Are polls reliable?
After the EU elections: fuss about the pollsters
The FPÖ "only" achieved 25.36 percent. Before the elections, it was polling at up to 30 percent. Criticism of its fallibility is being voiced again. The pollsters are fighting back.
What percentage should it be? 30 or 25, 23 or 19? The pollsters are once again the focus of criticism after the election evening. The FPÖ has been far ahead in all polls for months - for the National Council and EU elections - and in the end they won just ahead of the ÖVP, with the SPÖ in third place.
What's going on? Not much for pollster Peter Hajek (Unique). He had the FPÖ at 30 percent before the election. "We slightly overestimated them," he says. You have to consider the fluctuation range. It was between 26 and 34 percent. The FPÖ ended up with 25.36. "Admittedly, that was slightly off the mark. We got the other parties absolutely right."
The explanation: the DNA was not on the radar. It came out of nowhere, so to speak, and addresses an FPÖ issue with coronavirus scepticism. Secondly, many potential blue voters did not go to the polls.
"Well placed overall"
Christoph Haselmayer (IFDD) also says that the range of fluctuation is not made transparent enough in the publication, as the media want concrete figures.
"It is not made clear enough that this is an estimate. The research is off the mark when it is clearly outside the fluctuation range," explains communications scientist Matthias Karmasin. In these elections, the overall results were good.
In addition to the 30 percent for the FPÖ, there were two outliers at another institute: 19 percent for the ÖVP and 15 percent for the NEOS (ultimately 10.14).
Exciting election day polls
The trend research based on election day polls conducted by Foresight, ARGE Wahlen and Peter Hajek before election day also caused astonishment. At 5 p.m., 27 percent were reported for the FPÖ. ÖVP 23.5, SPÖ at 23. With a fluctuation margin of 2.5 in the green area, the researchers argue.
Peter Hajek cites very specific figures here: "95 out of 100 polls are within the fluctuation range. So that's correct. Generally speaking, you have to say. The surveys are 40 percent craft, 40 percent experience, 20 percent luck." They are an approximation of reality, not precision landings. The best way to achieve this is through exit polls, says Haselmayer. In other words, nationwide surveys immediately after the votes have been cast on the ground. "But that's far too expensive."
This article has been automatically translated,
read the original article here.
Kommentare
Liebe Leserin, lieber Leser,
die Kommentarfunktion steht Ihnen ab 6 Uhr wieder wie gewohnt zur Verfügung.
Mit freundlichen Grüßen
das krone.at-Team
User-Beiträge geben nicht notwendigerweise die Meinung des Betreibers/der Redaktion bzw. von Krone Multimedia (KMM) wieder. In diesem Sinne distanziert sich die Redaktion/der Betreiber von den Inhalten in diesem Diskussionsforum. KMM behält sich insbesondere vor, gegen geltendes Recht verstoßende, den guten Sitten oder der Netiquette widersprechende bzw. dem Ansehen von KMM zuwiderlaufende Beiträge zu löschen, diesbezüglichen Schadenersatz gegenüber dem betreffenden User geltend zu machen, die Nutzer-Daten zu Zwecken der Rechtsverfolgung zu verwenden und strafrechtlich relevante Beiträge zur Anzeige zu bringen (siehe auch AGB). Hier können Sie das Community-Team via unserer Melde- und Abhilfestelle kontaktieren.