators. Prereq:
Stat 330 or 368.
661 Applied Regression Models 3- Simple linear regression, matrix approach
to multiple regression, and introduction to various tests and
confidence intervals. Includes discussion of multicollinearity
and transformations. Prereq: Stat 330 or 368 and a knowledge of matrix algebra.
662 Introduction to Experimental Design 3- Fundamental principles of designing
an experiment: randomized block, Latin square, and factorial.
Also covers analysis of covariance and response surface methodology.
Prereq: Stat 330 or 368.
663 Nonparametric Statistics 3- Various tests and confidence intervals
that may be used when the underlying probability distributions
are unknown. Includes the Wilcoxon, Kruskal-Wallis, and Friedman.
Prereq: Stat 330 or 368.
664 Discrete Data Analysis 3- Application of binomial, hypergeometric,
Poisson, mixed Poisson, and multinomial distributions in discrete
data analysis. Log-linear models and contingency tables. Logistic
regression. Discrete discriminant analysis. Prereq: Stat 368.
665 Meta-Analysis Methods 3- Statistical methods for meta-analysis
with applications. Various parametric effect sizes from a series
of experiments: fixed effect, random effect linear models; combining
estimates of correlation coefficients; meta-analysis in the
physical and biological sciences. Prereq: Stat 330 and 331,
or 461/661 or 725.
670 Statistical SAS Programming 3- Focuses on statistical problem solving
and writing SAS computer code. Data types, data management,
data input/output, SAS as a programming language, data analysis,
report writing, and graphing. Prereq: Stat 461/661 or 462/662, or Stat 726.
-
472/672 Time Series 3
- Estimation of trend in time series data. Seasonal models.
Stationary models. Moving average, autoregressive, and ARMA models. Model
identification. Forecasting. Intervention analysis. Prereq: Stat 461/661, Stat 468/768,
and a course in matrix algebra.
725 Applied Statistics 3- Data description, probability, inference
on means, proportions, difference of means and proportions,
categorical data, regression, analysis of variance, and multiple
comparisons. Prereq: Knowledge of algebra. NOTE: This course
is not intended for statistics or mathematics majors.
726 Applied Regression & Analysis of Variance 3- Simple and multiple regression, ANOVA tables, correlation,
regression diagnostics, selection procedures, analysis of covariance, one-way ANOVA,
two-way ANOVA. Prereq: Stat 725.
730 Biostatistics 3- Direct assays, parallel line assays,
slope ratio assays, multiple assays, and quantal assays. Model,
estimation, and testing. Probit and logit analysis. Prereq:
Stat 461/661 or 725.
732 Introduction to Bioinformatics 3- An introduction to the principles of
bioinformatics including statistical techniques for the analysis
of one or more gene sequences, and computational techniques
for knowledge discovery from biological data. Prereq: Stat 461/661.
Cross-listed with Math 732 and CSCI 732.
761 Advanced Regression 3- Multiple regression, analysis of residuals,
model building, regression diagnostics, multicollinearity, robust
regression, and nonlinear regression. Prereq: Stat 461/661, Stat 468/768, and a course in matrix algebra.
762 Messy Data Analysis 3- One-way classification models with heterogeneous
errors. Two-way classification analysis in the unbalanced case.
Analysis of mixed models. Split-plot, nested, and crossover
designs. Prereq: Stat 462/662 and a course in matrix algebra.
764 Multivariate Methods 3- Sample geometry; correlation; multiple,
partial, canonical correlation test of hypothesis on means;
multivariate analysis of variance; principal components; factor
analysis; and discriminate analysis. Prereq: Stat 461/661 or 462/662, and a course in matrix algebra.
767 Probability and Mathematical Statistics I 3- Random variables, discrete probability
distributions, density functions, joint and marginal density
functions, transformations, limiting distributions, central
limit theorem. Additional project required. Prereq: Math 265
or Stat 368.
768 Probability and Mathematical Statistics II 3- Properties of estimators, confidence
intervals, hypotheses testing, Neyman-Pearson lemma, likelihood
ratio tests, complete and sufficient statistics. Additional
projects required. Prereq: Stat 767.
770 Survival Analysis 3- Basic methodology in the analysis of
censored data, two basic types of censoring, parametric estimation,
nonparametric estimation, and life table methods. Prereq: Stat
768.
772 Computational Statistics 3- Assortment of computational statistics and statistical
computing techniques. Specific topics include: random variable generation,
optimization and root finding, resampling statistics, Monte Carlo methods,
statistical graphics, non-linear and generalized least squares, and the EM algorithm.
Prereq: Stat 661 and Stat 768.
774 Linear Models I 3- General linear models. Full rank models.
Estimation, confidence ellipsoids, and tests of hypotheses.
Not full rank models. Applications to regression and design
of experiments. Prereq: Stat 768 and a course in matrix algebra.
777 Multivariate Theory 3- Wishart distribution, distribution of
Hotelling's T-square and Lambda statistics, cluster analysis,
correspondence analysis, principal components, factor analysis,
discriminant analysis, multidimensional scaling. Prereq: Stat
764.
778 Modern Probability Theory 3- Probability theory presented from the
measure theoretic perspective. Emphasis on various types
of convergence and limit theorems. Discussion of random walks,
conditional expectations, and martingales. Prereq: Stat 767
and Math 750. Cross-listed with Math.
780 Asymptotics, Bootstrap, and Other Resampling Plans 3- Development of large sample and small
sample properties of a variety of estimators. Prereq: Stat 768.
786 Advanced Inference 3- Further discussion of properties of
estimators, theory of estimation, and hypotheses testing. Prereq:
Stat 768.
-
-
-
- 690, 790 Seminar 1-3
696, 796 Special Topics 1-5
793 Individual Study 1-5
794 Consulting/Presentation Practicum 1
797 Master's Paper 1-3
797R Paper Continuing Registration 1
798 Master's Thesis 1-10
798R Thesis Continuing Registration 1
799 Doctoral Dissertation 1-15
799R Dissertation Continuing Registration 1
|
