Do polls lie?

In an oped in today’s Sydney Morning Herald, I make the simple point that opinion polls have a margin of sampling error. While the best US journalists and newspapers tend to incorporate this into their analysis, Australian articles often ignore the fact that the gap between the parties is sometimes smaller than the margin of error. When reporting a change from one poll to the next, the error margin is larger still, since both polls are measured with error. The bottom line is that it would be better to have fewer column centimetres devoted to the reading of polling tealeaves, and more spent on discussing ideas for our future.

Sidenote: This was the first time I’d written about multiple pollsters in an oped. I hadn’t realised before the sensitivity of the relationship between a newspaper and its primary pollster.

This entry was posted in Australian issues. Bookmark the permalink.