Statistics are one of the most used and abused analytical tools in today’s world, and this article gives a good overview of a very common problem. When calculating the effect of a policy, behavior, or in this case, a medication, should you report the total effect or absolute percentage, or should you consider the likelihood of a change over a time period of use?
There is no right answer, you have to apply logic to determine which calculation is more appropriate – see below for more.
Via Medicine’s Dangerous Guessing Game – WSJ.com.
No related posts.