Spring 2007

Prof. Sanjeev Setia
setia at


Prerequisites: STAT 344 (or equivalent), at least two 600 level courses in computer science, and doctoral status. Integrated treatment to the models and practices of experimental computer science. Topics include scientific methods applied to computing, workload characterization, forecasting of performance and quality metrics of systems, uses of analytic and simulation models, design of experiments, interpretation and presentation of experimental results, hypothesis testing, and statistical analyses of data. Involves one or more large-scale projects.


Recommended textbook:

Either of the following books can be used for the class. Both cover the same material. In some respects, the Lilja book is more up to date.

  1. Raj Jain, The Art of Computer Systems Performance Analysis, John Wiley, 1991, ISBN: 0-471-50336-3. Please download the errata
  2. David Lilja, Measuring Computer Performance: A Practitioner's Guide,  Cambridge University Press, 2005. ISBN: 05216-4670-7.

Other recommended books:
  1. P. Cohen, Empirical Methods for Artifical Inteligence, MIT Press, 1995.
  2. Balachander Krishnamurthy and Mark Crovella, Internet Measurement: Infrastructure, Traffic, And Applications, John Wiley and Sons, Inc., 2006. ISBN: 04700-1461-x
  3. I. Miller, J. Freund, R. Johnson, Probability and Statistics for Engineers, Sixth Edition, Prentice Hall, 2000, ISBN: 0-13-014158-5.
  4. David M. Levine, Patricia P. Ramsey, Robert K. Smidt, Applied Statistics for Engineers and Scientists: Using Microsoft Excel & MINITAB, Prentice Hall, 2001, ISBN: 0134888014.
  5. Averill M. Law and W. David Kelton, Simulation Modeling and Analysis, McGraw Hill, 2000.
  6. D. A. Menascé and V. Almeida, Capacity Planning for Web Services: metrics, models, and methods, Prentice Hall, 2002.

Course Outline

The following topics will be covered (not necessarily in the order below):


The grade for the course will be based on the following components: (i) Homework Assignments (25%) (ii) Class Project (35%) (iii) Mid-term exam (20%) (iii) Take home final exam (20%).

Important Dates

Mid-term exam: March 19 (tentative)
Project Presentation : April 30

Class Project

Students will work on an individual project dealing with various aspects of experimental computer science. Each student will submit a proposal for an experimental project dealing with a quantitative analysis of a computer system, algorithm, and/or method of interest to the student. The deliverables are a technical report and a short presentation to the class.

Office Hours

Office hours will be on Monday from 3-4 pm in my office (S & T II Room 430), or by appointment.

Class Home Page

All handouts and other course material will be available at URL