Crikey readers will know about the Reuters Poll Trend, which comes out once a month. It uses something called the “Henderson moving average” to crunch together three regular polls.
The Reuters graph is a fine thing, but it has some shortcomings, and I reckon we can do better. So from now until election-day I’ll be regularly mixing up the polls, using my own herbs and spices, and publishing headline two party preferred numbers to the nearest half a percent.
Those so inclined can read more about the methodology here , but it involves, among other things, estimating the two party preferred from the pollsters’ primary numbers.
The biggest coup: two pollsters have very kindly agreed to provide, from now until the election, their voting intention data to one decimal place (rather than to the nearest integer, as it is published). I won’t be publishing those numbers, but they will greatly improve the quality of my aggregates. (One of those helpful pollsters is Galaxy; the other prefers to remain anonymous but is also one of the Big Four.)
Test-driving my formula on the final published polls before the 2004 election gives 52.5 to 47.5 in the Coalition’s favour – very close to the actual result of 52.8 to 47.2.
But back to 2007. The most recent calculation, for the fortnight ending with last weekend’s Newspoll, which was published today in The Australian is: 54.5 to 45.5 in Labor’s favour.
And the graph over the last six fortnights looks like this:
In general, my numbers put the contest about two points closer than would a raw averaging of the published two party preferreds.
So ok news for both sides: it’s a bit closer then is generally believed, but the gap isn’t noticeably narrowing.
Things will hot up between now and polling day, so stay tuned here (and keep an eye on Mumble for updates).