[R] log log regression model

[Andras Farkas]

Dear All,

wonder if you have a thought on the followimg: if I have a simple model like model <- lm(log(y)~log(x)+log(z),data=data), where both, the dependent and independent variables are log transformed, is it ok just to use ypred <- predict(model,type=response) to get the predictions , then transform ypred with exp(ypred)  to y's original scale to compare observed or known data (y) with model predicted (ypred) on the original scale?

appreciate your thoughts...

Andras