Not Clever

One of the nicer things about working at the VA Spa. 
Our groundskeepers are top drawer.  If I find out what these
are I will update.  If you know what they are please tell me

Further thoughts on this article.

One of the most irritating aspects of Western Medicine and thought is the idea of the "Model".  It pervades everything.

One of our self-anointed geniuses who inhabits the halls of academe that provide the future practioners of anesthesia once told me, with a straight face, that "the plural of anecdote is not data"!!!

This guys claim to fame is that he lost on Jeopardy.

I can see why.

That particular statement is why the current way of doing science is doomed for failure.  Because the individual observations that make up the body of the data are trivialized.  Service to the model comes before everything.  If the data does not fit the model, the data must be made to disappear.  Most importantly, data not fitting the model and must be trivialized.

I think that what we are looking at is overreach.  Science and the scientific method worked for a long time because the hypotheses generated were sufficiently non-complex that the results generated actually applied.

Now, when a model is proposed, scientists think that they need to "prove" that the model works.  All sorts of statistical gyrations need to be laid down to stretch the tattered weave of data over the model.

Nope, science works best when there is a clear question with clean measurement methodology (preferably yes/no).  As soon as a scientist starts yammering about the need for a statistician, you can rest assured that the data to be presented has a strong chance of being less than conclusive.

Think about these:

If your experiment needs statistics, you ought to do a better experiment.

Lord Ernest Rutherford 

It doesn't matter how beautiful your theory is, it doesn't matter how smart you are. If it doesn't agree with experiment, it's wrong.

Richard P. Feynman

All models are wrong, but some models are useful.

George E.P. Box (1979) Robustness in the strategy of scientific model building, in Robustness in Statistics, R.L. Launer and G.N. Wilkinson, Editors. 1979, Academic Press: New York.