A Benchmarking Forecast of the 2013 Bundestag Election Mark Kayser and Arndt Leininger Hertie School of Governance, Berlin 31 July 2013 Election forecasts are too serious a business to be left to pollsters alone. 1 --(Gschwend und Norpoth 2001) With the German federal election roughly two months away, forecasts and prognostications about who will win are attracting considerable attention both with Germany and beyond. Leaving casual punditry aside, the more serious forecasts are nearly uniformly based on opinion polls. While polling certainly improves on the anecdotal stories and opinions of media experts, it also has its own shortcomings. Assembling and properly weighting samples in the age of mobile telephones is a challenge and even when that can be properly done, pollsters still face problems of respondents giving false replies (who admits voting for the NPD?) or most problematically, changing their minds before election day. Polls offer a good snapshot in time but when the election is distant, they predict outcomes less well. We offer an alternative: a theory-driven empirical model of election outcomes that draws on previous election outcomes (Table 1); characteristics of the government and of voters; and, most originally, the relative economic performance of Germany ( benchmarked growth) in comparison to the three other most important economies in Europe, France, the UK and Italy. The ability of polling agencies to forecasts elections that are months or weeks away should not be overstated. Consider the January 2013 state election in Lower Saxony for an illustration of the pitfalls entailed in polling. Vote intention polls before the election underestimated the FDP vote share by a hefty 5 percentage points, roughly half of its 9.9% vote share. For the last three Bundestag elections the Politbarometer projections of the vote share of the parties of the outgoing coalitions provided by the Forschungsgruppe Wahlen for German public broadcasting station ZDF have been off by an average 4.2 percentage points. Because an empirical model like ours does not rely on opinion polls, it can be estimated well in advance of the election. The largest threat to the accuracy of its estimates is the accuracy of its economic and political predictors. Economic forecasts, however, are fairly accurate and our model only requires a single political variable partisan identification to be predicted. Of course, forecasting models like ours rely on some assumptions too, although, we argue, less heroic ones. First, we assume that no election really is unique and, second, that the importance of different factors affecting vote choice is constant over time. We rely on electoral research to construct our model. 1 Wahlprognosen sind eine zu ernste Sache, als daß man sie den Meinungsforschungsinstituten überlassen könnte. 1
Our model Electoral forecasting of the sort presented here, just like polling, was pioneered in the context of US presidential elections. While a small cottage industry has developed a variety of models that perform rather well in the United States (See, for example, the 13 forecasts in October 2012 issue of PS: Political Science and Politics) election forecasting in Germany is still in its infancy. Nevertheless, it is striking that to the best of our knowledge our benchmarking model is only the third model to be proposed for forecasting German federal elections the others being the Chancellor model first proposed by Norpoth and Gschwend (2001) who also provide a prediction for the upcoming election (2013) and Jérôme, Jérôme-Speziari and Lewis-Beck (2013). Most people are interested in forecasts because they want to know who will win the election. However, in a multi-party system like Germany s who will win also depends on the outcome of postelection coalition bargaining. Therefore it makes more sense not to look at winners or losers but to focus on parties vote shares. Specifically we focus on the vote share (to be) obtained by the outgoing governing coalition. The coalition vote share is the percentage of the popular vote received by the parties forming the governing coalition. This is usually the sum of the vote shares of two or more parties only once (in 1961) has Germany seen an outgoing single party government and even then only when one counts the CDU and CSU as one party. We focus on the coalition s vote share, rather than individual parties, because it is of the greatest substantive interest. With this forecast, we are able to predict whether the same government will continue in power. Grand coalitions are the exception here. They are mere coalitions of necessity ( Staatsräson ) when no other options involving a larger and one or more smaller parties seem feasible. Usually neither coalition partner has an interest in continuing the coalition beyond the next election. Furthermore, voters have no credible alternative government in opposition. For these reasons we calculate the vote share of the outgoing grand coalition as the vote share of the larger party in that government. This was the CDU/CSU in both of Germany s grand coalitions in 1969 and 2009. Having explained our dependent variable that we intend to predict, we now turn to the explanatory variables in our model. There are four: (1) the vote share received by the current governing parties in the previous election, (2) the proportion of people identifying with one of the governing parties, (3) the difference between Germany s growth rate and the benchmark, i.e., the average of the growth rates in France, the UK and Italy, and (4) the (log of the) number of terms a government has been in power. We include the voter share of the current incumbent parties in the previous election (even if they were not in government then) to form a baseline prediction. Past outcomes are a strong predictor of future outcomes, so controlling for previous vote share effectively focuses the other predictors on changes from the previous vote share. The combined vote share of the parties making up the outgoing government correlates strongly with their results in the previous election (r = 0.88). This is also because many people exhibit strong partisanship leading them to vote for the same party in successive elections. 2
Our second variable, party identification, captures the proportion of respondents expressing an attachment with one of the governing parties. Our data come from the Politbarometer 2, we average responses from monthly polling in the 6 months leading up to the election until 2 months before the election for an election in September this would be the months February till July. Party identification does not imply a formal attachment but, rather, simply feeling close to a party. However, as the number of people with a party identification still changes over the medium term, the proportion of people identifying with one of the governing parties correlates significantly with the vote (r = 0.61). In the US setting, partisan identification is often the strongest predictor of vote choice (Campbell et al. 1960). In Europe, it is comparatively weaker but nevertheless a strong predictor (Dalton und Wattenberg 2000; Kayser und Wlezien 2011). More specifically, we take the average partisan identification for the governing parties in the six months before the given election. Since monthly party ID data only began in Germany in 1980 we can only use elections since then in our estimation. The third variable is the most novel and also the namesake of our benchmarking model. We calculate Germany s growth, as benchmarked against the three next most important economies in Europe: the UK, France and Italy. Data are from the World Bank s World Economic Outlook which goes back to 1980 and includes a forecast for 2013. Implicitly by using the deviation of German growth rates from the average of British, French and Italian growth, we are presuming that voters judge the state of the economy relative to that of other countries. Evidence of such benchmarking across borders comes from Kayser and Peress (2012) who explain the phenomenon with evidence that the media report more positively on the economy when it is outperforming that of comparison countries. This measure of relative economic performance could be of special importance to the forecast for the 2013 election since German growth is sluggish but looks better when compared to that of other European states suffering from the aftermath of the financial and Euro crises. Lastly, we rely on the empirical regularity that governments, on average, loose support the longer they remain in office (Paldam 1986). The major governing parties (CDU/CSU or SPD) in Germany have on average lost 3.2 percentage points per term. We capture this with the log of the number of terms that a government has been in office. Model estimates Putting all variables in one regression model estimated over the elections 1980-2009 we can explain 99% of the variance in the vote share of the outgoing government in the past 9 elections (see Table 2). All coefficients are statistically significant and have the expected sign. Vote share decreases in the number of terms the major governing party has been in power. As expected, it increases in the proportion of people identifying with one of the governing parties and the relative performance of the national economy. The good fit of our model makes us confident that it is able to produce reasonable predictions. However, only once we predict elections outside our sample do we get an idea how good our model really is. The 2013 election will provide an essential test in that regard. But we do not need to wait until September to test our model s ability to make out-of-sample predictions. By omitting one election, re-estimating the model on the remaining elections and calculating a prediction using the 2 We thank the Forschungsgruppe Wahlen for providing us with their 2013 aggregate partisan identification data. 3
values of the omitted observation we can create synthetic out-of-sample predictions. We do this for all 9 previous elections, we compare our prediction to the actual outcome, square the differences, average them and take the square root to obtain the root mean square error (RMSE). This gives us an estimate of the average error of our model in out-of-sample forecasting. Figure 2 plots the actual vote shares received by the outgoing government against our prediction. The farthest we are off is 1.8 percentage points in 2005; in 1983 we get within 1 tenth of a percentage point of the actual result. The RMSE for our model is 1.4 percentage points which considering that the model only rests on 9 previous elections, compares rather favorably to standard errors of the regression in surveys involving many more observations. Our coefficients remain stable across all out-of-sample estimations showing that our results are not unduly influenced by outliers and that the effects of our explanatory variables are, as we expected, stable over time (Figure 3). Our forecast for 2013 When we regress the vote share of the outgoing government on our four explanatory variables we obtain coefficient estimates that allow us to calculate the 2013 vote share of the outgoing government by using up-to-date values for our explanatory variables. Inputting 2013 values for our explanatory variables into the below equation we obtain a point prediction of 47.05% as the combined vote share of the CDU/CSU and FDP in the 2013 Bundestag election. h = 8.708 + 1.025 h + 0.276 + 0.930 h h + 8.881 ( ) Using the RMSE calculated from our out-of-sample predictions we can calculate the probability of the coalition obtaining a majority of seats in parliament necessary to continue in office. As this year s change to the electoral system in Germany basically eliminates distortions of the vote-seat relationship arising from so called Überhangmandate we only have to worry about the votes obtained by parties who will not be represented in parliament. Current polling sees the sum of votes going to the Pirates, Alternative für Deutschland and other fringe parties most likely not to surpass the 5%-threshold at 8 (Forschungsgruppe Wahlen 24.07.2013, Infratest Dimap 25.07.2013) to 9.5 (Allensbach 12.07.2013) percent. We assume that the FDP and Die Linke will surpass the 5-percent threshold. The latter is consistently well above the 5-percent threshold while the former will surely again profit from lent votes from CDU/CSU-voters which polls have difficulty predicting. Considering the substantial error in poll based projections 2 months ahead of the elections this gives us a range of 6 to 12 percentage points. If the polling for these minor parties is correct, however, about 45.5 percent of the vote should suffice for Mrs. Merkel to continue the coalition of CDU/CSU and FDP. Our point prediction already is above this threshold; taking into account the statistical error inherent in the forecast, there is a 83.18% probability that the current coalition will have a majority in the next parliament. Conclusion Based on an analysis of past election results we have offered a theory- driven empirical model to predict the outcome of the upcoming Bundestag election. Our model draws on previous election outcomes, characteristics of the government and of voters and, most originally, the relative economic performance of Germany ( benchmarked growth) in comparison to the two other most important economies in Europe, France, the UK and Italy. Our approach differs from simple polling as we rely on data available well in advance of the election. 4
We predict that the current coalition of CDU/CSU and FDP will receive a vote share of 47.05% on September 22 nd. Taking into account the stochastic nature of predictions and that the likely vote share needed to obtain a governing majority parliament will be around 45.5% we also calculate the probability for the current coalition to stay in power: 83.18 percent. Current polls of vote intention place the coalition between 45 (Emnid 28 July 2013) and 46.5 percent (Allensbach 12.07.2013). Our prediction suggests that polling firms can hope to be less far off this time. One other model, provided by Norpoth and Geschwend (2013) predicts a significantly higher vote share of 51.7%. Jérôme, Bruno, Véronique Jérôme-Speziari and Michael S. Lewis-Beck (2013) predict individual party vote shares and a sum of 47 % for the current coalition. In September we will know which prediction was closest to the actual result. But already we know that predicting future election outcomes can and should be about more than just polls or prognostication. Electoral forecasting is promising because it is theory based and aims to capture the fundamentals of voting theory uncovered by electoral research. It promises to be less prone than polls to be disturbed by idiosyncratic events during the election campaign. Political scientists should feel encouraged to engage in forecasting to put their theories to the hardest test possible, predicting future outcomes. Theoretically informed forecasts also provide a baseline (a sort of expected normal vote) against which the actual election can be judged, so even if a forecast is off sometimes it will have explanatory value. Election forecasting as presented here provides an alternative and competition to traditional approaches of punditry and polls. We hope that they will receive even more competition in the future as every new election extends the dataset on which predictions can be based. References Campbell, Angus, Philip E. Converse, Warren E. Miller, und Donald E. Stokes. 1960. The American Voter: Unabridged Edition. Chicago: The University of Chicago Press. Dalton, Russell J, und Martin P Wattenberg. 2000. Parties Without Partisans: Political Change in Advanced Industrial Democracies. Oxford; New York: Oxford University Press. Gschwend, Thomas, und Helmut Norpoth. 2001. Wenn am nächsten Sonntag... : Ein Prognosemodell für Bundestagswahlen. In Wahlen und Wähler: Analysen aus Anlass der Bundestagswahl 1998, herausgegeben von Hans-Dieter Klingemann und Max Kaase, 473 499. Wiesbaden: Westdeutscher Verlag. Jérôme, Bruno, Véronique Jérôme-Speziari, und Michael S. Lewis-Beck. 2013. A Political-Economy Forecast for the 2013 German Elections: Who to Rule with Angela Merkel? PS: Political Science & Politics 46 (03) (Juni 21): 479 480. doi:10.1017/s1049096513000814. Kayser, Mark Andreas, und Christopher Wlezien. 2011. Performance pressure: Patterns of partisanship and the economic vote. European Journal of Political Research 50 (3) (Mai): 365 394. doi:10.1111/j.1475-6765.2010.01934.x. Kayser, Mark Andreas and Michael Peress. 2012. "Benchmarking across Borders: Electoral Accountability and the Necessity of Comparison." American Political Science Review, 106(03), 661 684. doi:10.1017/s0003055412000275. Norpoth, Helmut, und Thomas Gschwend. 2013. Chancellor Model Picks Merkel in 2013 German Election. PS: Political Science & Politics 46 (03) (Juni 21): 481 482. doi:10.1017/s1049096513000802. Paldam, Martin. 1986. The distribution of election results and the two explanations of the cost of ruling. European Journal of Political Economy 2 (1): 5 24. doi:10.1016/s0176-2680(86)80002-7. 5
Appendix Table 1: Elections in model Year Outgoing Government Coalition Outgoing government vote share (%) 1980 SPD and FDP 53.5 1983 CDU/CSU and FDP 55.8 1987 CDU/CSU and FDP 53.4 1990 CDU/CSU and FDP 54.8 1994 CDU/CSU and FDP 48.4 1998 CDU/CSU and FDP 41.3 2002 SPD and Greens 47.1 2005 SPD and Greens 42.3 2009 CDU/CSU and SPD 33.8 2013 CDU/CSU and FDP 47.05 (forecast) Figure 1 : Predictors of the vote 6
Table 2: A regression model of past elections to predict future elections Predictors Coefficient (S.E.) Previous Vote Share 1.025*** (0.0544) Party ID 0.276** (0.0563) Benchmarked Growth 0.930* (0.224) Log Terms -8.881** (1.295) Constant -8.708* (2.724) Observations 9 R-squared 0.993 Adj. R² 0.986 RMSE 1.424 Durbin-Watson d 2.561 *** p<0.001, ** p<0.01, * p<0.05 calculated from out-of-sample predictions Note: Model estimated on elections 1980-2009 Figure 2: Actual and predicted vote share 35 40 45 50 55 55.78 53.5 52.55 55.8 53.28 55.1 53.4 54.8 48.22 48.4 40.18 47.1 46.23 44.13 41.3 42.3 32.94 47.05 33.8 1980 1983 1987 1990 1994 1998 2002 2005 2009 2013 Actual vote share Forecast Predicted vote share Vote share of outgoing governing coalitions and corresponding point predictions from 'out-of-sample' prediction ^ 7
Figure 3: Stability of coefficient estimates -.5 0.5 1 1.5 2 2.5 1980 1983 1987 1990 1994 1998 2002 2005 2009 2013 Prev. Election Vote Share Benchmarked growth Party Identification Coefficient values and 95% confidence intervals obtained in 'out-of-sample' prediction 8