Posts from May 2012 (43)

As you will have heard, excises on smoking are going up.  This will raise money (to the extent that smokers don’t quit) and reduce smoking (to the extent that they do quit).   If you’re interested in the modelling used to estimate the impact on these conflicting goals, the Treasury’s Regulatory Impact Statement is a well-written and detailed explanation.

It’s also interesting to note that Treasury agrees the excise costs are already probably higher than the costs to other people imposed by smoking, and since the smoking excise is probably a regressive tax, the only convincing motivation for smoking excise taxes is to stop people smoking and so improve population health in the long term.

In this light it’s interesting that the Herald’s bogus poll for today is on whether increasing costs will lead to fewer smokers: at the moment, only 11% of responders think it will.  Fortunately, there is strong evidence that the poll respondents are wrong.

Team Ratings for Round 12

Here are the team ratings prior to Round 12, along with the ratings at the start of the season. I have created a brief description of the method I use for predicting rugby games. Go to my Department home page to see this.

Performance So Far

So far there have been 84 matches played, 48 of which were correctly predicted, a success rate of 57.14%.

Here are the predictions for last week’s games.

Predictions for Round 12

Here are the predictions for Round 12

Team Ratings for Week 14

Here are the team ratings prior to Week 14, along with the ratings at the start of the season. I have created a brief description of the method I use for predicting rugby games. Go to my Department home page to see this.

Performance So Far

So far there have been 87 matches played, 61 of which were correctly predicted, a success rate of 70.1%.

Here are the predictions for last week’s games.

Predictions for Week 14

Here are the predictions for Week 14. The prediction is my estimated points difference with a positive margin being a win to the home team, and a negative margin a win to the away team.

Hans Rosling had a question: Do some religions have a higher birth rate than others — and how does this affect global population growth? Speaking at the TEDxSummit in Doha, Qatar, he graphs data over time and across religions. With his trademark humor and sharp insight, Hans reaches a surprising conclusion on world fertility rates.

In Lake Wobegon all the women are strong, all the men are good looking, and all the children are above average.   We laugh because it is impossible for everybody to be above average.  It is quite possible, however, for 80% of the population to be above average. Take ten people two of whom die at birth and eight die on their hundredth birthdays. In our sample the average life expectancy is 80, and 80% live longer than average. Even if our two unfortunates live until they are 99, 80% still live longer than average.  So for any fraction, p%, other than 0% or 100% it is entirely possible for “p% of the population to be taller /shorter/ fatter / thinner / longer lived / or… than average.”

A blog post by a veteran editor, on one of the recurring stories about ‘lucky’ lottery-ticket outlets, explains elegantly and simply why it’s a real problem:

In some cosmic sense, sharing popular delusions about the lottery isn’t any worse than publishing the horoscopes. But if you’d like to be taken seriously when you proclaim “study says” or “poll reveals,” you need to run a disclaimer with your “want to hit the lottery” tales:

“We’re spending $70 per person to fill this out. That’s just not cost effective,” he continued, “especially since in the end this is not a scientific survey. It’s a random survey.”

That’s US Congressman Daniel Webster, quoted in the New York Times talking about the American Community Survey, the more-detailed part of the US Census that is administered to a 2% sample of Americans each year.  As you know, the fact that the ACS is based on a random sample is what makes it a scientific survey, and it is a very valuable one to US government and business as well as to researchers.

If the NZ census goes to a ten-year rather than five-year cycle, an interim sample similar to the ACS would be one way of maintaining up-to-date and accurate information at reasonable cost.  Or we could just leave information collection to Facebook and Wikipedia.

Thanks for all those who sent in a nomination last week for our Stat of the Week competition. Please enter this week’s competition too!

This week’s winner has been chosen to be Nick Iversen’s nomination of the New Zealand Herald’s editorial which says “Self-selecting polls show which option has the most supporters who care enough to cast a vote”:

The Herald appears to be trying to justify why they can headline bogus polls as news (https://www.statschat.org.nz/2012/05/13/bogus-polls-treated-as-news/).

But a self selecting poll does not in fact show which option has the most supporters among those who care to cast a vote.

The self-selectors did not select themselves based on their level of care. They selected themselves based on having internet access, reading the Herald web site, and willingness to participate in a bogus poll. They don’t represent any meaningful segment of NZ.

The poll is still bogus (even if they published the sample size).

James Russell from our department explains why this is our winner this week (even though there were some fantastic other nominations!):

Self-selection is one of many biases that can affect the results of a survey. In this case the winning post highlights that self-selection can have many filters imposed on it, including motivation to respond to the survey as a final probability filter (e.g. x% of people), however prior to that there are other filters such as access to the internet (z%) and reading the Herald website (y%).

In this simple case the probability of a random person responding is already at least a function of z% x y% x x%. This is certainly not a random subset and is unlikely to be a meaningful one of society. Internet polls can struggle from other fascinating biases such as viral hacking. These biases can never be completely avoided in any survey but any statistician should have some idea of the level of them and their potential impact on the results.

As the winning post, this highlights a methodological issue underpinning many of the statistics discussed on Stats Chat.

Congratulations Nick Iversen!

Each week, we would like to invite readers of Stats Chat to submit nominations for our Stat of the Week competition and be in with the chance to win an iTunes voucher.

Here’s how it works:

• Anyone may add a comment on this post to nominate their Stat of the Week candidate before midday Friday May 25 2012.
• Statistics can be bad, exemplary or fascinating.
• The statistic must be in the NZ media during the period of May 18-25 2012 inclusive.
• Quote the statistic, when and where it was published and tell us why it should be our Stat of the Week.

Next Monday at midday we’ll announce the winner of this week’s Stat of the Week competition, and start a new one.
(more…)

Team Ratings for Round 11

Here are the team ratings prior to Round 11, along with the ratings at the start of the season. I have created a brief description of the method I use for predicting rugby games. Go to my Department home page to see this.

Performance So Far

So far there have been 79 matches played, 44 of which were correctly predicted, a success rate of 55.7%.

Here are the predictions for last week’s games.

Predictions for Round 11

Here are the predictions for Round 11