Friday, May 31, 2013

Predictions at 3.5 months out

In the past week a couple of analysts have turned their hand to forecasting the election outcome.

Julian King at Pottinger has developed a Bayesian model to predict the election outcome based on past election outcomes and the current polls. His conclusion: the Coalition has a 93.6% chance of winning the election, the ALP has a 1.9% chance of winning the election, and there is a 4.5% chance of a hung parliament.

In the Guardian, Simon Jackman (also drawing on Bayesian statistics) observes "I expect some narrowing to be more likely than the Coalition improving on 55-45 TPP. But bottom line: Labor just can’t get to an election winning position from here."


Kevin Bonham has looked at the above analyses. While he agrees with their conclusion, it is not because a five point move in the polls is uncommon. They have happened many times in past; just under different circumstances.

Paul Davis also had a look at these analyses. His assessment is more critical.

Tuesday, May 28, 2013

Weekly aggregation

This week we have two fresh poll reports. A status quo report from Essential (45-55), and 0.5 percentage point improvement for the government from Morgan (45.5-54.5). I have ignored the Queensland-only Galaxy poll, which was a shocker for the government (41-59). My model does not include single-state polls of Federal voting intention.

Both the LOESS and the Bayesian Aggregation suggest that over the past two months there has been a slow trickle of votes back to the government worth almost one percentage point (on the BA - don't get me going about the way in which LOESS exaggerates end point trends).

Sunday, May 26, 2013

Sensitivity tests

When writing about the Bayesian hierarchical model for the poll aggregation, I refer to the assumption that population wide voting intention today is much the same as it was yesterday. In my model I actually make a far more precise assumption: the day-to-day change in voting intention is normally distributed with a standard deviation of one percentage point. I chose this standard deviation for two reasons. First, it was the number initially used in Simon Jackman's model. Second, pragmatically, it seemed to work.

This week I received an email from someone doing similar modelling. In looking at their work, it appeared they had chosen a figure of 0.2 percentage points (one fifth of my value). It left me thinking that I need to do some sensitivity testing on one percentage point assumption I used up until now in my model. I decided to test a range of standard deviations between 5 and 0.1 per cent.

Five per cent

Two per cent

One per cent

Half a per cent

0.2 per cent

0.1 per cent

0.3 per cent

It is clear from the above charts that the day-to-day constraint has little if any effect on the model for the values in the range of 2 down to 0.5 per cent. This means that the daily walk in these runs is essentially unconstrained. At 0.2 per cent, it appears to be having significant impact, and 0.1 per cent it is clearly over-smoothed. The obvious thing to do now is to test 0.3 per cent.


While 0.3 percent has a small impact, it does not have enough in terms of smoothing the resultant aggregation (and ignoring the odd outlier rouge poll). In future, I will use 0.25 per cent in my model.

Tuesday, May 21, 2013

Weekly aggregation

With a fresh Budget to assess, every polling house was in the field searching for a Budget bounce. And you would never read about it, but they found one. The combined message is one of a small bounce-let for the Government. (And this is where I feel a compelling need to utter the following mantra as a public service: don't confuse correlation with causation. Just because some polls went up, it still could be noise, and even if its real it doesn't mean the Budget made it happen).

Monday, May 13, 2013

Weekly aggregation 44.2 to 55.8

Today's Morgan (56-44) and Essential (55-45) polls are largely narratives of the status quo. The Morgan result is identical to last week. The Essential result is the same as the previous independent fortnight; however, it is up a point for Labor on last week.

For the past six weeks, the Bayesian aggregation of Labor's two-party preferred polling has been bouncing along in a range between 44.0 and 44.6 per cent.

The end point of the series currently sits at 44.2 per cent. Like last week, this result would see the Coalition winning around 99 seats and Labor around 48 seats in the House of Representatives.

Tuesday, May 7, 2013

Weekly aggregation: back where we were a month ago

Last week, I urged caution with one poll suggesting a decline in Labor support. This week, we see more evidence of a decline in Labor support:

  • Essential has moved a point in the Coalition's favour (now 56 to 44) over last week and the previous independent fortnight
  • Newspoll has moved a point in the Coalition's favour (now 56 to 44) over the previous Newspoll
  • Morgan has moved half a point in Labor's favour over last week (now 56 to 44)

The raw poll results follow:

The decline has affected the Bayesian aggregation:

The projected seat outcome for the House of Representatives from the Bayesian aggregation was: 99 seats for the Coalition, 48 for Labor and three for others. The result almost tipped 100 (and indeed, the Henderson smoothed line above did tip 100-47-3).