Submitted by Mish Shedlock of MishTalk
Yesterday I wrote how that even recent phone polls show Leave ahead in the Brexit debate.
A BMG poll that was supposed to be released on Friday was delayed until today. That poll strongly reverses other recent telephone polls.
The headline reads “Remain 53.3%, Leave 46.7%” but that representation is quite inaccurate.
The BMG/Herald Final EU Referendum shows Remain leads 46% to 43% with 11% undecided.
Don’t Knows and PNTS (prefer not to say) totaled 11%. From this set of numbers BMG issued the final result “Remain 53.3%, Leave 46.7%”. Remain lead by 7pts after imputed DK/PNTSs.”
Why impute voting intention for Undecideds and Refusals?
BMG states “It is our view that using predicted voting intentions to impute voting intentions for undecideds and refusals is preferable and more accurate than existing methods of excluding undecideds and refusals.”
Headline Numbers Believable?
In a word, No (at least without normalizing the results to other polls).
Let’s do that now.
Recent Phone Poll Analysis
The above tabulation is the best interpretation as to where we stand now.
The latest poll is actually Survation, but is it biased to Leave?
Leave Bias
BMG notes “Our latest poll took 6 days to complete for just over 1,000 responses. Some respondents are harder to reach than others, and some are more difficult to convince to take part in a survey. If there’s no response our interviewers will call the sample of respondents up to eight times and never at the same time of the day. It is for this reason that the majority of our survey responses are collected on the second or later attempt.”
Survation was the only pollster not to conduct its survey over multiple days. If one disregards Suration for that reason, the two latest polls are BMG and Ipos MORI.
BMG has a 3 point lead for Remain whereas IPOS Mori has a 6 point lead for Leave. ICM is the next most recent poll and it has a 5 point lead for Leave.
No Trend Change
One poll does not change the trend. It does suggest things are not as clear-cut for Leave as they were.
Moreover, we still do not know how the death of Jo Cox affects the overall results. To understand, we need to see new polls after the her senseless murder.
