The randomized experiment , the decided unsexiness of the term masks a truly elegant and explicit form . Simply put , it's for devising answers to the questions that scientists across various disciplines seek to answer ; How do we know whether something works ? Or how do things work and why do they work that way .
Take a question that keeps reappearing regularly in the media each year : Is red wine good or bad for us ?? We learn a great deal about how red wine works by asking people about their consumption and health and looking for correlations between the two .
To estimate the specific impact of red wine on health , though , we need to ask people a lot of questions , questions pertinent to everything they consume ( food , prescription medication , more unsavory forms of medication ) , their habits ( exercise , sleep , sexual activity ) , their past ( their health history , their parents' and grand parents' health histories ) and on and on , and then try to control for these factors to isolate the impact of wine on health . Think how long and complicated this survey might be .
Randomized experiments completely re engineer how we go about understanding how red wine works . We take it as a given that people differ in the many and various ways described above ,( and many other ways as well ) but we cope with these variances by randomly classifying and allotting people to either ; drink wine or not .
If people who eat doughnuts and never exercise are equally likely to be in the " wine treatment " or the "control treatment ," then we can do a decent job of assessing the average impact of red wine over and above the likely impact of other factors .
Randomized experiments are by no means a perfect tool for explanation , but they sure help informing us how things work (or don't work ), and why they work this or that way .
Inspired and compiled from excerpts commenting on the works of the late P. Meier by I. Norton , my usual gratitude for your time , salamat .
No comments:
Post a Comment