What is the difference between slection crieteria and validity and reliability?
Social and Medical sciences uses these statistical concepts.
ideally, we have to measure the same way each time, but
intrasubject, interobserver and intraobserver variance occur, so we
have to anticipate and evaluate them. In short, it is the
repeatability of a measurement, by you, myself and everybody person
or instrument.
Validity is how much the mean measure that we got is near of the
true answer or value.
So, an instrument can be reliable but not valid, valid but not
reliable, both valid and reliable, nor valid neither reliable.
I suggest that you imagine a target:
you can aim and
1) always get the center (both valid and reliable)
2) always get the same distant point (reliable but not
valid)
3) err much around the true center (valid but not reliable - the
mean and median of your arrow's shot will get the center)
4) err much around the another center, false one (nor valid
neither reliable)
I did not understood exactly what selection criteria have to do
with the rest of question, so, left in blank ;-)