McCullagh, Peter - In: Journal of the Royal Statistical Society Series B 70 (2008) 4, pp. 643-677
In a regression model, the joint distribution for each finite sample of units is determined by a function "p"<sub><b>x</b></sub>(<b>y</b>) depending only on the list of covariate values <b>x</b>=("x"("u"<sub>1</sub>),…,"x"("u"<sub>"n"</sub>)) on the sampled units. No random sampling of units is involved. In biological work, random sampling is...