Category: verejná mienka

Polls, Politics and Parties, Part 6: How (not) to second guess the polls…

Two-and-a-half months ago I finished up a blog post on poll predictiveness with a cliffhanger:

This question has driven experts to find a variety of proxy measures to figure out how to adjust polling numbers to reflect the final outcomes.  This post is already too long, however, so that will have to wait for another post.

By now readers have no doubt forgotten that they have been hanging on in suspense and have moved on to other important things, but I have not forgotten the promise.  Indeed I could not since this is one of the two biggest questions that shape how we look at poll numbers in Slovakia (the other is the threshold, which I will deal with in the next part of this series) and since the issue has surfaced in nearly every major Slovak daily.  No refer to just a few:

Each of these articles refers to methods by which one might try to put poll numbers in context, with the ultimate goal, the grail, to make a better prediction of election results.  On the one hand some articles, such as the most recent one from SME, say that this can’t really be done–that it depends too much on idiosyncratic behaviors and random events.  Other articles, such as the one in Hospodarske Noviny suggest that the firmness of voter commitment might offer some clues that would allow us to make better predictions.  Others have suggested factors such as voter turnout likelihood, measured either by surveys or by past polls.  Recent trends may also play a role in shaping how people decide when they actually enter the voting booth.  These all seem plausible, but rather than take any of these potential influences as real, it is worth testing them to see if they do have any relationship to the difference between polls and actually election outcomes.

The Role of Voter Loyalty

It seems quite plausible to assume that for two otherwise identical parties, the party whose voters are more committed to voting for it will perform better.  It seems plausible, the,  that polls (which usually don’t ask about degree of committment) will tend to underestimate the election-day performance of parties with more committed voters.  And this should give us a tool for making better predictions.

But it doesn’t.

At least it didn’t in 2006.  Below is the first in a series of graphs that looks at the relationship between potential sources of “poll adjustment,” such as “voter committment,” on the x- or horizontal-axis and the actual predictiveness of polls (specifically the difference between election results and poll results) on the y- or vertical-axis.  If a source of adjustment is useful, the graph should follow a straight line between lower left and upper right (in other words, parties which score “low” on whatever factor also underperform polls while parties that score high overperform polls).

The graph for “voter loyalty” (measured here as the difference in a March FOCUS poll between those supporters of a party who say they will “definitely” vote for the party and those who say they “might change” their minds) suggest that this data source does not allow us to improve our assessments.

In fact, there is a slightly negative relationship between loyalty and support.  The factor of loyalty might help explain why the longstanding SMK did better than expected and why the relatively new and weak SF did worse (which, if true, might suggest a discounting of current preferences for SaS), but it does not explain the overperformance of SDKU (except to the extent that SF voters may have shifted to that party, something not factored into the “loyalty” question).  More to the point, perhaps, it also does not explain the underperformance of HZDS, which in 2006 had the most loyal voters of all.  “Committment” may have something to do with it, but if it does, the interaction is too complicated for this single piece of information to produce any meaningful insights.  So HN may be right in pointing out that KDH voters are the most “solid” but that does not help much.

A related factor–perhaps very closely related–was cited by ING Bank in its own quite thorough 2006 analysis of the prospective election results which circulated before the elections.  The bank’s report, which unfortunately did not contain full footnotes, cited two measures of voter “discipline” and compared the share of “disciplined” voters committed parties to the share of voters overall.  Here again, a party with more “disciplined voters” should in theory have a better chance of outperforming the polls than a party with fewer disciplined voters.  Unfortunately, I do not know how they defined “disciplined” and I have a feeling that it is simply another way of calculating the same “loyalty” data above.  Since I don’t know whether it means anything, I analyze the results here only to demonstrate that the same results emerge for polls by both FOCUS and MVK (and therefore that this is not simply an artifact of FOCUS polling).

The trendlines here are essentially flat, suggesting no relationship.  The MVK results have a slightly positive trend, but not by much and the overall pattern is murky: again it works for SF and, with MVK, for SMK and SDKU but not for SDKU in the FOCUS survey or HZDS in the MVK survey.

The Role of Party-Voter Turnout

The voting decision is actually twofold: alongside the question of whom to vote for is the question of whether to vote at all.  The preference question itself does not measure whether those who prefer a party will actually make it to the polls on election day.    In theory those parties with voters who were more likely to go out and vote would do better than others and therefour outperform the polls.  We have data on this because in 2006 the pre-election FOCUS polls regularly asked about likelihood of participation.   The graph below combines the results for all major parties over four months and shows the relationship-line for the February data, the May data and the data for all four months aggregated together.

As with the loyalty data, the trendlines here point down, suggesting that knowing the likelihood of voter turnout for a party does not help figure out whether the party will perform better than the polls.  This figure works for the same parties as loyalty–SMK in the positive, SF in the negative–and fails for the same parties as loyalty–SDKU and SNS  outperform likely turnout while HZDS underperforms.  Of course there may be a reciprocal relationship here between SDKU and SF and between SNS and HZDS, but the point here is that the loyalty and turnout figures alone do not tell us that information and cannot be used to specify our predictions.

Previous Polls

An even more direct way to estimate the overperformance or underperformance of parties compared to polls is to look at the performance in the previous election.  In 2006 I set out to create a prediction model based largely on this principle, looking at the gap between past polls and past actual results using the 2002 Slovakia parliamentary election and 2004 Europarliament election and suggesting a relationship between differences in turnout (medium in 2002, very low in 2006) and differences between party polls and party performance.   The model did not work.  Or more precisely, it worked so idiosyncratically that it was not useful:  it worked well for SDKU and SF and badly for most of the rest.  The graph below demonstrates the weakness of that attempt: the

The graph shows two sets of dots because there is a slight comparability problem:  in 2002 the law forbade polls within the last two weeks of elections whereas in 2006 it did not.  The graph above shows differences between polls and results as a percentage of the poll figures in 2002 compared to 2006 for both the 2006 polls taken immediately before the election (white circles and colored rims) and those taken in a more comparable 2-4 week period before election (colored circles and gray rims).  In both cases, the results are the same:  predictiveness of polls in 2002 did not help assess predictiveness in 2006 except for SDKU, SMK and Smer (but only the 2 week prediction and  not the election day prediction).  It would appear that too many other variables affect the parties and polls over time for this method to work well.

What we need, then, is some kind of indicator that itself incorporates a significant share of the factors that shape poll predictiveness.

Oddsmakers and Experts

One way of assembling and integrating relevant factors is to find a smart and trustworthy person who has already done it.  It is even better if the person (unlike the author of this blog) stands to lose some tangible resources if the predictions are wrong.  There are not many public sources for this kind of information for Slovakia.  Political scientists, pollsters and journalists (precisely because they do have something to lose–reputation and perhaps even revenue) tend to keep their predictions to themselves.  And there is not yet a widespread public odds market in which individual buying and selling of shares offers a glimpse into public assessment of probabilities (a mechanism which has been extremely effective in predicting close races in the United States) except in SME‘s ambitious effort, which at least for now does not seem to involve real losses or gains or a particularly large base of participants (though that does not mean that the collective wisdom of SME‘s readers won’t be correct, and the consensus I see there is not implausible) .

What we have instead are two rather thin reeds: in 2006 the firm Tipos.sk allowed public betting on election questions, though the odds were established by the bookmakers themselves and only occasionally updated rather than in a true shares market (and which can be reverse-engineered into an assessment of the bookmaker’s own predicition); and in that same year an assessment by an analyst at ING Bank became public (though not necessarily with the encouragement of the bank).  I am sure there are other analyses floating around by political risk mangement firms, but I don’t have access to them (though if readers do and can share them, even for past elections, I would be extremely grateful).  The question is whether these expert opinions do much better than the raw data.  The answer is no, as the chart and graph below show.  In only 4 cases out of 16 did the expert opinion do better than the actual final polls in predicting the outcome (and in this cases for the likely suspects:  SF, with its weak base, and SDKU with its past history of significant underestimation) while in 7 of 16 cases the expert opinion did rather worse than the actual data.  Of course these analyses emerged more than a month before the actual election and, to be fair, they actually performed slightly better than the poll estimates from May polls, so experts do have their (slight in this case) value for those needing their predictions well in advance.

Party Actual 2006
election result		 Actual results minus pre-election estimates
Final week
poll average

Tipos odds

ING Bank
HZDS 8.8 -2.7 -3.8 -3.7
KDH 8.3 -1.4 -1.3 -2.8
KSS 3.9 -1.2 -1.1 -0.9
SDKU 18.4 5.4 3.8 2.4
SF 3.5 -1.9 -1.0 0.3
Smer 29.1 1.5 4.2 4.6
SMK 11.7 1.4 2.5 -1.8
SNS 11.7 1.6 3.7 3.9
Average error in raw points 2.1 2.7 2.6
Average percentage error 21.7% 25.7% 22.5%

The best tool I can find: Pre-election trends

In the process of testing all of these various mechanisms for prediction, I decided to try one last method:  does a party’s trajectory actually affect its final outcome?  In this case the theory suggests it should not have much of an effect:  when polls are taken up to the last minute, then trends themselves should not shape the final decision.  It is possible, however, that a voters’ sense of trend might bring a reluctance to vote for a declining party or an enhanced willingness to vote for one on the rise.  And lo, when I ran the numbers the results came out shockingly clear:  in 2006 a party’s trendline for January through April had a clear relationship to the party’s tendency to over- or underperform polls:

This source of information correctly predicts 5 of the 8 and incorrectly predicts only 2 (and then only by narrow margins).  The dots are grouped tightly around the line, suggesting a strong relationship.  It is as if the election results followed the trendlines, but at levels they would have produced in July or August rather than June; the experience of going into the voting booth may force the kind of concentration that pushes voters to become the extrapolation of trends.

A strong caveat: I am hesitant to take this too far, especially since I have not been able to put together a time series for previous elections or in other countries, but the initial results suggest that the past trend is something worth attending to.

A word about prediction, caveat be damned. So what would this flawed (but not as flawed as the other methods I’ve looked at here) say about Slovakia’s upcoming 2010 election?  Well it is necessary to begin by looking at the 2010 four-month trends.  There are, of course, several ways to calculate the trend, averaging individual poll trends or aggregating all poll data together.  The results and relative positions of parties are reasonably similar, however.  The following table gives the range:

Party Trend Change
SaS Significantly positive +60% to +80%
KDH Moderately positive +10% to +13%
SMK Slightly positive +7% to +11%
MOST Slightly positive +2% to +8%
SNS Mixed -5% to +8%
SDKU Flat 0% to +1%
Smer Moderately negative -10% to -12%
HZDS Significantly negative -10% to -23%

This is good news for SaS (especially since if the question of “loyalty” and “discipline” are relevant anywhere it is for new parties such as SaS whose positive trend here may be enough for it to overcome the at-the-polls reluctance that kept SF from parliament in 2006) and not bad news for KDH, though this party seems locked into a 9.5%±1.5% performance zone regardless of external circumstances.  The news Smer is not good–but this is not unexpected, since the even party elites know that their party gathered a significant amount of soft support during its more successful years–but not catastrophic since Smer has a huge lead over the next largest party.  The worst news is for HZDS which has both the strongest negative trend in recent months and the least cushion to offset any losses.  If the trendline factor found in 2006 applies in 2010 then HZDS will not make it into parliament.  A big if.

For the other parties the prediction is far less clear.

  • I suspect this model does not apply at all to Most-Hid and SMK since the intra-ethnic competition takes a quite different form.  Of course this makes all of the above assessments rather useless since this is what everybody wants to know.
  • For SDKU the neutral trend is probably about right.  In the past the party has benefitted from last minute decisions by voters to stick with the tried and true on the right.  With a revived KDH and a solid alternative in SaS (barring any mistakes by the party or revelations about it in the next month), SDKU will likely not see the big jump that it saw in 2006 or 2002.  Its has a good chance of being the strongest of the right-wing parties, but probably not by too great a margin.
  • As for SNS, it is an open question.  In the last four months, SNS saw a general decline offset by a major rise in a single poll: FOCUS in April.  Take out that one data point and SNS shows a trend in the last four months that matches its sharp decline over the past full year.  It is for that reason that I am keen to see the April Median poll–not for level but for trend–and especially the May FOCUS trend.  If FOCUS in May puts SNS back under 6% then the party may be in real trouble.  The threshold will have a big impact on the shape the next government (the topic for the next post, I hope.)

Dashboard News [Update]: April MVK [and Polis] follows FOCUS on coalition drop and opposition rise.

[A quick note.  Rather than write a new post, I have simply updated Wednesday’s post with results from Polis.  This was easy to do because the Polis results were largely consistent with the others.  Unfortunately this doesn’t mean we have the answers to the key questions:  how do poll numbers translate into votes, and, in particular, what will happen with will the parties around the 5% threshold.  But if it weren’t for these there would be too little suspense.]

When two [three] different polls agree on shifts in most parties it is time to pay attention. The April poll for FOCUS came out last week and this week MVK [and Polis] revealed [their] own (always, to my regret and frustration, with less information than that provided by FOCUS). The movements in both of these polls correspond quite closely, even if they begin from different baselines: Smer, HZDS and KDH down, SaS up, others moving in different directions but not by much. The overall movement of coalition and opposition also agrees fairly closely, with the coalition dropping to some of its lowest levels since the coalition took office almost four years ago, though still likely ahead (despite headlines that “the opposition has caught up to Fico,” it is probably not that simple and it is the small details and narrow margins that will make the difference in what kinds of governments are viable after the election.

As always the numbers are on the Dashboard. The analysis is below:

Both MVK and FOCUS [and Polis] show an almost identical drop for Smer of about 2.5 points from February to April (and with FOCUS the March numbers are not far out of line with that trend). Because MVK begins with a lower baseline, it shows a lower result—35.1–which is in line with MVK’s overall lower result for Smer.  [Polis is between the two at  36.2].  Nevertheless the number is still striking because it is the lowest preference that Smer has received on an MVK poll since the just before the 2006 election (The FOCUS numbers from last week are low by FOCUS averages as well—the third lowest since 2007) [For Polis we do not have such a long baseline of results.].  Why so low? Probably a certain amount of fatigue, accumulation of scandals and problems and, I suspect, a bit of defection to SaS and, this month, to SNS.

FOCUS showed a big jump for SNS in April. MVK also shows a jump, though smaller in magnitude and from a smaller baseline [Polis shows no jump at all and a figure just at the threshold of viability.  SNS has usually polled low in Polis polls, however, so this needs to be taken with some caution]. [The FOCUS and MVK results] puts SNS more safely above the threshold in both of these major polls. How safe is anyone’s guess. It is hard to know how to think about this party’s chances. It’s past levels suggest that it has a decent level of residual support (if not strong organization) and I have been slightly surprised by its low but the years of scandal and extreme behavior by the party leader certainly have pushed it toward the low edge of viablility.

For HZDS the last two months show a drop in both FOCUS and MVK to just above the threshold of viability. [In the Polis poll, the party’s results are stable, but from an already quite low baseline, well below 4%.]  Of course it has been at that level on and off for the last year, and the overall trend has been quite consistently downward. The question is whether that downward trend will overcome the party’s fairly loyal voter base. This one will be close.  [News about Polis polls, whether or not they are accurate, certainly cannot help the party’s chances for persuading voters to choose it over another alternative].

The current coalition shows slightly different patterns in FOCUS and MVK: in MVK the pattern is one of clear decline from the mid-50’s to the mid-40’s.  In FOCUS polls, the drop is much smaller: from mid-50’s to the low 50’s [and Polis shows a result somewhere in-between, from low-50’s to mid-40’s] . It is still unlikely that the coalition seat would drop below 50% off this estimate, unless one of the two smaller coalition parties falls below the 5% threshold.

For SDKU the most recent polls of FOCUS and MVK show a more mixed pattern: in MVK, SDKU dropped a point from February to April but is two points up on its results from January. FOCUS shows the identical pattern but off by a month: in FOCUS polls SDKU dropped a point from March to April but up two points from February. [Polis actually shows SDKU up, suggesting the same sort of random fluctuation within a quite narrow range.] This kind of mapping is probably pointless however. What is clear is that SDKU is fluctuating quite a bit within its normal range and voters themselves are probably fluctuating as well. What is striking is that SDKU has lost so little in the face of a huge rise in SaS which should, in theory, compete for the same voters.

KDH shows almost the identical slow slide in both MVK and FOCUS, dropping about a point over the last two months (and slightly more from earlier polls) to a level around 9%. [Polis shows a slight drop but from a higher initial point.  For KDH it is the range that is unclear–the 9% of FOCUS, the 11% of MVK or the 13% of Polis–while the pattern of slight decline in the most recent months is common to all polls].  Like SDKU, KDH is probably seeing some effects from the rise of SaS: there was always a small cadre of voters who would opt for KDH as an alternative to SDKU. Now they have another alternative.

SaS shows virtually the same jump in both FOCUS and MVK [and only slightly smaller in Polis] and to virtually the same level—around 11.5% [and 9% in Polis, but SaS has tended to lag in Polis polls]. I suspect that some of these voters will, in the final equation, fall back to SDKU or KDH, but for the moment SaS has done well in exciting voters and does not seem to have made any major mistakes.

Hungarian parties. Here is really the only place where the [three] sets of major polls show differences in trend and even then it is only to place them in the same positions. The MVK poll in April is virtually identical to that of February, with MKP-SMK around 6% and Most-Hid around 5%, a result also reached by FOCUS.  [In the Polis poll the numbers for the two parties are stable as in MVK but the percentages are almost precisely are reversed, as in last month’s FOCUS poll, with Most-Hid a point ahead of MKP-SMK, with both ahead of the 5% threshold.]  For a party with weaker organizational basis and history, Most-Hid’s decline to near the threshold [in FOCUS and MVK polls] must be rather worrisome for the party’s leaders, but what will happen here, however, remains extremely difficult to assess.

The current opposition, particularly the right has done well lately. The parliamentary right has dropped somewhat, but not much, and the rise of SaS recently is more than double the combined losses of SDKU and KDH. In fact both FOCUS and MVK show an overall rise for the three parties combined by a significant amount: about [4 points in Polis in the last six months] 6 points in FOCUS and about 8 points in MVK. This was a fairly predictable outcome, I think, as the campaign and the emergence of new parties gave the right a stronger focus and pushed at the relatively soft electoral support for the current government (exemplified by Radicova’s ability to reach near parity with Gasparovic in 2009). The ability of these parties to form a government is still a longshot, but these numbers probably better reflect the overall composition of opinion in Slovakia’s society (keeping in mind that some of the SaS support, I suspect, is not from the ideologically “right” but from dissatisfied “new party” support which had previously gone to Smer.

But the threshold will still be the key determinant.

Dashboard News: April MVK follows FOCUS on coalition drop and opposition rise.

When two different polls agree on shifts in most parties it is time to pay attention.  The April poll for FOCUS came out last week and this week MVK revealed its own (always, to my regret and frustration, with less information than that provided by FOCUS).  The movements in both of these polls correspond quite closely, even if they begin from different baselines: Smer, HZDS and KDH down, SaS up, others moving in different directions but not by much.  The overall movement of coalition and opposition also agrees fairly closely, with the coalition dropping to some of its lowest levels since the coalition took office almost four years ago, though still likely ahead (despite headlines that “the opposition has caught up to Fico,” it is probably not that simple and it is the small details and narrow margins that will make the difference in what kinds of governments are viable after the election.

As always the numbers are on the Dashboard.  The analysis is below:

Both MVK and FOCUS show an almost identical drop for Smer of about 2.5 points from February to April (and with FOCUS the March numbers are not far out of line with that trend). Because MVK begins with a lower baseline, it shows a lower result—35.1–which is in line with MVK’s overall lower result for Smer. Nevertheless the number is still striking because it is the lowest preference that Smer has received on an MVK poll since the just before the 2006 election (The FOCUS numbers from last week are low by FOCUS averages as well—the third lowest since 2007). Why so low? Probably a certain amount of fatigue, accumulation of scandals and problems and, I suspect, a bit of defection to SaS and, this month, to SNS.

FOCUS showed a big jump for SNS in April. MVK also shows a jump, though smaller in magnitude and from a smaller baseline. Still, it puts SNS more safely above the threshold in both of these major polls. How safe is anyone’s guess. It is hard to know how to think about this party’s chances. It’s past levels suggest that it has a decent level of residual support (if not strong organization) and I have been slightly surprised by its low but the years of scandal and extreme behavior by the party leader certainly have pushed it toward the low edge of viablility.

For HZDS the last two months show a drop in both FOCUS and MVK to just above the threshold of viability. Of course it has been at that level on and off for the last year, and the overall trend has been quite consistently downward. The question is whether that downward trend will overcome the party’s fairly loyal voter base. This one will be close.

The current coalition shows slightly different patterns in FOCUS and MVK: in MVK the pattern is one of clear decline from the mid-50’s to the mid-40’s. In FOCUS polls, the drop is much smaller: from mid-50’s to the low 50’s. It is still unlikely that the coalition seat would drop below 50% off this estimate, unless one of the two smaller coalition parties falls below the 5% threshold.

For SDKU the most recent polls of FOCUS and MVK show a more mixed pattern: in MVK, SDKU dropped a point from February to April but is two points up on its results from January. FOCUS shows the identical pattern but off by a month: in FOCUS polls SDKU dropped a point from March to April but up two points from February. This kind of mapping is probably pointless however. What is clear is that SDKU is fluctuating quite a bit within its normal range and voters themselves are probably fluctuating as well. What is striking is that SDKU has lost so little in the face of a huge rise in SaS which should, in theory, compete for the same voters.

KDH shows almost the identical slow slide in both MVK and FOCUS, dropping about a point over the last two months (and slightly more from earlier polls) to a level around 9%. Like SDKU, KDH is probably seeing some effects from the rise of SaS: there was always a small cadre of voters who would opt for KDH as an alternative to SDKU. Now they have another alternative.

SaS shows virtually the same jump in both FOCUS and MVK and to virtually the same level—around 11.5%. I suspect that some of these voters will, in the final equation, fall back to SDKU or KDH, but for the moment SaS has done well in exciting voters and does not seem to have made any major mistakes.

Hungarian parties. Here is really the only place where the two sets of major polls show differences in trend and even then it is only to place them in the same positions. The MVK poll in April is virtually identical to that of February, with MKP-SMK around 6% and Most-Hid around 5%, a result also reached by FOCUS. For a party with weaker organizational basis and history, Most-Hid’s decline to near the threshold must be rather worrisome for the party’s leaders, but what will happen here, however, remains extremely difficult to assess.

The current opposition, particularly the right has done well lately. The parliamentary right has dropped somewhat, but not much, and the rise of SaS recently is more than double the combined losses of SDKU and KDH. In fact both FOCUS and MVK show an overall rise for the three parties combined by a significant amount: about 6 points in the last six months in FOCUS and about 8 points in MVK. This was a fairly predictable outcome, I think, as the campaign and the emergence of new parties gave the right a stronger focus and pushed at the relatively soft electoral support for the current government (exemplified by Radicova’s ability to reach near parity with Gasparovic in 2009). The ability of these parties to form a government is still a longshot, but these numbers probably better reflect the overall composition of opinion in Slovakia’s society (keeping in mind that some of the SaS support, I suspect, is not from the ideologically “right” but from dissatisfied “new party” support which had previously gone to Smer.

But the threshold will still be the key determinant.

Dashboard News: Slovak papers see the light

It is absolutely delightful for me to see that after years of publishing one poll after another without much analysis and presenting each difference as “news”, two major papers in Slovakia have begun to present long-term time-series data of polls.  I suspect they will still present each new poll as “news” (though congratulations to them also for doing much more comparison and acknowledgment) but now readers can at least do some comparing on their own.  A few brief thoughts on the two attempts

  • Of the two the less ambitious effort is Pravda’s which is simply a story link containing tables of results from the major polls from January until the present.  It does the job but without much visual impact.  The full chart can be found here http://spravy.pravda.sk/prieskumy-agentur-focus-median-a-mvk-dvb-/sk-volby.asp?c=A100421_160242_sk-volby_p12.  Since this is merely a story page it is not clear whether Pravda intends this as an ongoing feature or merely as a one-off presentation of the data.  The omissions are also interesting: first, there are no smaller parties listed even though FOCUS does list the smaller parties and those parties sometimes rise to the level of relevance, if only in the way they take votes away from others (by this standard, SaS would not have qualified to appear on the list until November of 2009); the other interesting omission is Median, the polling firm with the “you name it” methodology.  I have been critical of this in the past and suggested that the poll is out of line, so its omission is justified here.  I use Median to look at trends, but without graphics (as in Pravda’s case) this is not as relevant and including Median might simply be confusing.
  • Sme’s effort is rather more ambitious, a graphic interface with three parts.  The top one shows politicians standing next to lines representing party support and four buttons for polling firms.  Clicking on the poll button shows the results for the most recent iteration of the poll and the month in which it was taken.  Hovering over the individual politicians and lines shows the numerical level of support for the party.  This is great, and it is great to have a choice, but there are two minor problems: first, the lines are dwarfed by the pictures of the politicians and so it is hard to gauge the relative levels of support by eye, and you have to move the bar across to see numbers for individual parties so it is not easy to ‘eyeball’ the levels either.  Of course this is a relatively minor problem (and one easily fixed).  The second part of the display is a long-awaited (by me at least) effort to put party support for various polls and various time periods together in the same graph.  I’ve been doing this on and off for several years in this blog (most recently in the Dashboard, above) and have been waiting for a long time for Slovak papers to do it so I wouldn’t have to and could focus on the analysis rather than the creation of the graphics.  Unfortunately, while this comes close it does not get close enough for me to be able to shut down my efforts.  There are several minor but significant problems: first, the graphic rounds the numbers off to the nearest percentage point, which is actually fine for most parties but problematic in discerning key trends for smaller parties where rounding up or down may actually mean mischaracterizing party support by up to 10%; second, and most important, the graphic puts lines and dots where they do not belong.  Because it measures in one month increments, it puts dots even where polling firms did not issue polls (and the reader has no way of knowing when without looking at Pravda or my own data); it also puts all polls on the same line when in fact they may have been taken at significantly different periods during a month, something that becomes important as we get into the final months; the biggest problem is that it carries these forward from “present” levels, suggesting, for example, that we have data for Premier polls in April (or MVK in March and April) when we simply do not.   Still, this is such a big improvement over what has been done before that I am extremely impressed, and the problems above could probably be fixed by a clever webdesigner in about 2 hours.   The last part of Sme’s graphics is an assessment of the number of parliamentary seats produced by the results in question using “person” icons.  This is fine, but takes up much more space than it needs to do and does not easily tell the important story (mine doesn’t either, and I should fix that) which is how much that represents for various coalition combinations.

All of this means that I’m not yet ready to leave the dashboard business, but the great news is that the average consumer of news in Slovakia now has a relatively easy method for assessing the meaning of claims about polls and that is fantastic.  It also means that Slovaks, for the moment at least, have pulled ahead of their Czech neighbors who also have an election coming up and whose Lidove Noviny publishes what was, until Sme, the best graphical analysis: http://www.lidovky.cz/ln-volby-ps10.asp?v=preference.  The graphics here are better and more readable than Sme’s but they lack the comparative polling elements (and therefore the implicit “trendfinder” capability) that Sme has introduced.  Perhaps it is time for me to get into the Czech dashboard business as well.  Until the papers catch up again.

Dashboard News: Polls disagree, parties shift (maybe), but blocs stay stable

The blog has been slow lately as I’ve finished up some local and international projects and concluded the semester.  And because Slovak poll numbers tend to be a mid-month phenomenon.  I have lots that I hope to talk about in the coming week but for now I want to get a jump on the numbers that appeared yesterday from Median and today from FOCUS.

While the two polls show a bunch of individual shifts in various parties, the limits of the polls themselves make these suspect to closer scrutiny.  What emerges is some uncertainty about specifics but a fairly clear general picture of stability (one that does not lend much insight into the crucial question of performance of those parties near the edge of viability (the two Slovak National parties HZDS and SNS and the two Hungarian National parties MKP-SMK and Most-Hid) which will affect coalition performance in a major way.

The overall results can be found on the dashboard.  Analysis is below.

Smer. A slight drop in FOCUS, stable in Median.  The difference between the two is about 7 points, one of the wider gaps between FOCUS and Median on Smer, but not the widest.  Median’s method of asking people to name parties should tend to boost the reported fortunes of well known parties (such as Smer).  No great changes or surprises here.

HZDS: Stable in both Median and FOCUS and at what are near-record lows in both polls.  It is interesting (but difficult to parse) that after HZDS’s huge drop in the Median polls between January and February, that the two are relatively close, between 5% and 6%.  HZDS thus stands at the threshold of viability for both a pollster that regularly poll about average for HZDS (FOCUS) and one that has recently polled high for HZDS (Median).

SNS: SME calls SNS’s rise in this month’s FOCUS poll a “second wind.”  Is this right?  Maybe, but not certainly.  This may reflect the recent Hungarian election results, but those have been predictable for so long (a colleague of mine wrote a paper in March in which he put the Orban victory in Hungary in past tense before it had even happened) that I wonder how much that really influences SNS numbers.  but I have doubts about whether this reflects a broader rise in preferences or simply a polling artifact.  Of the major existing parties, SNS poll results have a slightly greater propensity to jump around than do those of other parties.  The party saw a temporary drop of this same magnitude for one month late in 2009 and this may be a similar occurrence (in reverse) or a genuine Fidesz induced recovery.  Polis polls (which should be coming soon) may help us to tell if it is statistical noise.  Next month’s poll will tell us if it is a temporary blip.  It is worth noting, however that an article that says SNS has a second wind blows some of that wind itself.

The current coalition: Extremely stable, the even as individual party results have jumped around in both polls.  In Median polls coalition support dropped by about one twentieth over the last 3 months, from 60% to 57% while in FOCUS polls its support has stayed remarkably consistent: 50.6% in February, 50.1% in March and 50.8% in April (down from the mid-50’s in late 2009).  Losses by any one of these parties seem, for the present, to offset gains by others.

SDKU: Stable, though it is hard to know exactly what that means.  SDKU has gone through big changes lately both in its internal structure (Dzurinda to Miklos v. Radicova) and external environment (the rise of SaS and Figel in KDH) and has jumped around quite a bit.  That said, on this party FOCUS and Median have produced relatively similar results for this party, and continue to do so, putting relatively stable around 13%.  Read one way, Radicova’s arrival has not helped the party; read another way, the party has not lost much despite the emergence of a significant rival (or two) on its own territory.

KDH: Unclear.  FOCUS shows a small drop for KDH while Median shows a big jump.  Hard to parse this as well.  In February and March FOCUS was the outlier on KDH showing lower support smaller gains than any of the other three major polls.  For now FOCUS is all we have for April so it’s hard to say whether to take its numbers seriously.

SaS: No drop yet.  Every poll shows the same trend for SaS: an almost uninterrupted rise during 2009 with a brief pause or slight reversal in February/March 2010.  FOCUS new poll shows renewed growth in April and we do not have any other polls that confirm or deny that movement.  Median shows the same trend, though it’s much lower numbers for SaS are undoubtedly the result of its different survey question (which does not specify any options a priori).  In this case the SaS mechanism may offer a useful corrective for the numbers found by other parties (with lack-of-awareness of a party substituting here for lack-of-commitment to that party).  It is hard to believe that SaS will sustain results over 11% in the final tally if ANO and SOP did not, but this result does seem to put it out of immediate danger of falling below the threshold (thus reducing the number of parties in danger to “only” four.

Most-Hid and MKP-SMK: Stable but polls offer no insight on the key “threshold” question. The Hungarian parties results remain the most difficult to judge, at least with regard to the most important question of whether either party (or both together) will pass the 5% threshold.  FOCUS puts both parties right on the line (MKP stable over 3 months, Most-Hid dropping from a higher position).  I have argued that one of the two should pass the threshold but it is not clear which one.  The current stasis (with both above the threshold) makes it unlikely that one party will be seen as “running away with it” and lower the possibility of something like an 8% v. 3% split (not ideal, sacrificing maximum gain for maximum loss) while maximizing the possibility of either something like a 5.9% v. 5.1% split (a best case scenario) or something like 6.1% v. 4.9% (a worst case scenario).  Median, I think, simply needs to be ignored on Hungarian parties.  There is no basis that I can think of for trusting a result that shows the total Hungarian electorate at less than 8%; Median puts it at 6.2%.

The current opposition: Steady increase.  Averaging parties into blocs shows a lower overall shift (suggesting that volatility is within rather than between blocs).  Median shows very little change for the current opposition over time, and only 0.3% gain in the last month.  FOCUS likewise shows only a 1% gain in the most recent month though the longer term numbers suggest a rise of about one tenth since late 2009, likely consisting of new voters attracted by SaS and Most-Hid.

Dashboard News: Median offers different numbers but confirms decline of SNS and HZDS

That’s what the headlines of Slovakia’s papers should say.  But again they don’t.  Still, what we get now is better than before since the nature of differences in polling methods in Slovakia has begun to seep into the Slovak press.  Now at least the major sources specifically mention the poll by name in headlines before announcing the exciting “news” that certain new parties will not get into parliament. Pravda announces “Median: SaS and Most do not pass into parliament” while SME says almost the same thing: “Median Poll does not let SaS or Most-Hid into parliament” and TA3 writes “Median SK: SaS and Most would not get into parliament” and both SME and Pravda mentioned somewhere in the article that this differed from the results of other polls.

This is better than nothing, but not good enough.  The Dashboard contains the results including February Median poll, and what that shows is the following:

  • Median remains far from the other major pollsters on 3 important parties: SaS, Most-Hid and SNS.  This is probably because of the poll’s method of not listing party choices for respondents and requiring them to name a party without prompting.   It may be that Median is right in doing this and that the others are wrong, but Median’s past performance in predicting elections (worse than the other major pollsters: http://www.pozorblog.com/?p=684) suggests not.  So its predictions of parliamentary failure for Most-Hid and SaS, must be taken with a large grain of salt.
  • SaS:  Despite its raw numbers, Median confirms the upward trend of SaS. Median has always polled low for SaS but even with this the party now is near the threshold even for that pollster and shape of the lines (if not their locations) are roughly the same.  All major pollsters show the party with a big upward jump in January or February:
  • SNS and HZDS.  Likewise despite differences in raw numbers, Median shows a significant downward shift for both SNS, conforming to the trends in other surveys.  HZDS is now at the lowest level it has ever been in available Median polls (2005) and SNS is at its lowest level since 2007.  If Median had not showed these declines, it would be worth looking twice at the others, but the unanimity here cannot be good news, even if its raw numbers might hearten Meciar and Slota by suggesting that they are actually several steps short of the abyss.
    skp_sns

    		 skp_hzds

Otherwise Median numbers are not wildly different from those of the other pollsters:  in Median, as in FOCUS but not in the other two, Smer showed some recovery in February, and MKP-SMK showed signs of stabilizing above the threshold.  SDKU and KDH moved little.

Congratulations to the major papers for noticing that polling firms are different, but they still have work to do if they don’t want to miss the big story.

Dashboard News, March 2010: Stability despite overblown headlines; the importance of thresholds

No time to do a thorough post right now but a Polis came out yesterday and FOCUS came out today. Click the Dashboard above for the graphs.  Here are few thoughts:

  • Smer.  Both polls show the party slightly down but not by much.  The party has averaged between 38 and 41 for the last 6 months.  It is now on the low side of that but there are no signs of either a precipitous drop or a recovery.  Of course it will all depend on the likelihood of the “soft” Smer voters (of whom there are probably quite many) to go and vote.
  • SNS.  Polis shows a further drop to just above the threshold (but Polis has usually polled low for SNS compared to the others).  FOCUS shows it holding steady around 6%.  It probably does hang just above the threshold and its future may depend on an unlikely combination of Orban and Meciar.  We all know Orban is going to win but the tone of the campaign could help SNS a bit; if Meciar begins to fall repeatedly below the threshold, some voters might also shift to the next nearest “national” party, which is SNS.  There is still some degree of reciprocity between the voters of these parties, as with KDH and SDKU.
  • HZDS. Polis again shows it below the threshold, but Polis has usually polled low for HZDS.  FOCUS shows it with 5.2, the firm’s lowest result for the party since summer of last year.  Together these produce an average of 4.9 and so HZDS does not appear on this month’s roster of parliamentary parties.  Of course the upcoming Median survey will put the HZDS average back above the threshold, so there will not appear to be much of a change, but HZDS is clearly on the brink, and a drop like that of summer 2009 (and from a lower starting point) could knock the party out, especially if the April and May polls show it low and a few voters start to balk.
  • SDKU. Polis shows a drop from a high point; FOCUS shows a rise from a low point.  It is somewhere between 13% and 15%.  FOCUS, in particular, has shown a yo-yo, alternating between over 14 and under 12 since Fall.  Of course SDKU has been a bit of a yo-yo, with scandal followed by recovery.  Next month will help show whether the recovery shown by FOCUS is a “Radicova” bonus or just noise.
  • KDH.  In typical fashion the headline writer at the paper SME trumpeted KDH surpassing SDKU (along with a picture of Dzurinda pulling out a chair for Figel–they have pictures of elites interacting that serve every possible combination of events), but of course it probably doesn’t mean anything.  Polis puts KDH at a record high (and SDKU a bit low).  FOCUS puts KDH slightly higher.  Since FOCUS tends to poll slightly low for KDH and Polis tends to poll slightly high, the story–not one worthy of headlines–is KDH slightly up.
  • SaS.  Very little SaS news this month but that in itself is news:  FOCUS and Polis both show the party slightly down from last month, suggesting that Feburary may have been its peak.  A pre-election peak is a natural near-inevitability and is assisted by the election of Radicova to head the SDKU campaign during this period.  Watch what happens next here.   From the party’s position, the good news is that its peak and the resulting visibility is fairly high, permitting the party to sustain some losses.
  • Most-Hid and MKP-SMK. Both FOCUS and Polis show both parties slightly up, which seems unlikely in reality but which may be noise or a reaction to Hungarian-Slovak disputes.  In any case, MKP-SMK stands rather close to the threshold–too close for its comfort, I’m sure–but holds the organizational base, while Most-Hid stands higher but with a weaker voting base.  Either (but probably not both) could fall below the threshold… which brings me to a final thought.

The Importance of Thresholds.
As is to be expected these days, the Pravda headline writer announced yesterday, “Yet another poll shows opposition victory; HZDS remains below the line.”  And that is correct, as far as it goes.  The problem is “yet another” in this case means “yet another from the same polling firm” which is less surprising and that this firm has traditionally polled low for HZDS.  This is not to say that HZDS is not in trouble, but the lack of analysis is, as usual, unfortunate.  The really interesting point here–one which I do not blame newspaper writers for covering just yet–is that many parties are near the threshold and a .1% difference may shape Slovakia’s next government.  This month is an example.  The opposition and coalition are balanced closely enough that if one party from either side falls below (and there are two parties on each side near the line), it could mean victory for the other.  In the Polis poll dramatized by Pravda, it is HZDS that has fallen below, meaning that its seats get redistributed and Smer loses a partner, pushing it narrowly below the line.  Were HZDS 0.6% higher (7 more respondents in the poll), HZDS would stay above the threshold and the current coalition remains intact.  Such a small difference is not detectable by polls (even if we could get a perfectly representative sample and perfectly predict turnout behavior, it is still well within the margin of error).

It is also worth noting that an equally slight difference in SMK would put that party below the threshold and make it impossible for an “opposition” government, even if HZDS also fell below.

I hope to post more on threshold math in the near future.  Some preliminary calculations appear near the end of the Slovak Politics in a Nutshell post.

Dashboard News, February 2010: MVK shows Coalition Down

A new report from the polling firm MVK (the only company I know without a web address or logo) puts the current coalition down almost 5 points and the current opposition up by 6.  Here’s the poll:  http://spravy.pravda.sk/mvk-zostava-smer-hzds-a-sns-by-po-volbach-nezlozila-novu-vladu-pbp-/sk_domace.asp?c=A100309_094511_sk_domace_p12 .  But does it fit what we know from other polls?  More or less.

Coalition
As the dashboard shows, MVK’s numbers are within a plausible range nearly all parties.

  • Smer:  MVK shows a nearly 5% drop between mid-January and late February which seems rather large.  The other two polls we have (FOCUS and Polis) show the party with a slight recovery rather than a major drop during the same month, though MVK’s results did come late, however, and  it’s possible that something happened (not clear what that would be from the news) to reduce Smer support in a way that isn’t recorded yet in the other polls.
  • SNS: MVK shows a smaller loss for SNS but in some ways a more significant one because as far as I can tell from my records it is the first major poll since August 2004 to show SNS below the threshold.  Whether SNS is really that low is an open question (and one openly disputed by SNS which regards this poll as yet another election tactic by its opponents) but it is clear that every major poll has shown SNS down in recent months and the MVK poll certainly fits the trendline. Of course the party have low numbers because voters do not want to admit voting for it (this seems to have happened for HZDS during the 1990’s) but it could also have something to do with the party’s frequent scandals. Political commentators in Slovakia have argued that the party is immune to scandal because of its national message but that has struck me as rather condescending to nationalist voters. The fate of SNS will be–both for coalition development and for the overall tone of Slovakia’s politics–one of the most important questions in the coming election.
  • HZDS: MVK shows the party up a bit which is actually likely if SNS is really down. If one of these parties drops, the other is likely to be a minor beneficiary. It is fascinating, however, that the combined vote total for these parties is now down to around 10%-11%. Just two years ago the combined total averaged around 19%-20% in MVK polls.

Opposition
Most of these numbers, too, seem plausible though there is a bounce here that seems slightly unlikely:

  • SDKU: The poll shows this party up more than three points from last month which seems unlikely during a period of scandal, but last month was an exceptionally low month for SDKU in MVK and this merely returns the party to its levels for late 2009. Since the low poll came before the scandal and this more recent poll has come after (but before Radicova’s election), this would seem to offer some confirmatory evidence that the scandal did not hurt SDKU too badly, which makes some sense and gives some credit to Dzurinda for leaving the electoral list and more or less taking the scandal away with him.
  • KDH: The party’s 12.7 is the highest total (by a two point margin) that the party has received my 8 years of records of MVK polls. If SDKU were down this would make more sense to me, but it is hard to see this as anything other than a blip, even for a party that is doing better than it had in the past.
  • SaS: Is the same as last month suggesting that 1) the party has some staying power and 2) that the growth may be over. If this is SaS’s peak (and I have no way of knowing or thinking that it is) we now need to watch to see if the pre-electoral slide of new parties which hit ZRS, ANO, SOP and HZD will hit SaS and whethe it is enough. It is good for SaS that they are starting the slide from a relatively high point–at 9.2 they can lose nearly half and stay above the threshold–but not so good that there are 3 months in which to do it.
  • MKP-SMK and Most-Hid. Both are down slightly from last month’s MVK and Most-Hid is near the threshold of viability by these standards. I have no way of evaluating what the right level is; other polls have tended to put Most-Hid above SMK in recent months so MVK is different but not to be discounted for that reason. The real question is whether one of these two parties begins to fall short of 5% whether voters will flock to the other. The worst case scenario for Hungarians (short of both parties falling short of 5% which I still think is unlikely) is for one of these two parties to get nearly but not quite 5%. Right now the numbers make that a strong possibility. This means we have a 50%-50% chance of the best and worst-case scenarios (both in v. one weak party in) as opposed to a much stronger chance of a middle-of-the-road scenario (one marginally stronger party in, one weak party out).

Finally, a plea: Would MVK please include full results in its press releases as FOCUS and Median do. Perhaps it would help if journalists demanded them.

Slovakia’s politics in a nutshell

Everything you never wanted to know about politics in Slovakia and were therefore afraid to ask (lest I’d tell you).  I’ve finally had a chance to annotate an absurdly long and detailed presentation on Slovakia’s politics which derived in large part from the exercises I’ve been conducting on this blog (and past efforts).  The questions, some of which are rigorously answered in this presentation (and others of which I speed through hoping you’ll take my word for it):

  • What is politics in Slovakia about?  What is the struggle
  • Where is the power?
  • What are the parties like?  Their history, organization, voters, recent poll performance
  • What coalitions are possible after the elections?  Which are most probable?  Why?

Much of this is conjecture on my part, though I’ve tried to ground it as well as I could in data.  As always, I crave comments lest I write out into the void.

There are two versions:

American Politics in a Nutshell

imagesI am a comparativist by training and so it is not particularly surprising that I am fond of  T. S. Eliot’s famous quatrain from Little Gidding:

We shall not cease from exploration
And the end of all our exploring
Will be to arrive where we started
And know the place for the first time.

And I am therefore extremely grateful to Michal Kovacs of the Introduction to North America class at the Economics University of Bratislava for the chance to reverse the normal equation and talk about my own country using the tools that I usually use to talk about Slovakia.  Thanks, too, to the students who paid close attention and asked excellent questions (but I’m still not telling whom I would vote for if I were a citizen of Slovakia).  For those students who participated and for anyone else odd enough to care, a hasty, non-annotated (and therefore probably incomprehensible) .pdf of the talk is available here:

Since this is in many regards just a highly abbreviated version of lectures in my Citizenship class, the truly foolhardy can find a more extensive treatment at http://waynehonorsgold.pbwiki.com (login: waynehonorsgold@yahoo.com, login: abercrombie)