The Master of Science Program in Statistics

The program of study leading to the degree of Master of Science (M.S.) in Statistics is designed to provide, at the graduate level, effective operational knowledge of the theory and methods of statistics, and of the applications of statistical methods in other fields. This program prepares you for positions as a statistician in industry or government. It can also serve as a first step toward a doctoral degree in Statistics.

The core of the Master's program consists of four semester-long courses, in Intermediate Probability (36-703), Intermediate Statistics (36-705), Regression Analysis (36-707), and Linear Models and Experimental Design (36-708). Most students complete these courses (or equivalents) in the first year of the M.S. Program, along with courses in Statistical Computing (36-711) and Statistical Practice (36-726). Statistical Computing surveys programming languages, statistical packages, and computing and graphical techniques that are useful in modern applied Statistics. In Statistical Practice, you gain practical experience in applying statistical ideas to real-world problems posed by researchers outside of Statistics.

First year of Master's Program

The M.S. program is flexible and can be modified according to your background and interests. Most students can complete the M.S. program in one and a half to two years. Exceptionally well-prepared students can complete the program in a single academic year and begin preparation for the Ph.D. by taking Advanced Statistics I in the spring.

How quickly you move through the M.S. program is a decision you make in consultation with your academic advisor. The main determining factor is whether you have had a sufficiently strong course in elementary mathematical statistics so that you will be adequately prepared for Intermediate Statistics (36-705). If not, you must take the year-long course taught here at the level of DeGroot's Probability and Statistics (36-325, 36-326). You may also wish to take other background courses in mathematics, the theory of probability, mathematical statistics, or statistical methods.

Statistics courses attract students in and out of statistics. Laura Dugan, Statistics and Public Policy, and Doug Baker, Computer Science, in Intermediate Statistics.

Three Typical Course Schedules in the First Year of the M.S. Program:
Plan Fall Semester Spring Semester

A 36-705 Intermediate Statistics 36-703 Intermediate Probability
36-707 Regression Analysis 36-708 Linear Models and Experimental Design
36-701 Perspectives on Statistics 36-726 Statistical Practice
36-711 Statistical Computing Optional Elective(*)

B 36-325 Probability and Statistics I 36-326 Probability and Statistics II
36-707 Regression Analysis 36-410 Applied Probability
36-701 Perspectives on Statistics 36-726 Statistical Practice
36-711 Statistical Computing Optional Elective (**)

C 36-705 Intermediate Statistics 36-755: Advanced Statistics I; or Elective (***)
36-707 Regression Analysis 36-708 Linear Models and Experimental Design
36-701 Perspectives on Statistics 36-726 Statistical Practice
36-711 Statistical Computing Two Half-Semester Methods Courses
(*) A typical choice for this elective would be 36-724: Applied Bayesian Methods.
(**) Typical choices for this optional elective would be 21-356: Advanced Calculus II or 36-402: Advanced Undergraduate Data Analysis.
(***) Students intending to do Ph.D. work typically take 36-755: Advanced Statistics I here. Others may take additional methods courses or a special project course.

Second Year of Master's Program/Preparation for the Ph.D. Program

The second year of the M.S. program consists primarily of half-semester courses in statistical methodology, offered from the following list on a rotating basis. With the theoretical foundation and practical experience you have had in the first year, the relevance of the second-year methodology courses becomes clear. You can gain additional practical experience by participating in elective workshops and special projects with individual faculty members.

Half-Semester Methods Courses:
  • 36-720 Discrete Multivariate Analysis
  • 36-722 Continuous Multivariate Analysis
  • 36-724 Applied Bayesian Methods
  • 36-728 Time Series I
  • 36-730 Time Series II
  • 36-732 Biostatistics Methods
  • 36-734 Survey Sampling
  • 36-736 Nonparametric Methods
  • 36-738 Topics in Applied Statistics

Many students, such as Stella Salvatierra and Tzee-Ming Huang, will continue in the Ph.D. program after completing their Masters' degrees.

The requirements for an M.S. degree can be met in three semesters for students in Track A; however, these students have the option of remaining in the program and taking additional methodology courses and project courses in the fourth semester. Students intending to go on to Ph.D. work often take Advanced Probability I and II, Advanced Statistics I and Advanced Data Analysis, in their second year. Ph.D. courses are indicated in green.

Two Typical Course Schedules in the Second Year of the M.S. Program:
Plan Fall Semester Spring Semester

A Four Half-Semester Methods Courses 36-754: Advanced Probability II;
or Two Half-Semester Methods Courses
36-755: Advanced Statistics I;
or Elective II (**)
36-753: Advanced Probability I;
or Elective I (*) 		36-757: Advanced Data Analysis;
or Elective III (***)

B 36-705 Intermediate Statistics 36-708 Linear Models and Experimental Design
Four Half-Semester Methods Courses 36-755: Advanced Statistics I;
or Elective II (**)
36-757: Advanced Data Analysis;
or Elective III (***)
(*) Students intending to do Ph.D. work, but not yet ready for 36-753: Advanced Probability I, typically take 21-620: Real Analysis and Lebesgue Integration for this elective. Others may take methods courses.
(**) Students intending to do Ph.D. work typically take 36-755: Advanced Statistics I here. Others may take methods and projects courses.
(***) Students intending to do Ph.D. work typically take 36-757: Advanced Data Analysis here. Others may take methods and projects courses.

Computing plays a large role in the department. Prof. Rob Kass demonstrates aspects of the Bayesian Central Limit Theorem in Statistical Computing to Michele DiPietro, Caroline Kanet, and J. R. Lockwood.

In addition to coursework, all M.S. students attend a weekly seminar series sponsored by the Department and participate in research projects or as teaching assistants or industrial interns when these opportunities arise. The purpose of these activities is to broaden your exposure to the practice of Statistics beyond the experience and knowledge gained through formal course studies.

There is no thesis requirement, but candidates for the degree of Master of Science (M.S.) in Statistics are required to pass written comprehensive examinations.

Next Topic, The Ph.D. Program in Statistics 


CMU HomeH&SS HomeStatistics