This site is an archived version of Voteview.com archived from University of Georgia on May 23, 2017. This point-in-time capture includes all files publicly linked on Voteview.com at that time. We provide access to this content as a service to ensure that past users of Voteview.com have access to historical files. This content will remain online until at least January 1st, 2018. UCLA provides no warranty or guarantee of access to these files.

## Poole, Sowell, and Spear -- 1992 Dimensionality Paper

### Updated 25 March 2016

The files posted on this page replicate the analysis in Poole, Sowell, and Spear (1992):

Poole, Keith T., Fallaw B. Sowell, and Stephen E. Spear. 1992. "Evaluating Dimensionality in Spatial Voting Models." Mathematical and Computer Modeling, 16: 85-101.

When the Minority Margin is equal to the classification error we computed a point mass probability corresponding to the minority margin -- 0.025 - 0.500 -- for dimensions 2, 3, ... , 10.
The format of the Point Mass File is:
``` 1.  Minority Margin
2.  Probability Projection is from a Two-Dimensional Space of Perfect Voting
3.  Probability Projection is from a Three-Dimensional Space of Perfect Voting
etc.
11.  Probability Projection is from a Ten-Dimensional Space of Perfect Voting```
Point Mass File (Text File, 476 lines)

When the Classification error is less than the minority margin, the file tab2to8.dat gives the Likelihood of a minority margin/classification error pair projected from a space of two to eight dimensions with an infinite number of voters.
The format of the Likelihood file is:
```row 1. Minority Margin 25 (.025 to .500, but listed as 25 to 500)
column 2 - Classification Error of 0 -- Minority Margin minus 1, minus 2, etc. -- for .025 this runs from 0,1,2, ... , 24
columns 3 - 9 Likelihoods for 2 to 8 dimensions
row 2. Minority Margin 25 (0.25)
column 2 - Classification Error of 1
columns 3 - 9 Likelihoods for 2 to 8 dimensions
etc.
etc.
row 124,950.  Minority Margin of 500 (.500)
column 2 - Classification Error of 499
columns 3 - 9 Likelihoods for 2 to 8 dimensions
```
Likelihood Table (Text file, 124,950 rows by 9 columns)

pss.f95 -- FORTRAN 95 Program to Compute Likelihoods given an empirical vector of minority margins and corresponding classification errors

h01_113_codes.txt -- DW-NOMINATE House output with minority margins and classification errors read by pss.f95.

VOTEVIEW Blog
NOMINATE Data, Roll Call Data, and Software
Course Web Pages: University of Georgia (2010 - )
Course Web Pages: UC San Diego (2004 - 2010)
University of San Diego Law School (2005)
Course Web Pages: University of Houston (2000 - 2005)
Course Web Pages: Carnegie-Mellon University (1997 - 2000)
Analyzing Spatial Models of Choice and Judgment with R
Spatial Models of Parliamentary Voting
Recent Working Papers
Analyses of Recent Politics