SURVEYBIAS: Stata module to compute the B and B_w multinomial accuracy measures for polling bias
AbstractThis module estimates by Maximum Likelihood methods various polling accuracy measures for multi-party elections based on a generalisation of Martin, Traugott and Kennedy's two-party predictive accuracy index A. For detailed information on the measures A', B and B_w, see Arzheimer, Kai and Jocelyn Evans: A New Multinomial Accuracy Measure for Polling Bias. Forthcoming in Political Analysis(21) 2013, http://dx.doi.org/10.1093/pan/mpt012 The module consists of three ados: surveybias.ado is for use with a single survey (raw data). surveybiasseries.ado facilitates the comparison of surveys. It calculates accuracy measures from a dataset, where each row contains margins from a single survey. surveybiasi.ado is an immediate command that makes it easy to calculate accuracy measures from published survey results. Two example data sets illustrate the use of surveybias and surveybiasseries. More replication data and scripts are available from my dataverse at http://hdl.handle.net/1902.1/21603
Download InfoIf you experience problems downloading a file, check if you have the proper application to view it first. In case of further problems read the IDEAS help page. Note that these files are not on the IDEAS site. Please be patient as the files may be large.
Bibliographic InfoSoftware component provided by Boston College Department of Economics in its series Statistical Software Components with number S457666.
Programming language: Stata
Requires: Stata version 11
Date of creation: 03 Jul 2013
Date of revision: 09 Apr 2014
Note: This module should be installed from within Stata by typing "ssc install surveybias". Windows users should not attempt to download these files with a web browser.
Contact details of provider:
Postal: Boston College, 140 Commonwealth Avenue, Chestnut Hill MA 02467 USA
Web page: http://fmwww.bc.edu/EC/
More information through EDIRC
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Christopher F Baum).
If references are entirely missing, you can add them using this form.