Forecasting the 2002 Elections: Lessons from a Political Economy Model

Jérôme, Bruno; Jérôme-Speziari, Veronique

doi:10.1057/9780230523791_11

Cited by 14 publications

(10 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…With respect to the pre‐election polls just before that April contest, average error was about six percentage points. For IFOP, perhaps the most widely known firm, this average error rose to 7.7 per cent (Jérôme and Jérôme‐Speziari 2004, 182–185). The models also did badly.…”

Section: How French Models Have Faredmentioning

confidence: 99%

“…The French‐named ‘Iowa Model’ incorrectly forecast a narrow second‐round victory for Jospin (Fauvelle‐Aymar and Lewis‐Beck 2002). After‐the‐fact forecasts for 2002 were rendered by Bruno Jérôme and Veronique Jérôme‐Speziari (2004) and by Eric Dubois and Christine Fauvelle‐Aymar (2004), in pooled analyses. For example, in the former, the after‐the‐fact forecast was 42.4 per cent of the first‐round presidential vote for the Plural Left, which actually received 42.9 per cent (Jérôme and Jérôme‐Speziari 2004, 192).…”

Section: How French Models Have Faredmentioning

confidence: 99%

“…One difficulty it shares with other French efforts is conversion of vote forecasts to seat forecasts (Dubois and Fauvelle‐Aymar 2004, 219; Jérôme and Jérôme‐Speziari 2004, 194–195). The swing‐ratio equation predicting final seat total from first‐round vote share (regional level) yields a moderate fit (adj.…”

Section: How French Models Have Faredmentioning

confidence: 99%

See 2 more Smart Citations

Election Forecasting: Principles and Practice

Lewis‐Beck¹

2005

The British Journal of Politics and International Relations

174

114

View full text Add to dashboard Cite

To forecast an election means to declare the outcome before it happens. Scientific approaches to election forecasting include polls, political stock markets and statistical models. I review these approaches, with an emphasis on the last, since it offers more lead time. Consideration is given to the history and politics of statistical forecasting models of elections. Rules for evaluating such models are offered. Examples of actual models come from the United States, France and the United Kingdom, where this work is rather new. Compared to other approaches, statistical modelling seems a promising method for forecasting elections.

show abstract

Section: How French Models Have Faredmentioning

confidence: 99%

Section: How French Models Have Faredmentioning

confidence: 99%

See 1 more Smart Citation

Election Forecasting: Principles and Practice

Lewis‐Beck¹

2005

The British Journal of Politics and International Relations

174

114

View full text Add to dashboard Cite

show abstract

“…More precisely, UNEM is the difference in the departmental unemployment rate between the quarter prior to the election and four quarters before (that is on one year). This measure is frequently retained in the French vote-functions literature (see for example Jérôme and Jérôme-Speziari, 2004). We expect a negative sign for the coefficient of UNEM since this variable traduces a discontent.…”

Section: The Modelmentioning

confidence: 99%

More on the Seasonal Determinants of Turnout: Holidays and French Presidential Elections

Dubois

Lakhdar

2007

Fr Polit

View full text Add to dashboard Cite

“…The first models used aggregated national data. Since the beginning of the 1990s, several studies such as Jérôme, Lewis-Beck (1999, 2003) and Dubois (2003, 2005) for legislative elections, Dubois (2002), Jérôme, Jérôme-Speziari and Lewis-Beck (2003) and Jérôme et Jérôme (2004a) for presidential elections, Jérôme and Jérôme (2000) for regional elections and for municipal elections show the relevance of using national and local data (pooled time series models). 2 French European elections have been relatively neglected.…”

Section: Introductionmentioning

confidence: 99%