Bad Statistics From A Government

12/14/08 - StumblingAndMumbling   --> Source

The UK released statistics on knife crime. This post neatly asks questions that everyone should apply to all statistics. And more so, if it is a government trying to justify its actions and expenditures. Do the statistics really mean anything?

Read more ...

[edited] Sir Michael Scholar of the UK Statistics Authority accuses the Home Office of releasing “premature, irregular and selective” statistics on knife crime. This actually understates the case. Even if the Home Office’s numbers were accurate, they would still verge on the meaningless. There are at least seven questions which should be asked about many statistical claims.

Does the percent change mean a lot or a little?
What would have happened without special police action?
Were the selected areas special?
What is the usual volatility of the figures?
Do the figures vary by season?
What exactly do the figures measure?
What is the cost of this policy?

The Home Office makes no effort to answer these questions. This suggests they have no interest in statistical analysis, or they thought they could present such sloppy twaddle because journalists wouldn’t ask these questions.

This suggests a problem deeper than using premature numbers. It suggests that our political culture, our politicians and journalists, have no interest in proper statistical analysis at all.

This is odd. We are supposed to be living in a technocratic era without political ideology, where evidence-based policy is applied, and “what matters is what works.”