[Phys-L] Re: Should Randomized Control Trials Be the Gold Standard of Educational Research?

[Brian Whatcott <betwys1@SBCGLOBAL.NET>]

At 04:30 PM 4/17/2005, Richard Hake, you wrote:
> ///
>
> In his Phys-L post of 16 Apr 2005 of the above title, Jack Uretsky
> (2005) wrote:
> I don't understand.  If you can't control the variables, how can you get
> statistically "valid" results?

To which Richard responded:

> My experimentalist friends (in particle physics) now divide
> uncertainties into a "statistical" part and a "systematic" part.


Characterizing uncertainties is all well and good, no doubt.

I would have responded to Jack's plea for controlling
experimental factors, in this way:
It is  unnecessary to control variables pertinent to an experiment
if only they can be measured and associated with the results.
When it is uncertain which factors are germane, it is still possible to
test their degree of association with the measured results, if they have
  been measured.  In this way multiple factors all varying, can be
accounted for, and often ARE accounted for in agronomic testing.


Brian Whatcott    Altus OK    Eureka!
_______________________________________________
Phys-L mailing list
Phys-L@electron.physics.buffalo.edu
https://www.physics.buffalo.edu/mailman/listinfo/phys-l