Great piece in Political Betting on "herding" pressures on Pollsters
I will be careful not to pay too much attention to the opinion the polls in 2020, and sadly an excellent article by Nick Sparrow on Political Betting here tends to confirm me in that view.
Nick, former head of polling at ICM, says that
"A pollster with results diverging from the average will be asked by their client and others to examine every aspect of the methods for anything that might be “wrong”. A pollster with results on the average can relax."
He quotes the Market Research Society in the report published after 1992, the last time the polls got it as badly wrong as they did this time:
Unfortunately this is easier to say than to do. When he instituted new methods in the run up to 1997's election (in which ICM was closer than other pollsters),
"in the run up to polling day the pressure to adopt the alternative, less accurate average of the rest, was intense."
He concludes
"Now, as then, pollsters should be seeking new solutions, and be unafraid of producing results very different to each other. The average is clearly not to be trusted. Sadly, I suggest, the likelihood is that come 2020 both pollsters and political commentators will again be converging on the average."
Nick, former head of polling at ICM, says that
"A pollster with results diverging from the average will be asked by their client and others to examine every aspect of the methods for anything that might be “wrong”. A pollster with results on the average can relax."
He quotes the Market Research Society in the report published after 1992, the last time the polls got it as badly wrong as they did this time:
“We would encourage methodological pluralism; as long as we cannot be certain which techniques are best, uniformity must be a millstone – a danger signal rather than an indication of health. We should applaud diversity; in a progressive industry experimentation is a means of development. No pollster should feel the need to be defensive about responsible attempts to explore in a new direction …
Unfortunately this is easier to say than to do. When he instituted new methods in the run up to 1997's election (in which ICM was closer than other pollsters),
"in the run up to polling day the pressure to adopt the alternative, less accurate average of the rest, was intense."
He concludes
"Now, as then, pollsters should be seeking new solutions, and be unafraid of producing results very different to each other. The average is clearly not to be trusted. Sadly, I suggest, the likelihood is that come 2020 both pollsters and political commentators will again be converging on the average."
Comments