Dear all(statters)
I read a paper yesterday in which the same regression model
was fitted at three seperate time points during a child's early
development.
The three regression coefficients for each independent variable
were then examined and compared using a chi-square test to see
if the size of the effect differed across time.
Having never heard of this approach before I was just wondering
if it was a well established method or just something that the authors
made up.
if it is a standard method, does anyone know of a reference
describing its use with a dichotomous outcome?
Many thanks
Jon
|