Back in the day one of the first things I used to teach in my undergraduate biostatistics classes was that correlation is not causation.

For example, there may be a pattern between sun spot activity and the number of storks nesting in northern Europe, but you cannot conclude that sunspots cause nesting success. If it were that easy to assign a cause to all the patterns we see then a whole bunch of professions from currency speculation to climate change science would be unnecessary.

In my classes I used the presence of correlation to introduce the two main theme of my course: the concept of chance and the importance of the scientific method in helping us know when it is reasonably safe to ignore it.

Chance, and its measure probability, is a concept more intuited than taught. It was always fun to see the lights go on for a student who got it. More often though the pain of understanding likelihood was forsaken and students reverted to the age old standby of wrote learning.

All this recollection came about after I listened to a radio host who was recounting figures showing a significant spike in poker machine revenue in May and June 2012 (up 10 and 7%) across Australia. And in the same breath he reminded listeners that this coincided with cash payments to households from Federal government as compensation for cost of living rises from its introduction of a carbon price.

Now, of course, the radio host was smart. He didn’t imply or even hint that there was a causal relationship between the arrival of free cash and an increase in gambling revenue; but merely placing the two pieces of information together was enough.

My own emotions leapt to confirm gross inefficiency and lack of foresight in the government policy frame. Obviously people spent the money gambling.

Back in the classroom I would have berated my students for making the connection that I made. And really there is no evidence that a one-off cash payment to pensioners and low-income households ended up in slot machines, or even that some of it did.

Except that 10% of monthly poker machine revenue is roughly $100 million. This is a tidy sum and $500 more than usual in each and every poker machine.

Given that roughly 600,000 Australians play pokers machines weekly, that $100 million will be around $167 each.

The cash payments for families were $100 per child and for pensioners $250.

Chance is a fine thing.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s