Skip to main content
16 events
when toggle format what by license comment
Mar 19, 2016 at 12:47 history edited Ben S CC BY-SA 3.0
deleted 7 characters in body
Mar 19, 2016 at 11:18 vote accept Ben S
Mar 18, 2016 at 18:04 comment added Repmat @Nickcox exactly what I meant. But I suppose that $\beta_1$ would not be identified. I see the comment is unclear
Mar 18, 2016 at 17:57 comment added Glen_b @Repmat What are you taking the log of, exactly? I don't see how that works.
Mar 18, 2016 at 13:33 comment added Nick Cox OK, so you are reparameterising. That's not transformation (of variables), which was what I was inferring.
Mar 18, 2016 at 13:31 comment added Repmat Removing the product and the exp
Mar 18, 2016 at 13:29 comment added Nick Cox I don't see that anything, linear or nonlinear, will make $\beta_1, \beta_2$ separately estimable here. More positively, watch that GLM in different contexts means general linear models and generalized linear models, which overlap but are by no means identical classes.
Mar 18, 2016 at 13:28 comment added Nick Cox @Repmat How so? How will log transformation help here?
Mar 18, 2016 at 12:48 answer added Scortchi timeline score: 6
Mar 18, 2016 at 11:14 history tweeted twitter.com/StackStats/status/710786423536930817
Mar 18, 2016 at 8:42 comment added Repmat While you Are correct the function is not linear in the parameters, it can be made so with a log transformation
Mar 18, 2016 at 7:23 answer added Shijia Bian timeline score: 0
Mar 18, 2016 at 6:37 history edited Ben S CC BY-SA 3.0
added 4 characters in body
Mar 18, 2016 at 6:25 answer added probabilityislogic timeline score: 6
Mar 18, 2016 at 5:34 review First posts
Mar 18, 2016 at 6:16
Mar 18, 2016 at 5:29 history asked Ben S CC BY-SA 3.0