I'm given a model of the form $E(\ln Y|X)=X\beta$.

Should I call it a linear model or loglinear model?

I'm assuming $Y$ is log-normally distributed.

  • $\begingroup$ How would you call $E(Z|X) = X\beta$ where $Z=\ln Y$..? $\endgroup$ – Tim Nov 24 '16 at 10:15
  • 1
    $\begingroup$ This would be linear, so $Z$ has a linear form $\rightarrow E(\ln Y|X) = X\beta$ is linear? $\endgroup$ – GRS Nov 24 '16 at 10:24

$ E(\ln Y|X)=X\beta $ is a linear model of transformed variable $\ln Y$, more precisely, it is linear in parameters. As I noted in the comment, you can introduce additional variable $Z = \ln Y$ and then $ E(Z|X)=X\beta $ is just an ordinary regression model. You can make all kinds of transformations to your variables, but when talking about linearity of the model, we have in mind the relationship between variables.

  • $\begingroup$ I've got 2 models, one of the form $E(Y|X)$ and the other $E(\ln Y|X)$ where in both models I investigate $Y$. I was refering to $E(\ln Y|X)$ as the loglinear model, is this incorrect? $\endgroup$ – GRS Nov 24 '16 at 12:01
  • $\begingroup$ I can see that, given the transformation I can call it a linear model, but without the transformation, it is a loglinear one? $\endgroup$ – GRS Nov 24 '16 at 12:02
  • $\begingroup$ Both are linear for the reasons given above. "$\ln$" is not a part of your model, it's a transformation of the variable. $\endgroup$ – Tim Nov 24 '16 at 12:13
  • $\begingroup$ @GRS Check stats.stackexchange.com/questions/43930/… to see the difference. $\endgroup$ – Tim Nov 24 '16 at 12:15
  • $\begingroup$ thanks, could you comment on this kenbenoit.net/courses/ME104/logmodels2.pdf ? It seems to classify them as loglinear $\endgroup$ – GRS Nov 24 '16 at 12:22

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.