Showing posts with label elections. Show all posts
Showing posts with label elections. Show all posts

Monday, 18 September 2017

Angela Merkel wins German election



After my spectacular success as UK election pollster let my try my luck with a prediction for the elections here in German next week Sunday: Angela Merkel will win the election and stays Chancellor. I admit that it would have been more fun to make a claim that goes against the punditry, but that is harder to do for Germany than for the UK or the USA; the quality of German (public) media is quite high. The pundits also do not have a hard time this election, the only question is who is Merkel going to govern with and that depends on details we will only know on election night.

[UPDATE on the eve of the election. Something I did not think of because I have not heard anyone talk about it is that Merkel may step down when her party loses more than 5% and the coalition loses more than 10%. She took quite some time considering whether she would run again. My impression is that that was not just theatre; it is a tough job. Losing the election may well be the right excuse to hand power to the next generation.]

Germany is a representative parliamentary democracy. The voters select their representatives in parliament, like in the UK, and parliament elects the prime minister (Bundeskanzler). The prime minister is the most powerful politician, although officially ranked third after the president (Bundespräsident) and the president of the parliament. The advantage of this system is that when you notice your leader is an incompetent ignorant fool with no interest in working, you can get rid of them. Not to end up with a power vacuum, a new prime minister has to be elected to remove the old one, just voting against the old one is not enough.


Advertisement & song for a major supermarket chain. The title literally translated is: "Super horny", but more accurate is: "terrific". On the other hand, we have less gory violence on TV than the USA.

Germans get two votes: one for their local representative, just like the districts in the UK or USA, and a second vote for a party. This way you have politicians that represent their district, which some people seem to see as important; I have never understood why. The second vote determines the proportions in parliament. Parties make lists of candidates and they are added to the directly elected candidates to get a proportional result. This way all voters count, parties have to campaign everywhere and [[gerrymandering]] does not help. Win, win, win.

The only deviation from a representative result is that there is an [[election threshold]] of 5%. If a party gets less than 5%, their votes are unfortunately lost, except for elected direct candidates. In the last federal election 16% of the votes were lost that way. The election threshold should reduce the number of parties, but also conveniently limits competition for the existing parties.

Political parties

The latest polls are shown below.


Election polls over the last 4 years. For comparison the results of the 2013 election were: CDU/CSU: 41.5%, SPD: 25.7%, Greens: 8.4%, FDP: 4.8%, Die Linke 8.6%, Pirate party: 2.2%, AfD: 4.7%.

It is expected that six parties will cross the election limit. The largest party will be the Christian Democrats or Conservatives of Kanzler Merkel. They actually are two parties who caucus together in parliament: The Christian social Union (CSU) running in Bavaria and the Christian Democratic Union (CDU) in the rest of Germany.

The second largest party will be the Social Democrats, similar to Labour in the UK. The upward jump in spring this year of almost 10% almost made the party as large as the Christian Democrats. This was when their new party leader Martin Schulz was elected and he suggested to again treat unemployed people as humans and get rid of the policy package called [[Harz IV]].

This peak went away when Schulz explained that actually he only wanted to make a few small Clintonite tweaks. This Harz IV package was made by Germany's Tony Blair, the neo-liberal Gerhard Schröder who is now living on Vladimir Putin's pay check. The party strategists must have seen the movement in the polls, but threatening the middle class that they can fall really deep into poverty if they do not conform was apparently more important to them than being Social Democrats.


The Doctors: Man & Woman. die ärzte - M&F

The four small parties have about the same size this time. It is the policy of the Conservatives to be a sufficiently nationalistic big tent party to keep purely racist parties below the 5%, but this time the anti-Muslim party Alternative for Germany (Alternative für Deutschland) will likely make it into parliament. It started with a Euro currency sceptical party whose leader was open to racists to pass the 5% threshold and then got kicked out by them.

The latest polls show a few percent less for the two main parties and the Alternative for Germany at or above 10%. The easily exited punditry is immediately talking about 15 or 20%. People tend to worry whether people answer polling questions well when it comes to racist parties. The evidence shows that there is no bias, but that the noise error can be larger, especially for new parties. Racist parties typically are new parties as they do not last long being a coalition of unreasonable people with often a violent criminal past.

The other right-wing small party is the pro-business party FDP. They are officially classical liberals, but unfortunately in practise often crony capitalists. They got kicked out of parliament in the last election because their coalition government with the Conservatives was so disastrous. Their new leader Christian Lindner resurrected the party by stressing the pro-human parts of their liberal heritage. All these terms should be interpreted in a German perspective: Not even this classical liberal party would deny people health care and Barrack Obama could be a good replacement for Lindner.

On the left we have we a party called "The Left", Die Linke. They are mostly the Social Democrat party the SPD once was. Their main campaign promise is to get rid of the Harz IV package. However, they were born out of the communist party of Eastern Germany, which has left its traces. Due to old ties and maybe kompromat they are very pro-Russia. They are against NATO and German military actions, but were not particularly worried about the Russian occupation of Crimea. Because of their communist past and officially because of their foreign policies, most other parties are not willing to govern with them. It could be that this taboo will be broken this election or the next; about time almost three decades after the fall of communism.


Election billboard of the German Green party: Environment is not everything, but without the environment everything is nothing.

The German Greens are traditionally seen as part of the left being born out of the hippy movement, but for a Green party they are very conventional, the old geezers have become much like the parents they once revolted against. Half of the party would like to be in the middle and the party is flirting with the idea of a coalition government with the Conservatives. In one of the most conservative German states Baden-Württemberg the Green politician Winfried Kretschmann leads the coalition government with the Christian Democrats. I mostly mention this to emphasize that politics in Europe is a bit different than in corrupt Washington.

Coalitions

I am not expecting any large changes in the last week and German polls are normally quite good.

[UPDATE.
Now the the preliminary final result is in we can see that the last polls were reasonably good. The uncertainty is given as 2 to 3% and was met. Still the difference for the Conservatives is rather large and the larger percentage for the racist party sad.
PartyPollingResultDifference
Conservatives (CDU/CSU) 35.8%33.0%-2.8%
Social Democrats (SPD) 21.8%20.5%-1.3%
Greens (B'90/Grüne)  7.8% 8.9%+1.1%
Classical liberals (FDP) 9.6%10.7%+1.1%
The Left (Linke)  9.5% 9.2%-0.3%
Racists (AfD) 11.0%12.6%+1.6%
Others  4.6%
]

Theoretically Schulz could discover his inner Jeremy Corbyn and still announce to get rid of Harz IV, but even that would likely not change the coalition options much. The results will be very similar to those of 2013, but the two big parties will likely lose a few percent and the AfD and the FDP will likely pass the threshold this time. Because of this this 10% less votes will be wasted and the other parties will get less seats for the same percentage of votes. Thus all current parties will likely lose seats.

Currently the Bundeskanzler is Angela Merkel and she is likely the next one as well. There is no limit to how often one can become Bundeskanzler. Helmut Köhl did it four times. Merkel already made coalition governments with the social democrats (SDP), the FDP and currently again the SPD. Each time her coalition partner suffered clear losses.

To govern normally a coalition of parties is needed. The best part of the election night in 2013 was to look at the face of Angela Merkel when the exit polls suggested she might have a majority without any coalition partner. She clearly did not look forward to having to implement her platform without being able to blame the coalition partner for softening it.

The right parties (CDU and FDP) will not want to make a coalition with the racists (AfD). The left parties (SPD and Greens) will likely not be willing to make a coalition with the former communists (Die Linke) and this coalition is also likely not big enough. Also a coalition of Social Democrats, Greens and classical liberals is likely too small.

So whatever coalition is possible, it will include the Christian Democrats of Merkel. If it is possible to make a coalition with the classical liberals she will do so. This is likely only possible if the AfD stays below the election threshold. Due to this threshold it would perversely be best for people on the left if the racists get into parliament.

If a coalition with the liberals is not possible Merkel will most likely try to build a coalition with the Greens, a new combination federally, but a coalition that has been tested in the German states the last years as preparation and works.

Maybe I do have one complaint about the German punditry, they keep on talking about a coalition of Conservatives, classical liberals and greens (CDU/CSU, FDP, Greens). I understand that the small parties like such speculation to keep themselves in the news and having more options improves their negotiation position, but I do not see this coalition as a realistic option, although not fully impossible. The members of the Greens will have to vote on the coalition agreement and I see it as highly unlikely that they would approve such a right-wing government.

Whether any of these options work will depend on the last few percent of votes and we will thus have to wait for election night. The most likely result, which is always possible, but not a popular option, will be a continuation of the current ruling coalition of Christian Democrats and Social Democrats. Both parties will probably lose votes and not be keen to continue the coalition and likely loose again in four years.


An election billboard of the racists of Alternative for Germany above a sign saying "liars have tall ladders". A bit unfair: racists parties are not particularly popular after what they did to Germany and the world, so they have to hang their posters up high lest they get vandalized. Parties are allowed to advertise on the streets for free to make money in politics less important. They also get free time on public television.

Climate Change

A main environmental group (BUND) has made a comparison of the party platforms on climate change. No German party denies climate change, except for the racist party. It makes sense that a party that is willing to shoot refugees to kill at the border is also willing to destroy their existence and kill them at home. In their party platform they go full Trump and deny man-made climate change and call for higher CO2 concentrations. They are also a Trumpian party in the sense that they get a little help from foreign racists and Moscow in their quest against free and open societies. As typical for these kind of  parties the candidates are mostly incompetent and many have criminal records.

The two big parties have deep ties with big industry and the last four years have seen a reduction in ambitions to fight climate change. As a consequence the CO2 emission goals for 2020 will be hard to reach for the next government.

The classical liberal FDP reject solutions to climate change beyond the European Emissions Trading System, which makes sense from their perspective, however, it does not work and Germany alone cannot fix it. Thus this easily leads to doing nothing in practice.

The Greens are naturally best on climate change. After ending nuclear power, they now want to end coal power in 2030 (Kohleausstieg). Angela Merkel indicated her willingness to form a coalition by writing in to the Conservative platform: an end to lignite coal power (Braunkohleausstieg).

Bonn

As an example of how the electoral system works let's consider Bonn, where I live (although I am not allowed to vote because the German parliament may have to vote whether to go to war with The Netherlands; as EU citizen I can vote locally.) If you, as reader of this blog, care mostly about the environment your best option for your direct (first) vote is the social democrat Ulrich Kelber. He is a strong pro-environment politician within the SPD, but the coal-NRW SPD did not put him on the party list, so he has to get a direct mandate. For this reason Campact is campaigning for Kelber.

In the last election Kelber won the direct votes, while the Christian Democrats got more of the party (second) votes. The Christian Democrat from Bonn Claudia Lücking-Michel still got elected via the list, something that is again likely as she has place 27 on the party list of North Rhine-Westphalia.

Your second vote would then be The Greens. The Green candidate Katja Dörner is third on the party list and will thus likely be elected via the party list although she has no chance to get a direct mandate in Bonn. Thus if Kelber gets the direct mandate, Bonn would likely be represented by the same three members of parliament as now. Because of the party lists, many districts have more than one candidates, but three is quite a lot.

This electoral system also distributes the power. The local/district party members determine their direct candidates. The state party members determine the party lists. The federal party only determines the leading candidate.

Related reading

Carbon Brief: German election 2017: Where the parties stand on energy and climate change.

If you are still undecided who to vote for, the Wahl-O-Mat can help you. (In German)

Where the donor money goes: Parteispenden - Wer zahlt? Wie viel? An wen? (In German)

Sonntagfrage Aktuell: Graph with the latest polls. (In German, but not many words)

The Guardian: Angela Merkel races ahead in polls with six weeks to go.


* Top photo Girls'Day-Auftaktveranstaltung am 26.04.2017 in Anwesenheit von Bundeskanzlerin Angela Merkel im Bundeskanzleramt, Berlin by Initiative D21 used under a Creative Commons Attribution-NoDerivs 2.0 Generic (CC BY-ND 2.0) license.

Photo Bundestagswahl 2017 #btw2017 Die Grünen by Markus Spiske used under a Creative Commons Attribution 2.0 Generic (CC BY 2.0) license.


Tuesday, 6 June 2017

Comrade Trend predicts the UK general election outcome

Poll whisperer Nate Silver himself just predicted that in the UK elections the conservatives would win by 7 %. My prediction is 2 %.

The prediction of Silver is a simple average of the last polls of the ten main polling organisations. He uses the same data as I do, kindly gathered by the volunteers of Wikipedia, who also made the plot below.



The statistics normally used to estimate the outcome of elections assumes that there is a fixed value and the surveys are noise around this value. In this case you have to average (in a smart way) to remove the noise of the surveys and get a better estimate of the fixed value.

Wikipedia uses the same assumption to compute the curve of the running average of all polls and takes the average over the 10 most recent polls. The distance between the curves of the Conservatives and Labour in the Wikipedia graph above is about 8 %.

Comrade Trend

However, if the polls are moving it typically keeps on moving in the same direction. Germans call this Genosse Trend, Comrade Trend. If you are going up in the polls Comrade Trend is a great friend.

This could be because it takes time until "everyone" has heard the news, only small part of the population is a news junky. You may also want to wait whether refuting information comes in some time later, whether a campaign changes its position or you may want to talk about the news with your family and friends.

It takes some time until people have found time to read the manifestos (Conservative | Labour). Hopefully many do, there is a real choice this time. Also the strengths and weaknesses of the campaigns mostly stay the same during the campaign. Each time Theresa May openly refuses to answer basic policy questions she loses voters, at least for people like me.

Comrade Trend seems like a good assumption to me. The polls in the UK move so fast that the difference in assumptions really matters this time. The smoothing method [[LOESS]] estimates the trend at a certain time to make the best estimate at that time. It fits a line to the data over a subperiod. Estimating a fixed value would correspond to assuming the line is horizontal over this subperiod. LOESS thus takes Comrade Trend into account. It gives the figure below.



The predictions for election day, this Thursday, were made by assuming a linear trend for the period since the 1st of May.

Election turnout

An important reason that it is hard for polling to predict the outcome of an election is that it is not known who will actually get off the couch and vote. The figure/tweet below shows for one of the polls how much difference various turnout assumptions makes. The spread in the polls is very large this election. That may well be because turnout is very important this time. Older people tend to favour the conservatives and faithfully show up. The question we will not know until election day is how much young people will show up.


Polling bias

Then there is the question whether polls are not just noisy estimate, but whether they are also biased relative to the election. Nate Silver writes:
Exactly how strong the Conservative tendency to outperform their polls has been depends on where you measure from. Since 1992, Conservatives have beaten their final polling margin over Labour by an average of 4.5 percentage points, and have done so in all but one election. (That was 2010, when both Conservatives and Labour gained ground as Liberal Democrats’ support collapsed, but Labour slightly outperformed its polling margin against the Tories.) Go all the way back to 1945, however, and the average Conservative overperformance is just 1.8 percentage points and is not statistically significant.
I prefer to look at all the data and would say that the bias is not statistically significant. It would be weird for the bias to have become worse, except maybe for really recent elections where parts of the population can no longer be reached with landline telephones. That you can find a period with a higher bias may well be cherry picking. As long as no one can provide a reason for a change in bias since 1992, picking a specific period after looking at the data is statistically suspect.

Outcome

According to Nate Silver UK polling tends to have a relatively high uncertainty and misses the election outcome typically by about 4 %. Estimating a trend is harder than estimating a mean, thus it could be that my 2 % prediction is even a bit more uncertain. Thus if my best estimate is right and the conservatives are only 2 % ahead the election is a toss up: the difference is less than the uncertainty.

Let's see who turns out.

[UPDATE. If you put in my numbers for the conservatives and Labour and add 8 % for the Liberal Democrats, 4 % for UKIP and 3 % for the Greens (estimated from Wikipedia graph), the Electoral Calculus app computes the following seat distribution:

National Prediction: Conservative majority 4

Party2015 Votes2015 SeatsPred VotesGainsLossesNet ChangePred Seats
CON 37.8%331 40.0%610-4327
LAB 31.2%232 38.1%141+13245
LIB 8.1%8 7.6%05-53
UKIP 12.9%1 3.8%01-10
Green 3.8%1 2.9%00+01
SNP 4.9%56 4.7%01-155
PlaidC 0.6%3 0.5%02-21
Minor 0.8%0 2.5%00+00
N.Ire 18 00+018
]

[UPDATE. Just before closing of the election let me publish my last updated graph here. Currently Tories are 4.2 % ahead. That is still within the uncertainty and while it is quite likely that the Conservatives will win, there is still a Trump chance that Labour will win. Let's see who shows up to vote.


]

[POST ELECTION UPDATE. One of the best polls was by YouGov. Good with respect to statistical methodology and accuracy in this election. Interestingly, they did not find a steep trend towards Labour, but had a stable 3% lead for the conservatives since 27 May. Thus Comrade Trend may be more the inertia of the other polling organisations than that of the public.]

Related reading

YouGov, the heavily criticized poll that got it right: UK election: The day after. "But the general picture is clear: the model was a huge success in an election which most politicians, pollsters and commentators got badly wrong."

Nate Silver at 538: Are The U.K. Polls Skewed?

Response to Nate Silver, part one (because it’s early!) This post warns that the averaging method in Nate Silver's post is very basic and not comparable to the advanced methods he uses for US polls.

UK polling report: How the polls have changed since 2015

* The code used to generate my prediction plot is on Github.