Electoral Calculus and pollster Find Out Now ran a couple of predictive polls in the run-up to the local elections in May 2022. How accurate were our predictions?
There were elections to 168 district and unitary councils in England and Wales on 5 May 2022. For these elections we ran an MRP poll, which interviewed over 12,000 respondents in the first wave and a smaller sample of 1,700 respondents in the second wave. The MRP method is often a bit more accurate than traditional polling approaches, and also allows estimates of public opinion in small geographic areas, such as district councils and council wards. More details of the MRP approach are available here.
The MRP poll allowed us to estimate the result in every council ward which was up for election. By adding up the wards won, it also predicts which party would win each council, or whether there was 'no overall control' (NOC) of the council.
The final predictions, including the council-by-council predictions, are visible on our website at Local Election Poll April 2022.
The poll predicted that Labour would gain 16 councils and that the Conservatives would lose 4 councils, and the Liberal Democrats would gain three councils. In reality, the direction of travel was correct, but both Labour and the Conservatives did worse than predicted.
The following table shows the number of councils predicted and actually won by each party:
| Party | Previous | Prediction | Actual |
|---|---|---|---|
| CON | 43 | 39 | 35 |
| LAB | 69 | 85 | 73 |
| LIB | 11 | 14 | 16 |
| Plaid | 1 | 1 | 4 |
| NOC/OTH | 40 | 29 | 40 |
| Total | 164 | 168 | 168 |
Of the 168 councils, the vast majority (138) were correctly predicted. Highlights include:
It's not possible to correctly predict every council, as some are very finely balanced, and others are driven by specific local factors which are hard to capture even in regional MRP polling. Mispredictions include:
The overall council results suggest that the two big parties both did a bit worse than predicted and the minor parties and independents did better.
We can also look at the ward results. These are shown in the table below.
| Party | Previous | Prediction | Actual |
|---|---|---|---|
| CON | 1,526 | 978 | 1,186 |
| LAB | 2,695 | 3,514 | 2,791 |
| LIB | 613 | 662 | 781 |
| Green | 49 | 23 | 124 |
| Plaid | 193 | 151 | 202 |
| OTH | 516 | 265 | 538 |
| Vacant | 1 | 0 | 12 |
| Total | 5,593 | 5,593 | 5,634 |
We correctly predicted that the Conservatives would lose hundreds of seats, but their seat losses were not as big as our poll suggested. We predicted around 550 seats lost in England and Wales, and the actual figure was nearer 350.
The results for Labour were less accurate. We predicted a large gain in council seats for Labour, and they actually only gained around 100 seats in England and Wales. That was a disappointing result for the polling and modelling, which will need further consideration.
Smaller parties and independents all did better than predicted which is, perhaps, a corollary of our over-prediction for Labour.
Overall the prediction worked satisfactorily, and correctly predicted that the Conservatives would lose councils and that Labour would gain councils.
We correctly predicted the headline gains for Labour in London, including the City of Westminster, Wandsworth and Barnet.
Overall, over 80pc of councils were correctly predicted, which is similar to results from the 2021 prediction. As usual, a small number of councils were mis-predicted.
In terms of predicted seats, the prediction gave a broad idea of the correct outline (Conservatives to lose seats, Labour and Lib Dems to gain seats), but the size of Labour's gains was significantly over-predicted.