So how does this then distort having such a low floor, in a sense, of an assessment? How does this distort effect sizes and what we can tell is the power of a particular program?

I think there are other papers more sort of from the psychometrics literature on the sort of suitability of the assessment for the group here.

And one of the big issues that we are concerned with in any test development is floor effects and ceiling effects.

So that would be, we're trying, what we want for all of these programs is a fairly smooth distribution of scores, right? I want to be able to separate all of the children.

I want to be able to discriminate and put on a line, right? So that I can say this kid's got the highest level of performance in my particular test, and this kid's got the lowest level of performance in my particular test.

And if we have a floor effect, that means that we get a lot of kids who score zero on this test.

Well, let's say that half of the kids scored zero on this test, which would be quite common, actually, among many of these oral reading fluency assessments.

where there's not necessarily even a very easy way of explaining