James Lo and Keith Poole

Updated 30 June 2011

• Aldrich, John H. and Richard D. McKelvey. 1977. "A Method of Scaling with Applications to the 1968 and 1972 Presidential Elections." American Political Science Review, 71:111-130.
  
  
• Palfrey, Thomas R. and Keith T. Poole. 1987. "The Relationship Between Information, Ideology, and Voting Behavior." American Journal of Political Science, 31:511-530.
  
  
• Poole, Keith T. 1998. "Recovering a Basic Space From a Set of Issue Scales." American Journal of Political Science, 42:954-993.
  
  
• Poole, Keith T. 1998. "How to Use the Black Box." A Supplement to "Recovering a Basic Space From a Set of Issue Scales" that shows in detail how to apply the various programs used in the article.
  
  
• Poole, Keith T. 2001. "The Relationship Between the Aldrich-McKelvey Scaling Solution and the Individual Differences Problem." Manuscript, University of Houston.
  
  

Aldrich-McKelvey Examples

Additional Examples can be found on the Voteview Blog

basicspace_AM.r -- R program that performs Aldrich-McKelvey Scaling on the 1980 Liberal-Conservative Seven Point Scale

LC1980V.DAT -- 1980 L-C Data (See R Program for documentation)


basicspace_AM_Vietnam_1968.r -- R program that performs Aldrich-McKelvey Scaling on the 1968 Vietnam Seven Point Scale

VIETNAM_1968.TXT -- 1968 Vietnam Data (See R Program for documentation)


basicspace_AM_Vietnam_1968_Stata_Bootstrap.r -- R program that performs Aldrich-McKelvey Scaling on the 1968 Vietnam Seven Point Scale with the Data stored as a Stata file. Performs a bootstrap analysis to get the standard errors for the candidate placements which are written out as the file 1968_Stimuli.txt.

nes1968_first_11.DTA -- NES1968 STATA 11 File (See R Program for documentation)


basicspace_AM_Urban_Unrest_1968.r -- R program that performs Aldrich-McKelvey Scaling on the 1968 Urban Unrest Seven Point Scale

URBAN_UNREST_1968.TXT -- 1968 Urban Unrest Data (See R Program for documentation)


basicspace_AM_Urban_Unrest_1968_SPSS.r -- R program that performs Aldrich-McKelvey Scaling on the 1968 Urban Unrest Seven Point Scale with the Data stored as a SPSS file

anes1968.POR -- NES1968 SPSS File (See R Program for documentation)


basicspace_AM_Urban_Unrest_1968_Stata_2.r -- R program that performs Aldrich-McKelvey Scaling on the 1968 Urban Unrest Seven Point Scale with the Data stored as a Stata file

nes1968_first_11.DTA -- NES1968 STATA 11 File (See R Program for documentation)


basicspace_AM_L-C_2004_Stata.r -- R program that performs Aldrich-McKelvey Scaling on the 2004 Liberal-Conservative Seven Point Scale From the NES 2004 Stata file

anes2004.DTA -- 2004 NES 2004 (See R Program for documentation)

BLACKBOX Examples

Additional Examples can be found on the Voteview Blog

basicspace_blackbox.r -- R program that performs the basicspace scaling on the 1980 issue scales shown in "Estimating a Basic Space From A Set of Issue Scales," American Journal of Political Science, 42 (July 1998), pp. 954-993. Program reads a text file with just the issue positions.

FORT99.DAT -- 1980 Issue Scales Data


basicspace_blackbox_nes1980.r -- R program that performs the basicspace scaling on the 1980 issue scales shown in "Estimating a Basic Space From A Set of Issue Scales," American Journal of Political Science, 42 (July 1998), pp. 954-993. Program reads a STATA file containing the NES 1980 survey. To use the STATA 7 file just change the read.dta() command in the program.
basicspace_blackbox_nes1980_plots.r -- Same as above but it also plots respondents across the first and second Basic Dimensions. This capability will be included in the final package.

nes1980_first.dta -- 1980 NES survey in STATA 7 File
nes1980_first_11.dta -- 1980 NES survey in STATA 11 File


basicspace_blackbox_nes1980_bootstrap.r -- Same as above but it also performs the bootstrap to obtain standard errors for the W and c coefficients for one to three dimensions. The number of trials is set to 101 but any number can be used.

basicspace_blackbox_nes1992.r -- R program that performs the basicspace scaling on 15 issue scales from the 1992 NES. This is a replication of the example shown in the appendix to the 1998 article -- How to Use the Black Box. This program reads the STATA file containing the entire 1992 NES survey. To use the STATA 7 file just change the read.dta() command in the program.

nes1992_first.dta -- 1992 NES survey in STATA 7 File
nes1992_first_11.dta -- 1992 NES survey in STATA 11 File

BLACKBOX TRANSPOSE EXAMPLES

Additional Examples can be found on the Voteview Blog

basicspace_blackbox_transpose.r -- R program that performs the basicspace transpose scaling (a generalization of A-M to multiple dimensions) on the 1980 Liberal-Conservative Seven Point Scale. This application is shown in the appendix to the 1998 article -- How to Use the Black Box. The Transpose Scaling Method can be used to test whether or not an Issue Scale is unidimensional.

LC1980V.DAT -- 1980 L-C Data (See R Program for documentation)


basicspace_blackbox_transpose_L-C_2004_Stata.r -- R program that performs the basicspace transpose scaling on the 2004 Liberal-Conservative Seven Point Scale.

anes2004.DTA -- 2004 NES 2004 (See R Program for documentation)


basicspace_blackbox_transpose_1968_Therms.r -- R program that performs a basicspace transpose scaling on the 12 Candidate Feeling Thermometers From the 1968 National Election Study.


NES1968_FIRST.DTA -- NES 1968 STATA 7 file
NES1968_FIRST_11.DTA -- NES 1968 STATA 11 file
-- 1968 NES (See R Program for documentation)


basicspace_big_blackbox_transpose_1968_Therms.r -- R program that performs a basicspace transpose scaling on the 12 Candidate Feeling Thermometers From the 1968 National Election Study. This version removes the 1500 respondent restriction -- Use with caution! The program reads this R program (courtesy of James Lo):

big_blackbox_transpose.R -- R code that creates the function big_blackbox_transpose which is used in the R program above.


The R program produces a plot of the Candidate Configuration -- the Y (PSI) Matrix. This matrix is normalized so that Y'Y=I.


The Respondents are the W matrix. Note that the scale is different from the Candidate Configuration because this is, in effect, a singular value decomposition (see cited papers above) and not an unfolding analysis.

STATA FILES

Variable Listing (includes traditional LOC and WIDTH information), summ Listing, d Listing

Variable Listing (includes traditional LOC and WIDTH information), summ Listing, d Listing

Variable Listing (includes traditional LOC and WIDTH information), summ Listing, d Listing

Variable Listing, summ Listing, d Listing

Variable Listing, summ Listing, d Listing

Variable Listing, summ Listing, d Listing

Variable Listing, summ Listing, d Listing

Variable Listing, summ Listing, d Listing

Variable Listing, summ Listing, d Listing

Variable Listing, summ Listing, d Listing

Variable Listing, summ Listing, d Listing

Site Links