Shy Tory Factor

[Iannis]

"Shy Tory Factor is a name given by British Opinion polling companies to a phenomenon observed in the 1990s whereby the share of the vote won by the Conservative Party in elections was substantially higher than the proportion of people in opinion polls who said they would vote for the party. The Conservative Party is often referred to by the name of its predecessor party, 'the Tory party'.

In the 1992 general election, the final opinion polls gave the Conservatives between 38% and 39% of the vote, about 1% behind Labour. In the final results, the Conservatives had a lead of 7.6% over Labour. As a result of this failure to 'predict' the result, the Market Research Society held an inquiry into the reasons why the polls had been so much at variance with actual public opinion. The report found that 2% of the 8.5% error in the party lead could be explained by differential refusals to be interviewed by Conservative voters; it cited as evidence for this factor the fact that exit polls on election day also underestimated the Conservative lead, when they could not be affected by sampling error.

After the election, most opinion pollsters altered their methodology to try to correct for the observed behaviour of the electorate being less likely to admit to voting Conservative. The methods varied for different companies. Some asked their interviewees how they had voted at the previous election, and assumed that those who had voted Conservative before but were now unsure or refusing to answer would return to the party. Others weighted their panel so that their past vote was exactly in line with the actual result of the election. For a time, opinion poll results were published both for unadjusted and adjusted methods". Da wikipedia

Come vedete nelle elezioni inglesi del '92 vi fu uno scostamento del risultato reale da sondaggi ed exit-polls superiore a quello avvenuto in Italia. Eppure nessuno pensò a brogli ma con atteggiamento razionale si misero a ricercare le cause e trovarono questo fattore, del resto facilmente immaginabile: gli elettori del partito al governo e considerato "cattivo" sono spesso restii a dichiarare il proprio voto per questo, e ciononostante, lo votano. Accadeva anche con la DC in Italia, ed è successo alle elezioni del 9 aprile, anzi, in modo assai inferiore da noi.

[benfy]

il paragone ci sta come i cavoli a merenda in quanto in gran bretagna i sondaggi danno sempre un punto due in più ai laburisti rispetto ai risultati reali ed è una cosa notoria

[Iannis]

Veramente la difefrenza era ben più dell'1-2%. Per questo ci fu quello studio. Coem sempre si dovrebbe fare in simili casi. In Italia poi la discrepanza era anche minore...

[benfy]

infatti guardavo i collegi storicamente incerti che sono andati tutti ai tory