Timeline for How to find how independent variables affect dependent variables
Current License: CC BY-SA 3.0
9 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jun 7, 2013 at 8:45 | comment | added | IMA | I will write a few words about the potential problems you will face generally in a moment, gonna take a couple of minutes. | |
| Mar 10, 2013 at 17:22 | comment | added | gung - Reinstate Monica | @DuaneAllman, my position is No. You should read the post that I linked to. | |
| Mar 9, 2013 at 1:17 | comment | added | Duane Allman | Hmm, ok. I've just run a new program which goes through every subset and prints the "best" subset for (1-length, 2-length, 3-length...20-length) etc subsets. I'll treat the results with some scepticism, but it should give me some sort of idea of the variables to use, no? | |
| Mar 9, 2013 at 0:45 | comment | added | gung - Reinstate Monica | @DuaneAllman, unfortunately no. What you have suggested is a simplified for of model building akin to "best subsets regression". If these comments don't make much sense / you want to understand why, it may help to read my answer here: algorithms-for-automatic-model-selection. | |
| Mar 8, 2013 at 22:42 | comment | added | Duane Allman | Ok, I imagine the problems backward stepwise has is that you could easily remove a criteria which looks bad, but is actually good when correlating with something else (or however you say it)? If I did an exhaustive search of all combinations of independent variables (up to order 3), and pick the combination which gave me smallest "fisher f" value, would that be a decent result? | |
| Mar 8, 2013 at 22:20 | comment | added | whuber♦ | Duane, although there's a kernel of good advice in this reply, I suggest you not follow it. The first part advocates a simplified form of model building akin to "backward stepwise regression." This is known to have problems. The second part--"playing"--does not seem to provide any actionable advice at all. | |
| Mar 8, 2013 at 22:00 | comment | added | Duane Allman | Ah, now what are the p-values, are they to do with partial residual plots? and what makes them significant or not? | |
| Mar 8, 2013 at 21:42 | review | First posts | |||
| Mar 9, 2013 at 0:45 | |||||
| Mar 8, 2013 at 21:25 | history | answered | wlq | CC BY-SA 3.0 |