Here’s something I don’t get. It hasn’t been keeping me up nights, but I should get it, because I had to take statistics for 3 excruciating semesters. Sampling. The deal is, if you want information about a population, the most efficient way to get the information is by collecting a random sample from an observation set and testing it. The least efficient way is by testing every single widget. So why are we testing every single kid? What am I missing? Is this just a stupid federal mandate? A stupid state mandate? Am I really stupid that I don’t understand this methodology?
NAEP seems to think random sampling across schools works. Why wouldn’t this work on CSAPs? It would save money, time and pain. And it might accomplish a couple of other things as well. First, there is a lot of talk about “teaching to the test.”More here: http://www.headfirstcolorado.org/blog/index.php/2007-07-26/testing-123/
No comments:
Post a Comment