Less research is needed

In which a health blogger gets dangerously close to putting her finger on what's wrong with climate science, but pulls back and zings several sacred cows in health research instead:
On my first day in (laboratory) research, I was told that if there is a genuine and important phenomenon to be detected, it will become evident after taking no more than six readings from the instrument.   If after ten readings, my supervisor warned, your data have not reached statistical significance, you should [a] ask a different question; [b] design a radically different study; or [c] change the assumptions on which your hypothesis was based.
H/t Rocket Science.

6 comments:

  1. But...but...we feel this impending doom because mankind is out of touch with nature, especially western civilisation with its Machines, and Chemicals, and Plastics...when we should be doing spiritual things like contemplating nature and staring into the embers of campfires, like we used to do at camp when we were little.

    Therefore we know that something is terribly wrong, and our society has to reverse course and put the right people, who think like us, in charge, because then we'll be safe. Otherwise, a plague o'er all the earth.

    All that remains is to discover exactly what bad thing the bad people are making happen, and make them stop.

    ReplyDelete
  2. Research is costly in time and money compared to throwing a few virgins in the volcano.

    ReplyDelete
  3. It must be nice to have such easy analyses.

    ReplyDelete
  4. I think we may have to make an exception for some lines of research. James is hereby officially allowed more than ten readings before he revamps his experimental program.

    You're welcome.

    ReplyDelete
  5. Simple comments are not necessarily the product of easy analysis. Good analysis usually yields a relatively simple answer. Complex answers usually hide some point where we haven't figured things out yet, or where the question was too fuzzy.

    ReplyDelete
  6. Or, in the case of the examples cited by the linked author, where someone too desperately wanted a particular answer.

    ReplyDelete