Are diversity statistics misleading?


I just read the article in Legal Week (“CMS sets out female promotions as key issue“) and wondered whether the numbers provided are statistically significant.

For example, there are practically no black or black British partners or associates – but 7% Asian associates.

There are quite a few lawyers working at CMS, but not a huge number, so gaps could be considered accidents of fate rather than deliberate decisions indicating a particularly sexist or racist environment. What I mean is: it is likely that the particular mix of people is luck.

The comparison group should be everyone in similar law firms – I suspect CMS come out as good as – or better – than most, and the differences could be entirely due to random fluctuations.

In the seventies, Kahneman and Tversky wrote about “belief in small numbers“, where people (scientists) drew conclusions from samples that were too small to be statistically significant. You’ve got to have a lot of people in your sample to be able to say “the statistics support my conclusion”. Many people don’t have enough.

So: More to be done in law firms to increase diversity, for sure; but CMS can’t be described as awful compared to peers.

The evidence doesn’t stand up.


Add yours →

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

%d bloggers like this: