Skip Navigation

Spring 2012 - 62205 - PA397C - Advanced Empirical Methods for Policy Analysis

Quantitative Methods for Management

Instructor(s): Matwiczak, Kenneth
Unique Number: 62205
Day & Time: W 2:00 - 5:00 pm
Room: SRH 3.220
Waitlist Information:For LBJ Students: UT Waitlist Information
Course Overview

In addition to the Introduction to Empirical Methods course in the common core, MPAff students are required to take another three-hour course in quantitative analysis, selected from among a set of courses focusing on the application of quantitative theory and techniques to policy analysis. Topics offered vary from year to year but include econometrics, demographic techniques, systems analysis, simulation modeling, and quantitative indicator methods. As the second course in the two-course MPAff quantitative sequence, this course is intended to provide students with an in-depth understanding and hands-on experience with a specific quantitative method useful in policy analysis. This course is usually taken during the second semester of the first year.

Section Description

In an effort to broaden and expand the students’ “toolkit” of decision-making and management aids, this “topical” course covers additional decision analysis and modeling methods not addressed in IEM. It is intended for students who are interested in quantitative methods applied to management and administration. Topics covered in this course include:

(1) Decision Analysis:

  • Utility Theory: How to incorporate/assign value and assess risk associated with qualitative decision criteria.
  • Multi-Criteria Decision Models: Modeling and analyzing decisions based on several quantitative and/or qualitative criteria, such as contract bidder evaluation /selection, personnel selection, etc.  Also used for performance measurement modeling.
  • Game Theory: Two-party, competing decision strategies.

 (2) Optimization:

  • Linear Programming: Expanding on Sensitivity and Post-Optimality Analysis
  • Integer Programming: Solving linear programs in which solutions are constrained to be integer values, such as problems involving personnel assignments, etc.
  • Goal Programming: Optimization problems in which we would like to achieve multiple objectives. Problems of this nature might include maximizing profit, while minimizing the total project budget, and meeting all time deadlines.
  • Network Analysis: The application of linear programming and other algorithms to the optimization of networks, as in transportation, communication, utilities, and project schedules.

(3) Queuing Theory: An introduction to the mathematics of waiting lines. How many “servers” are needed? How much room to allow for waiting line build-up? Are we making efficient use of servers?

(4) Inventory Theory: How much stock to keep on hand? How much to order? How often to order? How much will different inventory “policies” cost?

(5) Simulation: A means for gathering information about and studying complex processes or systems, that cannot be modeled mathematically or that have no analytical solution. Monte Carlo Methods can be used to generate stochastic inputs for processes and decisions involving uncertainty. Statistical analysis tools are applied to studying simulation model output.

The course is an "applied" course in the use of the management tools described above, and in the analysis and interpretation of the results. You will make extensive use of computer spreadsheets throughout the course. There will be several homework problem sets assigned, as well as a semester project which will require an oral presentation at the end of the semester. A mid-term exam and a final exam are included in the course.


  1. Successful completion of PA397 – Introduction to Empirical Methods for Policy Analysis, or equivalent course(s) which introduced linear programming and decision analysis methods.
  2. Familiarity with computer spreadsheets such as MS-Excel. “Familiarity” includes recording data in a spreadsheet, performing simple calculations, and using the graphing, statistical, and other functions.