Tuesday, February 17, 2009

A Good Science Article. No... Really.

A science article by someone who understands science! Holy crap, finally! God only know the number of POS articles that appear in health sections of newspapers and magazines that promise antioxidants will cure you or that plastic bottles will kill you. I would go so far as to make this article a must-read in every high school. Very few people understand that scientists don’t perform studies to achieve newspaper headlines (okay, well some probably do), but by and large they are working incrementally towards answering a larger questions, publishing the results of the lesser questions along the way. Meanwhile, their research could be flawed or preliminary.

An important take-away message from this article is the scientists miss things sometimes, and when dealing with complex multi-variable phenomena they are especially prone to overlooking a key variable. Even the best and the brightest have had their ideas ruthlessly shot down. Right now I’m reading James D. Watson’s autobiographical book, Avoid Boring People: Lessons from a Life in Science. This was the man that co-discovered the structure of DNA. Long before this ever happened though, he writes about being a graduate student who had his some of his research findings on phages eviscerated by no less than Leo Szilard- who switched to biological experimentation after World War II.

I wish the author of the article would have had the time to go into statistics and significance. A good introductory book on the subject is the classic How to Lie with Statistics, by Darrel Huff (which also manages to be a really good read). It may have gone over the heads of a lot of readers but it’s something that I think more people should be familiar with. If for no other reason than it helps them to identify when someone is lying that someone else is lying with statistics.

UPDATE: It might help if I actually link the article I'm referring to. Oops.

2 comments:

  1. By "eviscerate" does he mean "plagiarize"? I will have to check this out since I am a Szilard fan and have not heard of this before, most notably not in Szilard's biography "Genius in the Shadows". How To Lie With Statistics is great.

    ReplyDelete
  2. Sorry about the above statement; I misunderstood. Must. Get. Coffee.

    ReplyDelete

Freedom of speech! Comment freely. I will delete just as freely. Generally, avoid being obnoxious and you'll avoid frustration.

Keep in mind your comments may be held up by a spam filter.