Feb 182012
 
The reviewer thinks that “the piece is quite long for a research note on a regional election.” I’m afraid s/he is right, as it took me an unduly long time to complete it. But (and this is a very big but) the reviewer nonetheless recommends publication, and (even better the editor does not think that a reduction in size will be necessary.  Rejoice! So, just under one year after the fact, here is my analysis of the 2011 Land election in Rhineland-Palatinate

The 2011 election in Rhineland-Palatinate was a political earthquake: Following a string of political scandals, the SPD lost almost ten percentage points of their support, while the CDU could hardly improve on their disastrous 2006 result. The FDP is no longer represented in the state parliament. The Greens more than tripled their last result, allowing them to enter a coalition with the SPD for the first time.

Analyses at the municipal level show that the party improved most in their urban strongholds while still showing a (relatively) weak performance in rural areas. This will make it difficult to sustain the momentum of their victory. Moreover, the SPD is battered and bruised and needs to select a new leader, but veteran minister president Kurt Beck shows no inclination to step down. This does not bode well for a coalition that needs to organise the state’s fiscal consolidation and structural transformation.

 There is a PDF, too.

This manuscript as PDF

PDF version of this paper

 

 

 

Jan 142012
 

I’m currently working on an analysis of the latest state election in Rhineland-Palatinate using aggregate data alone, i.e. electoral returns and structural information, which is available at the level of the state’s roughly 2300 municipalities. The state’s Green party (historically very weak) has roughly tripled their share of the vote since the last election in 2006, and I want to know were all these additional votes come from. And yes, I’m treading very careful around the very large potential ecological fallacy that lurks at the centre of my analysis, regressing Green gains on factors such as tax receipts and distance from next university town, but never claiming that the rich or the students or both turned to the Greens.

One common problem with this type of analysis is that not all municipalities are created equal. There is a surprisingly large number of flyspeck villages with only a few dozen voters on, whereas the state’s capital boasts more than 140,000 registered voters. Most places are somewhere in between. Having many small municipalities in the regression feels wrong for at least two reasons. First, small-scale changes of political preferences in tiny electorates will result in relatively large percentage changes. Second, the behaviour of a relatively large number of voters who happen to live in a small number of relatively large municipalities will be grossly underrepresented, i.e. the countryside will drive the results.

My PhD supervisor, who did a lot of this stuff in his time, used to weigh municipalities by the size of their electorates to deal with these problems. But this would lead to pretty extreme weights in my case. Moreover, while voters bring about electoral results, I really don’t want to introduce claims about individual behaviour through the back door.

My next idea was to weigh municipalities by the square root of the size their electorates. Why? In a sense, the observed behaviour is like a sample from the underlying distribution of preferences, and the reliability of this estimate is proportional to the square root of the number of people in a given community. But even taking the square root left me with weights that were quite extreme, and the concern regarding the level of analysis still applied.

Then I realised that instead of weighing by size, I could simply include the size of the electorate as an additional independent variable to correct for potential bias. But this still left me exposed to the danger of extreme outliers (think small, poor, rural communities where the number of Green voters goes up from one to four, a whopping 300 per cent increase) playing havoc with my analysis. So I began reading up on robust regression and its various implementations in Stata.Robust Regression of Aggregate Data in Stata 1

The basic idea of robust regression is that real data are more likely than not a mixture of (at least) two mechanisms: the “true model” whose coefficients we want to estimate one the one hand, and some other process(es) that contaminate the data on the other. If these contaminating data points are far away from the multivariate mean of the x-Variables (outliers) and deviate substantially from the true regression line, they will bias the estimates.

Robust regression estimators are able to deal with a high degree of contamination, i.e. they can recover the true parameters even if there are many outliers amongst the data points. The downside is that the older generation of robust estimators also have a low efficiency (the estimates are unbiased but have a much higher variance than regular OLS-estimates).

A number of newer (post-1980) estimators, however, are less affected by this problem. One particular promising approach is the MM estimator, that has been implemented in Stata ados by Veradi/Croux (MMregress) and by Ben Jann (robreg mm). Jann’s ado seems to be faster and plays nicely with his esttab/estout package, so I went with that.

The MM estimator works basically by identifying outliers and weighing them down, so it amounts to a particularly sophisticated case of weighted least squares. Using the defaults, MM claims to have 85 per cent of the efficiency of OLS while being able to deal with up to 50 per cent contamination. As you can see in the table, the MM estimates deviate somewhat from their OLS counterparts. The difference is most pronounced for the effect of tax receipts (hekst).

robreg mm has an option to store the optimal weights. I ran OLS again using these weights (column 3), thereby recovering the MM estimates and demonstrating that MM is really just weighted least squares (standard errors (which are not very relevant here) differ, because robreg uses the robust variance estimator). This is fascinating stuff, and I’m looking forward to a forthcoming book by Jann and Veradi on robust regression in Stata (to be published by Stata Press in 2012).

                     OLS              MM            WLS

greenpct2006        0.193***        0.329***        0.329***
                 (0.0349)        (0.0592)        (0.0278)

hekst               0.311***        0.634***        0.634***
                 (0.0894)         (0.124)        (0.0688)

senioren          -0.0744***       -0.100***       -0.100***
                 (0.0131)        (0.0149)       (0.00994)

kregvoters11      -0.0125        -0.00844        -0.00844
                 (0.0146)       (0.00669)       (0.00982)

kbevdichte         -0.433        -0.00750        -0.00750
                  (0.464)         (0.330)         (0.326)

uni                 1.258           0.816           0.816
                  (1.695)         (0.765)         (1.137)

lnunidist          -0.418**        -0.372**        -0.372***
                  (0.127)         (0.113)        (0.0918)

_cons               8.232***        7.078***        7.078***
                  (0.627)         (0.663)         (0.461)
Enhanced by Zemanta
Mar 142011
 

As predicted yesterday, the nuclear disaster in Japan is having a profound impact on something as trivial as three state election campaigns in Germany, more than 9000 kilometres away. Roughly 70 per cent of the population believe that an incident on the scale of the Japanese catastrophe could happen in Germany, too. The Federal Government has declared a three-month “moratorium” on its controversial decision to extend the life-span of German nuclear plants, what ever that means. Meanwhile, they want to reconsider their position on the issue and to re-assess the status of the German plants. It makes you wonder if/why they have not assessed those plants in the first place.

At least the oldest and least secure plants could indeed have reached the end of their life-span. If and when they would be switched off, that would be a U-turn for the government. This looks like a liberal-conservative panic attack.

Agenda Set, Japanese Style II 2
Mar 122011
 
The Fukushima 1 NPP

Image via Wikipedia

It’s amazing: Just 36 hours after the horrible earth quake in Japan, 60000 people are demonstrating in Swabia – against nuclear energy. While we do not know whether the Japanese plants are actually in meltdown, for the German liberal-conservative coalition, this is certainly the Most Credible Accident.

One of the governments most controversial decisions so far was to amend the red-green phase-out law so that the German nuclear plants can remain operative much longer than planned under the original law. This upset many people, as acceptance for nuclear energy in Germany is low. And so the issue was already salient for the ongoing state-election campaigns in Baden-Württemberg, Rheinland-Pfalz and Sachsen-Anhalt long before yesterday’s tragedy, particularly in Baden-Württemberg, which has four operational nuclear power plants.

Now, the Greens and the SPD are having a field day. Or so it would seem: The governments semi-official line is that it would be inconsiderate to discuss domestic matters in the face of the Japanese tragedy, and the SPD is playing along for today. But it’s difficult to imagine that the left parties will not play the issue over the next two weeks – the scale of the nuclear threat is just too big.

And the media are certainly on the job. The main public broadcaster ARD – roughly equivalent to BBC One – just changed its schedule and dropped one of its insufferable shows for the over 60s in favour of a documentary on the Chernobyl disaster. Showing something that is actually relevant one a Saturday night is an almost unprecedented move for them. And even if no one was trying to set the agenda, having a power plant in or near meltdown will certainly prime voters.

Enhanced by Zemanta