The state-by-state political economy model, developed by Bruno and Véronique Jérôme, is a pooled time series model that uses data disaggregated below the national level. The model thus builds on prior work by various researchers such as Rosenstone (1983), Holbrook (1991), and Campbell (1992). In addition, Jérôme and Jérôme use some variables that are inspired by their experience from French elections (e.g., Jérôme, Lewis-Beck and Lafay, 1993; Jérôme, Jérôme-Speziari and Lewis-Beck, 1999; Jérôme and Jérôme-Speziari, 2004; 2007), notably:
- The President’s job approval is taken as credibility index with two possible impacts on the vote:
- When the President is running for the second time and
- When the incumbent candidate is a “newcomer”,
- Unemployment rate is taken as the most significant variable of the economic trends,
- Two partisan representation indexes are built. They are gathering States Partisan pattern effects. For Democrats or Republicans, Jérôme and Jérôme distinguish historical strongholds (partisan stability over 1952-2012) from those which are considered as “new” strongholds (over 1980-2012).
- the opposition Nominee Vote share at primaries is included in the concerned States, asserting that the higher his or her score is, the more weakened the incumbent candidate is.
The model reads as:
Presidential Vote (Incumbents) i,t = Constant +
(Incumbents credibility)t-n +
(Partisan pattern)i,t-n +
(Politics and institutions)i,t-n +
(President’s local strongholds)i,t-n +
(Local peculiarities)i,t-n + Error term
A pooling process combining cross-section and time series data is then used as a forecasting method. That is, Jérôme and Jérôme first run a vote function, combining observations from 50 American states (+DC) over the 1980-2012 election years (N = 459 observations). Then, they use the (OLS) estimated parameters of the vote function to provide a forecast for the popular vote in each state. Finally, they use they state level predictions to generate an electoral vote forecast.
The state-by-state political economy model correctly predicted the two-party result in 2004 (Jérôme & Jérôme-Speziari, 2004), 2008 (Adaken, 2008; Pottier, 2008) and 2012 (Jérôme & Jérôme-Speziari, 2012; 2013).
Adaken, Y. (2008). La simumation des économistes donne Obama gagnant haut la main, www.lexpansion.com, 10 octobre.
Pottier, J.-M. (2008). Barack Obama, Chouchou des prévisionnistes, www.challenges.fr, 31 octobre.
Campbell, J.E. (1992). Forecasting the Presidential Vote in the States. American Journal of Political Science, 36(2), 386-407.
Holbrook, T.M. (1991). Presidential Elections in Space and Time. American Journal of Political Science, 35, 91-109.
Jérôme, B. & Jérôme-Speziari, V. (2004). Bush l’emporterait sur Kerry. La lettre deL’Expansion n°1730 , 25 octobre: p.2.
Jérôme, B. & Jérôme-Speziari, V. (2007). Prévision de la présidentielle 2007 : qui sera aux commandes du pays ?, in Lechypre E. France, l’Equation à 7 inconnues, L’Expansion, janvier, n°715, p.28.
Jérôme B., Lewis-Beck M.S. & Lafay J.D. (1993). Les prévisions des modèles politico-économiques, in Lafay, Cheminement du futur, Le Figaro Economie, (19 mars).
Jérôme, B. & Jérôme-Speziari, V. (2013). Why the State-by-State Political Economy Model Did It Right, PS: Political Science and Politics, 46(1).
Jérôme B. & Véronique Jérôme-Speziari (2012). Forecasting the 2012 US Presidential Election: Lessons from a State-by-State Political Economy Model. PS: Political Science and Politics, 45(4): 663–68.
Jérôme, B. & Jérôme-Speziari, V., Lewis-Beck, M. S. (2003). Reordering the French Election Calendar : Forecasting the Consequences for 2002. European Journal of Political Research, Kluwer Academic Publishers, Amsterdam , Vol.42, Issue 3 : 425 – 440, May 2003.
Jérôme, B., Jérôme-Speziari V. (2004). Forecasting the 2002 Election: Lessons from the Political Economy Model, in M.S. Lewis-Beck (ed.), The French Voter before and after the 2002 Elections., Palgrave.
Jérôme, B., Jérôme-Speziari V. & Lewis-Beck, M.S., (1999), Polls fail in France : Forecasts of the 1997 Legislative Election. International Journal of Forecasting, North Holland Elsevier, 15, 163-174.
Rosenstone, S.J. (1983), Forecasting Presidential Elections, Yale University Press, New Haven an London.