July 14, 2012
Poll shows not much
According to the Herald
The latest Roy Morgan Poll shows support for the National Party has fallen two per cent since early June.
The poll is based on 948 people, so the maximum margin of error (which is a good approximation for numbers near 50%) is about 3.2%, and the margin of error for a change between two polls is about 1.4 times larger: 4.6%.
Thomas Lumley (@tslumley) is Professor of Biostatistics at the University of Auckland. His research interests include semiparametric models, survey sampling, statistical computing, foundations of statistics, and whatever methodological problems his medical collaborators come up with. He also blogs at Biased and Inefficient See all posts by Thomas Lumley »
So, by itself the result is not particularly newsworthy…
… forgive me for displaying my lack of statistical nous, but a couple of questions:
– at what point does the trend become relevant?
– and how do you calculate the margin of error between two polls?
12 years ago
This data provides evidence that there was a downward movement. It’s just non-overwhelming evidence – it’s still not particularly improbable that the real movement was up. It didn’t stay exactly the same either, that’s a silly hypothesis.
Tony, the answer to your first question is that there is no special point where something becomes significant. If the difference were greater, there would be more evidence, but it’s a continuous thing: the evidence just gets gradually stronger. There’s no cutoff point.
The second question would involve some mathematics so maybe not good for here.
12 years ago