« Football managers on the hot seat | Main | Batmen not as interesting as it seems »



The reaction to the Australian unemployment figures http://www.abs.gov.au/ausstats/abs@.nsf/mf/6202.0 always amazes me. To a statistician they have a fairly obvious 95% CI of +/-0.2 pp, so they vary about 0.1 to 0.2 per month, occasionally more, but it is purely sampling variation. It takes at least 3 months, maybe more, of data before it is obvious what is happening in the economy. Even economists who you would hope would understand can't seem to understand this.

This graph will be updated, but if your looking at the February 2016 one, it is going down because of a massive property bubble. Something that economists can't understand either.

There really needs to be better understanding of sampling variation. A general course on statistics would work well without any hypothesis testing, only descriptive statistics and confidence intervals. Simulation could be used to explain the concepts.


Very interesting view. When you speak about ethics, my first thought goes to this video: https://www.youtube.com/watch?v=jWmUnU7HS-I (see in particular the animation at 1:20). It's a curious coincidence (really?) that I am the second reader who cited statistics about unemployment.

The comments to this entry are closed.

Kaiser Fung. Business analytics and data visualization expert. Author and Speaker.
Visit my website. Follow my Twitter. See my articles at Daily Beast, 538, HBR.

See my Youtube and Flickr.

Book Blog

Link to junkcharts

Graphics design by Amanda Lee

The Read

Keep in Touch

follow me on Twitter