Elizabeth Barrette (ysabetwordsmith) wrote,
Elizabeth Barrette
ysabetwordsmith

  • Mood:

Study Bias

Here's a good list of types of bias that can ruin scientific studies

#10 has been described as "what the Thinker thinks, the Prover proves."  This one is inherent to scientific method as it is customarily presented.  The formation of a hypothesis prior to performing an experiment necessarily creates a bias toward proving that hypothesis, which is then difficult to resist.  Quite different results may be obtained by performing experiments to see what will happen,  without expectations.  This open experimentation is most useful in the early stages of exploration when one can learn a great deal about possibilities.  After observing for a while, it becomes more feasible to discern patterns and then test to see which ones are an accurate description of the system.

Notably missing was any form of a very pernicious bias, personal benefit.  This can be personal, political, or whatever but if someone strongly benefits from a particular outcome, they tend to favor it, which skews the results.  The closest is #1 File Drawer, an avoidance of publishing unfavorable results.  I'm talking about the front end, where politics influences what studies can even be done or what is labeled pseudoscience, and where money encourages researchers to find results favorable to their sponsors.  The vast majority of studies today are done by people who have a dog in the fight -- which renders them suspect at best and fraudulent at worst.
Tags: #1, #10, economics, news, politics, science
Subscribe
  • Post a new comment

    Error

    default userpic

    Your IP address will be recorded 

    When you submit the form an invisible reCAPTCHA check will be performed.
    You must follow the Privacy Policy and Google Terms of use.
  • 2 comments