- My Forums
- Tiger Rant
- LSU Recruiting
- SEC Rant
- Saints Talk
- Pelicans Talk
- More Sports Board
- Fantasy Sports
- Golf Board
- Soccer Board
- O-T Lounge
- Tech Board
- Home/Garden Board
- Outdoor Board
- Health/Fitness Board
- Movie/TV Board
- Book Board
- Music Board
- Political Talk
- Money Talk
- Fark Board
- Gaming Board
- Travel Board
- Food/Drink Board
- Ticket Exchange
- TD Help Board
Customize My Forums- View All Forums
- Show Left Links
- Topic Sort Options
- Trending Topics
- Recent Topics
- Active Topics
Started By
Message
Posted on 2/7/14 at 3:47 pm to Winkface
Only if you want to pull outlying data from a positively skewed distribution closer to the bulk of your data in your quest to have the variable be normally distributed. Otherwise, I'd say don't do it.
ETA:
Much confusion exists about the normality assumption for multiple regression. Many people think that all the variables in a regression equation must be normally distributed. Nothing could be further from the truth. The only variable that is assumed to have a normal distribution is the disturbance term U, which is something we can't observe directly. The x variables can have any kind of distribution. Because y is a linear function of both the x's and U, there's no requirement that y be normally distributed either.
Another thing to keep in mind about the normality assumption is that it's probably the least important of the five assumptions....
Sometimes, however, log transformation of the DEPENDENT variable helps to satisfy another assumption of linear regression (homoscedasticity). Nonetheless, for reasons that have nothing to do with classical statistics or model assumptions, I actually argue that the dependent variables in linear regression should ALWAYS be log-transformed, followed by computation of a geometric mean ratio (rather than a mean difference.) I am talking about linear regression in the context of estimating an effect--not for purely predictive purpose. The explanation is too long and goes back to fundamental questions about measuring effects: should effects be measured as differences or as ratios, or may we simply toss a coin to decide?
If we talk about the independent variable (x), then log-transformation is, in my view, nonsense. The issue turns to be exploring the dose-response function for a continuous exposure, and there is an inventory of methods to do so. Log-transformation does not help much, if at all.
ETA:
Much confusion exists about the normality assumption for multiple regression. Many people think that all the variables in a regression equation must be normally distributed. Nothing could be further from the truth. The only variable that is assumed to have a normal distribution is the disturbance term U, which is something we can't observe directly. The x variables can have any kind of distribution. Because y is a linear function of both the x's and U, there's no requirement that y be normally distributed either.
Another thing to keep in mind about the normality assumption is that it's probably the least important of the five assumptions....
Sometimes, however, log transformation of the DEPENDENT variable helps to satisfy another assumption of linear regression (homoscedasticity). Nonetheless, for reasons that have nothing to do with classical statistics or model assumptions, I actually argue that the dependent variables in linear regression should ALWAYS be log-transformed, followed by computation of a geometric mean ratio (rather than a mean difference.) I am talking about linear regression in the context of estimating an effect--not for purely predictive purpose. The explanation is too long and goes back to fundamental questions about measuring effects: should effects be measured as differences or as ratios, or may we simply toss a coin to decide?
If we talk about the independent variable (x), then log-transformation is, in my view, nonsense. The issue turns to be exploring the dose-response function for a continuous exposure, and there is an inventory of methods to do so. Log-transformation does not help much, if at all.
This post was edited on 2/7/14 at 3:53 pm
Posted on 2/7/14 at 3:59 pm to goldenbadger08
I had a Sheldon moment.
Posted on 2/7/14 at 4:07 pm to Festus
Very cool. Skillet chose his e-bff wisely
Posted on 2/7/14 at 4:29 pm to lsunurse
bologna sandwich posting from jail
Posted on 2/7/14 at 4:30 pm to Caplewood
Oh uh....someone called the cops on you?
I just finished up at the gym. Made sure to do some tricep exercises for Cades
I just finished up at the gym. Made sure to do some tricep exercises for Cades
Posted on 2/7/14 at 4:31 pm to lsunurse
Barely 100 posts in a lunch thread? What happened to the OT?
Posted on 2/7/14 at 4:32 pm to theunknownknight
The GMT thread ran until like 1 pm
Posted on 2/7/14 at 4:32 pm to theunknownknight
Thanks for implying my lunch thread is crappy though
Posted on 2/7/14 at 4:44 pm to LSUballs
quote:
Sounds terrible.
It was meh, but still better than tex-mex
Posted on 2/7/14 at 4:50 pm to The Sad Banana
quote:
Bistro Byronz in Baton Rouge.
Thanks AJF.
Posted on 2/7/14 at 5:50 pm to lsunurse
Nurse, you're cool and all, but I don't think you're as cool as Stephen Colbert fistbumping a bald eagle in a suit.
Popular
Back to top
Follow TigerDroppings for LSU Football News