Statbusters: Were you drunk on Labor Day?

On Labor Day, our new Statbusters column appeared. This one concerns a popular news story from some weeks ago, saying science has proven that there are four types of drunks. The four refers to four "clusters" formed by running a cluster analysis algorithm. But four is decided by the analyst. Some algorithms won't run unless the analyst specifies the number of clusters; other algorithms generate the best structure for every number of clusters. This method is great for exploring and understanding the data but cannot confirm that there are precisely four types of drunks!

The media often removes the uncertainty of science in the name of "popularizing." The entire article is here.

Comments

[Ken]

While it has problems I don't see this study as being as wretched as you make out. A lot of this type of work is still based on qualitative methods where there is no attempt to be scientific.

They've used a sensible method of identifying the clusters and determining the number to answer a reasonable research question. Probably they should have mentioned that the classes could be further subdivided but that is an almost basic assumption. After all the classes are heterogeneous as they are based on multivariate normal, so there is an assumed variability within each class.

They should definitely ditch the funny names and think up descriptions which are more scientific.

[Kaiser]

Ken: Thanks for the note as usual. Inside the article, we specifically said we don't have an issue with the research but we have an issue with the media trumpeting it as if someone discovered there are four types of bases in DNA.

[Ken]

Thanks. Most likely the newspapers used the university supplied press release. I've never been lucky or unlucky to do anything that warrants a press release, but my brother who works for a large government organisation does. He is not allowed to write them, this is the realm of the media department, who are then not required to gain approval from the scientists and engineers to make the release. As they are not scientists or engineers you can imagine how wrong they can be.