Politics, elections and piffle plinking

Tag Archives: locally weighted polynomial regression

New Pollytrend Metric – Phone Pollster Trend

We all know about our Pollytrend chart – where we build a rolling average of the most recent poll from each pollster weighted by sample size, then run an aggressive locally weighted polynomial regression through the results to give us an adaptive trend line. While Pollytrend is good for picking up medium term shifts in [...]

Pollytrend – The August State of Play

During the polling cycle of the last fortnight, on the ALP two party preferred we’ve had Nielsen come in down 2 to 56 from June and Newspoll come in down 2 to 55 from last fortnight. Morgan Face to Face was down 2.5 to 58 from late July/early August and Essential moved down 2 from [...]

Pollytrend – Fading Coalition Edition

Now that this polling cycle is complete, we can update our Pollytrend to see whether the underlying trend in the cumulative polling results have changed.
Throwing in the new data for this fortnight and comparing this cycle’s Pollytrend with where our trend line was last fortnight gives us:

This cycle we’ve had Morgan Phone come in up [...]

Pollytrend – Where the polling now sits.

The end of the trend is nigh. Plugging the poll figures from this cycle into our Pollytrend algorithm – the locally weighted polynomial regression we run through an All Pollster pooled aggregation weighted by sample size -  shows how  the medium term trend running against the ALP since April has now bottomed out, even popping [...]

Pollytrend:Did the budget change the polling trends?

OK sports fans – as promised we’ll have a bit of a squiz at these post-budget polls collectively to see if there was a trend change – and to do this we’ll use our Pollytrend model. For those that don’t have a clue what I’m talking about, just click here for an explanation.
The reason we [...]

Pollytrend Tracking

With the last two polls (Nielsen and Essential) showing a move toward the ALP, it would be as good a time as any to show how our Pollytrend works in practice.
In the chart below, there’s 4 separate Pollytrend lines. The first – the blue line – shows where Pollytrend sits when the Nielsen poll is [...]

Nerdy Sunday: Predicting campaign effects

I was pondering over a glass of red the other day whether long term political beliefs have any residual effect from one election to the next? Particularly among swing voters – including those voters that tell pollsters that they will vote for Party A even though they normally and historically vote for Party B
If a [...]

Introducing Pollytrend

Today we bring a new metric to the blog specifically designed to measure change in political opinion. We’re all by now familiar with the Pollytrack series – the weekly polling aggregation of all pollster results weighted by individual sample size. The Pollytrack series is mostly good enough for ordinary periods of political activity, but it [...]

Pollytrack – Christmas Edition

With the final Newspoll and Essential Report for the year coming in (the results of which can be seen over at The Polls page) and with the December Nielsen poll going AWOL and not coming out at all (shame on you Fairfax), we ought to update our Pollytrack numbers. The last poll released was the [...]

Nerdy Sunday

Today we’ll have a bit of a squiz at how LOESS regressions (also known as local regressions and locally weighted polynomial regressions) are particularly spiffy for analysing polling behaviour over time. But before we get into that, we’ll have a look at our Intrade/Gallup Daily Tracker of the US Election showing the Obama surge continuing [...]