Corante

About this Author
DBL%20Hendrix%20small.png College chemistry, 1983

Derek Lowe The 2002 Model

Dbl%20new%20portrait%20B%26W.png After 10 years of blogging. . .

Derek Lowe, an Arkansan by birth, got his BA from Hendrix College and his PhD in organic chemistry from Duke before spending time in Germany on a Humboldt Fellowship on his post-doc. He's worked for several major pharmaceutical companies since 1989 on drug discovery projects against schizophrenia, Alzheimer's, diabetes, osteoporosis and other diseases. To contact Derek email him directly: derekb.lowe@gmail.com Twitter: Dereklowe

Chemistry and Drug Data: Drugbank
Emolecules
ChemSpider
Chempedia Lab
Synthetic Pages
Organic Chemistry Portal
PubChem
Not Voodoo
DailyMed
Druglib
Clinicaltrials.gov

Chemistry and Pharma Blogs:
Org Prep Daily
The Haystack
Kilomentor
A New Merck, Reviewed
Liberal Arts Chemistry
Electron Pusher
All Things Metathesis
C&E News Blogs
Chemiotics II
Chemical Space
Noel O'Blog
In Vivo Blog
Terra Sigilatta
BBSRC/Douglas Kell
ChemBark
Realizations in Biostatistics
Chemjobber
Pharmalot
ChemSpider Blog
Pharmagossip
Med-Chemist
Organic Chem - Education & Industry
Pharma Strategy Blog
No Name No Slogan
Practical Fragments
SimBioSys
The Curious Wavefunction
Natural Product Man
Fragment Literature
Chemistry World Blog
Synthetic Nature
Chemistry Blog
Synthesizing Ideas
Business|Bytes|Genes|Molecules
Eye on FDA
Chemical Forums
Depth-First
Symyx Blog
Sceptical Chymist
Lamentations on Chemistry
Computational Organic Chemistry
Mining Drugs
Henry Rzepa


Science Blogs and News:
Bad Science
The Loom
Uncertain Principles
Fierce Biotech
Blogs for Industry
Omics! Omics!
Young Female Scientist
Notional Slurry
Nobel Intent
SciTech Daily
Science Blog
FuturePundit
Aetiology
Gene Expression (I)
Gene Expression (II)
Sciencebase
Pharyngula
Adventures in Ethics and Science
Transterrestrial Musings
Slashdot Science
Cosmic Variance
Biology News Net


Medical Blogs
DB's Medical Rants
Science-Based Medicine
GruntDoc
Respectful Insolence
Diabetes Mine


Economics and Business
Marginal Revolution
The Volokh Conspiracy
Knowledge Problem


Politics / Current Events
Virginia Postrel
Instapundit
Belmont Club
Mickey Kaus


Belles Lettres
Uncouth Reflections
Arts and Letters Daily
In the Pipeline: Don't miss Derek Lowe's excellent commentary on drug discovery and the pharma industry in general at In the Pipeline

In the Pipeline

« Not Even Funny | Main | Structure-Inactivity Relationship Would Be More Like It »

October 20, 2002

Faces In the Clouds

Email This Entry

Posted by Derek

In the last post I mentioned the tendency people have to look for causes. It's innate; there's nothing to be done. We're conditioned by the world of our senses: a leaf falls in front of us, so we look up to find the tree. And this works fine, most of the time, for the macroscopic objects that we can see, touch, hear and smell.

It stops working so well on the microscopic scale. (And it goes completely to pieces on the really submicroscopic scale, when the colors of quantum mechanics start to seep through into the picture, but that's another story.) When we don't have direct sensory experience of the steps in a process, our intuition can be crippled. You can learn your way around the problems, but that has to be a conscious effort - the rules that we've all been practicing since birth won't be enough.

And this is where a lot of really bad ideas are born. Take the idea of a "cancer cluster." If we see a pile of large rocks with no others around, we assume that something moved them there. If we see a group of similar plants, we assume that they've grown there together from seeds or roots. But what is there to say when there's a group of cancer victims in a given area?

The temptation is overwhelming to say "something put them there." But it doesn't have to be so. People who haven't thought much about statistics don't usually have a good feel for what "random" means. It doesn't mean "even scattered in no particular pattern." It means "no particular pattern, and let the chips fall where they may." Looked at locally, a large random distribution isn't even at all - it's lumpy and patchy. Show a dozen untrained eyes a large scatterplot of random numbers and they'll never guess that there's no design behind it. Surely that bunch down there means something? And that swath that cuts over this way! Imposing patterns is what we do.

Discriminating between these accidental groups and any that might have a cause is fiendishly difficult. Generally, the only proof is statistical - you end up saying that you can't reject the null hypothesis, that this group is not larger than you would expect by chance. So in the absence of any hypothetical cause, there's no reason to assume that it's anything other than noise. Does that convince anyone? No one that really needs the convincing.

Statistics are all that'll save you, though, because the alternative is just noise and advocacy: trying to settle arguments by who's louder and more convinced that they're right. People who understand the math get upset when they argue with people who don't, because they can't make themselves understood. Their best evidence is in a language that the other side can't speak. Likewise, the advocates get terribly frustrated with the statistics-mongers, because they seem to be in the business of denying what's right in front of their eyes.

And that's why scientists and engineers are so happy to talk with other scientists and engineers. It's not that there aren't arguments - oh yeah, plenty of 'em - but there's at least a chance that you can convince people with data. Outside of those fields, I've come increasingly to think, the chances of doing that are often minimal.

Comments (0) + TrackBacks (0) | Category: General Scientific News


COMMENTS

EMAIL THIS ENTRY TO A FRIEND

Email this entry to:

Your email address:

Message (optional):




RELATED ENTRIES
How Not to Do It: NMR Magnets
Allergan Escapes Valeant
Vytorin Actually Works
Fatalities at DuPont
The New York TImes on Drug Discovery
How Are Things at Princeton?
Phage-Derived Catalysts
Our Most Snorted-At Papers This Month. . .