… which a well constructed opinion poll would be able to defeat or trump the results of an election. We know that the set of people who actually vote is not a random sample of the population, but we continue to accept voting as a legitimate means of collective decision-making (though we may…
I refer back to my previous point on the size of the sample this time round and the cross party interests. Given normal political engagement in non-general elections is in the low 20’s, the relatively high turnout of the referendum, which was comparable and often bigger, than the size of the General Elections, indicates that many people who voted are not regularly engaged in political discourse or activity. Hence, increasing the variability of the sample and thus, it’s randomisation and thus, pulls it forward to the population at large.
Note, I care little for opinion polls. The issue isn’t the science, it’s that opinion polls are inherently unscientific and are not reliable measures and not what I refer to when I use the term sampling. It returns back to your previous reference. A vote is a sample of the opinion of the population at large. A poll is a relatively small sample, over a short time, often in a local geography. Each of those increases the specificity of the result and is almost useless as a predictor, not least due to the level of type 1 and 2 errors.