El efecto de la ponderación y la imputación en el sesgo de los estudios electorales en España

  1. Pablo Cabrera-Álvarez 1
  2. Modesto Escobar 1
  1. 1 Universidad de Salamanca
    info

    Universidad de Salamanca

    Salamanca, España

    ROR https://ror.org/02f40zc51

Revista:
REIS: Revista Española de Investigaciones Sociológicas

ISSN: 0210-5233

Any de publicació: 2019

Número: 165

Pàgines: 45-64

Tipus: Article

DOI: 10.5477/CIS/REIS.165.45 DIALNET GOOGLE SCHOLAR lock_openDialnet editor

Altres publicacions en: REIS: Revista Española de Investigaciones Sociológicas

Resum

The purpose of this article is to assess the effectiveness of post-survey adjustments made to electoral polls in order to correct for non-response bias. To do so we have used different weighting and multiple imputation methods using pre-election and post-election polls conducted by Spain's Centre for Sociological Research for all Spanish general elections since 1982. The results show the benefit of weighting by past vote when voters’ preferences remain stable. However, the use of multiple imputation techniques to address missing values has a limited effect and is influenced by the variables included in the model.

€ Mostra el finançament

Informació de finançament

Esta investigación ha sido apoyada por el programa de becas predoctorales de la Obra Social «La Caixa».

Finançadors

Referències bibliogràfiques

  • Abrams, Mark (1970). «The Opinion Polls and the 1970 British General Election». Public Opinion Quarterly, 34(3): 317-324.
  • Abramson, Paul R. (2007). «The French Presidential Election of 2007: Was Sarkozy the Condorcet Winner?». French Politics 5(3): 287-291.
  • Anderson, Leslie (1992). «Surprises and Secrets: Lessons from the 1990 Nicaraguan Election». Studies in Comparative International Development, 27(3): 93-119.
  • Ansolabehere, Stephen y Hersh, Eitan (2012). «Validation: What Big Data Reveal about Survey Misreporting and the Real Electorate». Political Analysis, 20(4): 437-459.
  • Bernhagen, Patrick y Marsh, Michael (2007). «The Partisan Effects of Low Turnout: Analyzing Vote Abstention as a Missing Data Problem». Electoral Studies, 26(3): 548-560.
  • Bethlehem, Jelke; Cobben, Fannie y Schouten, Barry (2011). Handbook of Nonresponse in Household Surveys. New York: John Wiley & Sons.
  • Biemer, Paul (2010). «Total Survey Error: Design, Implementation, and Evaluation». Public Opinion Quarterly, 74(5): 817-848.
  • Biemer, Paul y Lyberg, Lars E. (2003). Introduction to Survey Quality. New York: John Wiley & Sons.
  • Bosch, Agustí y Riba, Clara (2005). «Coyuntura económica y voto en España». Revista de Sociología, 75: 117-140.
  • Caballé, Adriá; Grima, Pere y Marco-Almagro, Lluís (2013). «¿Aciertan los sondeos electorales? Análisis sobre la bondad de predicción de los sondeos electorales publicados en la prensa». Revista Española de Investigaciones Sociológicas, 143: 25-46.
  • Callegaro, Mario y Gasperoni, Giancarlo (2008). «Accuracy of Pre-Election Polls for the 2006 Italian Parliamentary Election: Too Close to Call». International Journal of Public Opinion Research, 20(2): 148-170.
  • Crespi, Irving (1988). Pre-Election Polling: Sources of Accuracy and Error. New York: Russell Sage Foundation.
  • Crewe, Ivor (1997). The Polls: Confidence Restored?. Parliamentary Affairs, 50: 569-585.
  • Crewe, Ivor (2001). «The Opinion Polls: Still Biased to Labour». Parliamentary Affairs, 54(4): 650-665.
  • Curtice, John (1997). So How Well Did They Do? The Polls in the 1997 Election. London: Centre for Research into Elecctions and Social Trends.
  • D’Souza, John (2010). Calibrate: A Stata Program for Calibration Weighting. London: Stata User Group.
  • D’Souza, John (2011). Calibrate: Stata module to calibrate survey datasets to population totals, Statistical Software Components S457240. Boston College Department of Economics.
  • Durand, Claire (2008). «The Polls of the 2007 French Presidential Campaign: Were Lessons Learned from the 2002 Catastrophe?». International Journal of Public Opinion Research, 20(3): 275-298.
  • Durand, Claire; Blais, André y Larochelle, Mylène (2004). «The Polls Review. The Polls in the 2002 French Presidential Election: An Autopsy». Public Opinion Quarterly, 68(4): 602-622.
  • Durand, Claire; Blais, André y Vachon, Sébastien (2001). «A Late Campaign Swing or a Failure of the Polls? The Case of the 1998 Quebec Election». Public Opinion Quarterly, 65(1): 108-123.
  • Durand, Claire; Deslauriers, Melanie y Vallois, Isabelle (2015). «Should Recall of Previous Votes Be Used to Adjust Estimates of Voting Intention?». Survey Methods: Insights from the Field, 1-14. Disponible en: http://surveyinsights.org/?p=3543, acceso el 19 septiembre 2017.
  • Escobar, Modesto y Jaime, Antonio M. (2013). «Métodos de imputación múltiple para predecir resultados electorales». En: Mendoza Velázquez, A. (ed.). Aplicaciones en Economía y Ciencias Sociales con Stata. Texas: Stata Press.
  • Escobar, Modesto; Rivière, Jaime y Cilleros, Roberto (2014). Los pronósticos electorales con encuestas: elecciones generales en España (1979-2011). Madrid: Centro de Investigaciones Sociológicas.
  • Fuente, Ángel de la y Domenech Vilarino, Rafael (2015). El nivel educativo de la población en España y sus regiones: 1960-2011. BBVA Bank, Economic Research Department. Madrid: BBVA Research. Disponible en: https://www.bbvaresearch.com/wp-content/uploads/2015/02/ WP_15-07_Educacion.pdf, acceso el 19 septiembre 2017.
  • Fuente, Ángel de la (2015). Series enlazadas de los principales agregados nacionales de la EPA, 19642014. Instituto de Análisis Económico (CSIC). Madrid: FEDEA Research. Disponible en: http:// documentos.fedea.net/pubs/eee/eee2015-07.pdf, acceso el 19 de septiembre 2017.
  • Groves, Robert M. et al. (2013). Survey Methodology. New York: Wiley.
  • Hyndman, Rob J. y Koehler, Anne B. (2005). «Another Look at Measures of Forecast Accuracy». Monash Econometrics and Business Statistics Working Papers 13/05. Monash University, Department of Econometrics and Business Statistics.
  • Jaime, Antonio M. y Sáez Lozano, José L. (2001). El comportamiento electoral en la democracia española. Madrid: Centro de Estudios Políticos y Constitucionales. 
  • Jennings, Will y Wlezien, Christopher (2018). «Election Polling Errors across Time and Space». Nature Human Behaviour, 1.
  • Jowell, Roger et al. (1993). «Review: The 1992 British Election: The Failure of the Polls». Public Opinion Quarterly, 57(2): 238-263.
  • Katz, Daniel (1941). «The Public Opinion Polls and the 1940 Election». Public Opinion Quarterly, 5(1): 52-78.
  • King, Gary et al. (2001). «Analyzing Incomplete Political Science Data». American Political Science Review, 85(1269): 49-69.
  • Lago, Ignacio y Lago, Santiago (2005). «Does the Economy Matter? An Empirical Analysis of the Causal Chain Connecting the Economy and the Vote in Galicia». Economics and Politics, 17: 215243.
  • Lewis‐Beck, M. S (2005). «Election Forecasting: Principles and Practice». The British Journal of Politics and International Relations, 7: 145-164.
  • Liu, Frank C. S. (2014). «Using Multiple Imputation for Vote Choice Data: A Comparison across Multiple Imputation Tools». Open Journal of Political Science, 4: 39-46.
  • Lundström, Sixten y Särndal, Carl E. (2001). Estimation in the Presence of Nonresponse and Frame Imperfection. Sweden: Statistics Sweden.
  • Lynn, Peter (2008). «The Problem of Nonresponse». En: European Association of Methodology (ed.). The International Handbook of Survey Methodology. New York: Lawrence Erlbaum Associates.
  • Lynn, Peter y Jowell, Roger (1996). «How Might Opinion Polls Be Improved? The Case for Probability Sampling». Journal of the Royal Statistical Society: Series A (Statistics in Society), 159(1): 21-28.
  • McEwen, Nicola (2004). «Opinion Polling in Scotland: An Analysis of the 2003 Scottish Parliament Election». Journal of Elections, Public Opinion and Parties, 14(1): 171-190.
  • Mercer, Andrew; Lau, Arnold y Courtney, Kennedy (2018). For Weighting Online Opt-In Samples, What Matters Most? Washington: Pew Research Centre.
  • Orriols, Lluís y Cordero, Guillermo (2016). «The Breakdown of the Spanish Two-Party System: The Upsurge of Podemos and Ciudadanos in the 2015 General Election». South European Society and Politics, 21(4): 469-492.
  • Pavía, José M.; Badal, Elena y García-Cárceles, Belén (2016). «Spanish Exit Polls. Sampling Error or Nonresponse Bias?». Revista Internacional de Sociología, 74(3): e043.
  • Pavía, José M. y Larraz, Beatriz (2012). «Sesgo de no-respuesta y modelos de superpoblación en encuestas electorales». Revista Española de Investigaciones Sociológicas, 137: 121-150.
  • Rama, José (2016). Crisis económica y sistema de partidos: síntomas de cambio político en España. Barcelona: Institut de Ciéncies Politiques i Socials.
  • Rivas, Cristina; Martínez Rosón, María del Mar y Galindo, Purificación (2010). «La imputación múltiple como alternativa al análisis de la no respuesta en la variable intención de voto». Revista Española de Ciencia Política, 22: 99-118.
  • Rivero, Gonzalo (2011). Análisis de datos incompletos en ciencias sociales. Madrid: CIS.
  • Rosenthal, Robert; Rosnow, Ralph L. y Donald B. Rubin (2000). Contrasts and Effect Sizes in Behavioral Research: A Correlational Approach. Cambridge: Cambridge University Press.
  • Rubin, Donald B. (1987). Multiple Imputation for Nonresponse in Surveys. New York: John Wiley & Sons.
  • Sanders, David (2003). «Pre-Election Polling in Britain, 1950-1997». Electoral Studies, 22(1): 1-20.
  • Särndal, Carl E. (2007). «The Calibration Approach in Survey Theory and Practice». Survey Methodology, 33(2): 99-119.
  • Särndal, Carl E. y Lundström, Sixten (2005). Estimation in Surveys with Nonresponse. London: John Wiley & Sons.
  • Sauger, Nicolas (2008). «Assessing the Accuracy of Polls for the French Presidential Election: The 2007 Experience». French Politics, 6(2): 116-136.
  • Sciarini, Pascal y Goldberg, Andreas C. (2016). «Turnout Bias in Postelection Surveys: Political Involvement, Survey Participation, and Vote Overreporting». Journal of Survey Statistics and Methodology, 4(1): 110-137.
  • Shlapentokh, Vladimir (1994). «The Polls a Review the 1993 Russian Election Polls». Public Opinion Quarterly, 58(46302): 579-602.
  • Smith, Fred T. M. (1996). «Public Opinion Polls: The UK General Election, 1992». Journal Of the Royal Statistical Society. Series A (Statistics in Society), 159(3): 535-545.
  • Stata (2015). Stata 14 Base Reference Manual. College Station. Texas: Stata Press.
  • StataCorp (2017). Stata Multiple Imputation Reference Manual. Texas: StataCorp.
  • Sturgis, Patrick; Allum, Nick y Brunton‐Smith, Ian (2009). «Attitudes Over Time: The Psychology of Panel Conditioning». En: Groves et al. (eds.). Methodology of Longitudinal Surveys. New York: Wiley.
  • Sturgis, Patrick et al. (2016). Report of the Inquiry into the 2015 British General Election Opinion Polls. London: British Polling Council.
  • Traugott, Michael W. (2005). «The Accuracy of the National Preelection Polls in the 2004 Presidential Election». Public Opinion Quarterly, 69(5 SPEC. ISS.): 642-654.
  • Urquizu, Ignacio (2005). «El voto oculto en España». Revista Española de Ciencia Política, 13: 119156.
  • Varela, Jesús et al. (1998). «Estimación de la Respuesta de los ‘No Sabe/No Contesta’ en los Estudios de Intención de Voto». Revista Española de Investigaciones Sociológicas, 83: 269-287.
  • Voogt, Robert J. J. y Saris, William E. (2003). «To Participate or not to Participate: The Link Between Survey Participation, Electoral Participation, and Political Interest». Political Analysis, 11(2): 164-179.
  • Voss, Stephen; Gelman, Andrew y King, Gary (1995). «Preelection Survey Methodology: Details from Eight Polling Organizations, 1988 and 1992». Public Opinion Quarterly, 59: 98-132.
  • Worcester, Robert (1996). «Political Polling: 95% Expertise and 5% Luck». Journal of the Royal Statistical Society. Series A (Statistics in Society), 159(1): 5.
Fuente de los datos: Dialnet