Betting market update
Since last Sunday, there has been little movement to report. One bookmaker has moved in Rudd’s direction just slightly. Three have moved in Howard’s direction, again just slightly. One is unchanged. Today the average probability for a Coalition win at the 2007 election is 48.8 per cent. It was 48.5 per cent last Sunday.
| Bookmaker | Coalition Odds | Labor Odds | Probability of a Coalition Win |
|---|---|---|---|
| Centrebet | $1.90 | $1.87 | 49.6% |
| IASBet | $1.95 | $1.85 | 48.7% |
| SportingBet | $1.95 | $1.85 | 48.7% |
| SportsBet | $1.95 | $1.83 | 48.4% |
| SportsAcumen | $1.93 | $1.83 | 48.7% |
What is the betting market doing? I have no idea. Nonetheless — and just for the fun of it — I fitted three regression curves to the market movements since 1 January 2007. These market movements are represented by the purple points on the chart in the 5 bookie average series.
The first curve is linear and explains 53 per cent of the variance to date. It suggests the market will continue to trend in Rudd’s favour. The second curve is logarithmic. It explains 67 per cent of the variance to date. It also suggests the market will continue to trend in Rudd’s favour, but at a slower rate than predicted by the straight line. The third curve is a fourth order polynomial. It explains 99.9 per cent of the variance to date. It suggests the market will turn back to Howard.
To help understand the regression formula, the x axis is expressed in days since 1 January 1900. So, for example, the constant 39073.4 in the logarithmic equation is late morning on 22 December 2006.
Finally — and this should not need to be said — none of these curves can be used as a serious or reliable projection of where the betting market will be when the election is called. I just thought it would be interesting to speculate on what sort of trends may be manifest.
The other graphs are here. You may need to hit the refresh or reload button on your browser to see the latest graphs.