POLS 8505: MEASUREMENT THEORY


Clyde H. Coombs
Born: 22 July 1912
Died: 4 February 1988



Fall Semester AY2011-2012
Department of Political Science
School of Public and International Affairs
University of Georgia
Athens, GA 30602

Classroom: Baldwin 302
Time: 3:35-6:35 Wednesdays

Instructor: Keith T. Poole

Office: Baldwin 304D
E-Mail: ktpoole@uga.edu
WebSite: K7MOA Home Page or Office Hours: 2:00 - 4:00PM Thursdays or By Appointment

The following texts will be used in this course:


Requirements

This course is concerned with dimensional analysis, that is, the measurement of latent dimensions in data matrices. A working knowledge of OLS multiple regression analysis and STATA is required for this course. Students will be required to learn Epsilon (EMACS), a screen editor, and the open-source statistical package -- R. In the second half of the course we will also use the open-source Bayesian statistical package WINBUGS. We will also use a variety of "canned" programs that perform various kinds of dimensional analyses.

Grades will be determined by regularly assigned class problems.


Below are links to my Advanced Multivariate Statistics course web page for the fall of 2001 and and spring of 2003 at the University of Houston and my Prob-Stat II (required MBA course) web pages from AY1997-98 at Carnegie-Mellon University. These should be helpful if you need to refresh your memory about multiple regression.

POLS 6382 Advanced Multivariate Statistics (UH, fall 2001)

Probability and Statistics II Main Page (CMU Spring 1998)

Useful Links -- EPSILON

EPSILON HomePage -- Lugaru Software Ltd.

Useful Epsilon Commands

Epsilon Keyboard Macro Examples

Epsilon Text File Macro Examples


Useful Links -- R

PCH Symbols in R

Octal References for Math Symbols that can be used in PlotMath in R

Miscellaneous Useful R Programs



Useful Links -- Multidimensional Scaling

How to Use KYST, A Very Flexible Program to do Multidimensional Scaling and Unfolding


Useful Links -- Old Homeworks

Old Homeworks: 2001 - 2008


Useful Links -- How to Install GNU C/C++ and FORTRAN Compilers for WINDOWS and MAC Machines

How to Install GNU Compilers


Useful Links -- How to Install JAGS on the MAC

How to Install JAGS


Useful Links -- JAGS for WINDOWS 64 bit

Sourcefore JAGS 3.1 -- Runs on 64 bit WINDOWS and 64 bit R


Problem Sets (2011)

Homework 1: Due 24 August 2011(WINDOWS)
Homework 1: Due 24 August 2011(iMAC)
Homework 2: Due 31 August 2011(WINDOWS)
Homework 2: Due 31 August 2011(iMAC)
Homework 3: Due 7 September 2011(WINDOWS)
Homework 3: Due 7 September 2011(iMAC)
Homework 4: Due 14 September 2011(WINDOWS)
Homework 4: Due 14 September 2011(iMAC)
Homework 5: Due 21 September 2011(WINDOWS)
Homework 5: Due 21 September 2011(iMAC)
Homework 6: Due 28 September 2011(WINDOWS)
Homework 6: Due 28 September 2011(iMAC)
Homework 7: Due 5 October 2011(WINDOWS)
Homework 7: Due 5 October 2011(iMAC)
Homework 8: Due 12 October 2011(WINDOWS)
Homework 8: Due 12 October 2011(iMAC)
Homework 9: Due 19 October 2011(WINDOWS)
Homework 9: Due 19 October 2011(iMAC)
Homework 10: Due 26 October 2011(WINDOWS)
Homework 10: Due 26 October 2011(iMAC)
Homework 11: Due 2 November 2011(WINDOWS)
Homework 11: Due 2 November 2011(iMAC)
Homework 12: Due 9 November 2011(WINDOWS)
Homework 12: Due 9 November 2011(iMAC)
Homework 13: Due 16 November 2011(WINDOWS)
Homework 13: Due 16 November 2011(iMAC)
Homework 14: Due 30 November 2011(WINDOWS)
Homework 14: Due 30 November 2011(iMAC)



Course Outline
  1. Clyde Coombs' Theory of Data: Similarities and Preferential Choice

  2. Assignment:

  3. Classical Scaling of Similarities Data

    Assignment:

  4. Non-Metric Multidimensional Scaling

    Assignment:

  5. Bayesian Multidimensional Scaling

    Assignment:

  6. Unfolding Analysis: Non-Parametric Methods [Optimal Classification (OC)]

    Assignment:

  7. Unfolding Analysis: Parametric Methods

    1. Analysis of Interval Level Data -- Interest Group Ratings and Thermometer Scores

      Assignment:

    2. Analysis of Perceptual Data -- Seven Point Scales

      Assignment:

    3. Analysis of Roll Call Data (Discrete Data)

      Assignment:

    4.