Unanticipated confounders

The burden of proof varies depending on the branch of science. When we establish causal relations in organic chemistry, we beat the drums and open up champaigne. Fundamental mechanistic insights enable us to formulate reliable hypotheses and pursue the next round of questions. Not long ago, I was reading a piece from The New England Journal of Medicine (my wife subscribes to this journal). I came across a most peculiar statement. It was something along these lines: “now that the causality has been established, really meaningful randomized control studies can commence”. That’s right: for those guys causality is just the tip of the iceberg. The reason is that, with causality demonstrated, one needs to balance the unanticipated confounders. The only way to do it properly is to design a double-blinded randomized controlled trial. Serious studies in medicine are unthinkable without analysis of large data sets. Imagine if chemistry were held to this standard. It might involve a respectable journal such as Org. Syn. sending 1000 referees a paper along with blinded bottles for each reagent used, asking them to repeat the experiments. What would a placebo for n-butyllithium be? I am not sure… Wouldn’t that be fun though? Of course I am joking, but elimination of subjective factors is the powerful feature of a double-blinded randomized controlled study.

2 thoughts on “Unanticipated confounders

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com 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 )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s