Thread by @centrist_phone

The new @KantarTNS poll shows the Tory lead dropping by 7%, and an 11% Con lead. The headline figures are weighted using Kantar's turnout model.

So what happens if we re-weight the data to 2017 General Election turnout levels?

In short - a Labour surge...

1/1

At the moment Kantar are using a turnout model that's hard to fully pick apart in their raw data.

We do know is that it is modelled based on 60% overall turnout. The 2017 general election turnout was 68.8%.

This matters. Occasional voters are more likely to vote Labour.

2/2

So, I've re-weighted the Kantar data to 2017 general election turnout across each age crossbreak;

18-24: 55%
25-34: 56%
34-44: 57%
45-54: 66%
55-64: 70%
65+: 70%

Voting intention comes out as:

CON: 37.8% (-5.2%)
LAB: 34.1% (+2.1%)

The gap closes by 7.3% - to just 3.7%.

3/3

It seems that the Kantar turnout weighting is making three potentially big mistakes

1) Assuming overall turnout is going to be 60%
2) Assuming that younger people will not vote in similar numbers to 2017
3) Assuming that older people will vote in greater numbers than 2017

4/4

Kantar are an exception in having a very harsh turnout model.

But even other pollsters, who use self-reported turnout, are nowhere close to using turnout numbers comparable to 2017.

If the election ends up with similar turnout, they are all over-stating the Con lead.

5/5