Timeline for How to interpret whether centering improves linear regression model or not?
Current License: CC BY-SA 3.0
11 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Sep 8, 2016 at 17:00 | comment | added | Matt L. | this might be of interest to you Similar Question I Answered with Visualizations | |
| Sep 8, 2016 at 16:28 | answer | added | mdewey | timeline score: 3 | |
| Sep 8, 2016 at 15:16 | history | edited | mavavilj | CC BY-SA 3.0 |
added 7 characters in body
|
| Sep 8, 2016 at 15:12 | comment | added | mavavilj | @mdewey Oh you mean mean()? | |
| Sep 8, 2016 at 15:11 | comment | added | mdewey | There is nothing wrong with either model but using mean is not giving you what you hoped for. | |
| Sep 8, 2016 at 15:10 | comment | added | mavavilj | @mdewey I also read that not having value 0 is not a problem since centering just changes the model so that instead of (Intercept) being the predicted value for an observation with predictor == 0, it's giving the predicted value for an observation with predictor == mean(predictor). | |
| Sep 8, 2016 at 15:07 | comment | added | mavavilj | @mdewey So centering in this case just "breaks" the model since the dichotomic predictor is meaningful as it was using values 0 and 1? | |
| Sep 8, 2016 at 15:06 | comment | added | mdewey | The intercept is the predicted value for an observation with predictor = 0 but you do not have any such so you will not be able to use mean in any simple way to check the value. | |
| Sep 8, 2016 at 14:59 | comment | added | mavavilj | @mdewey Now the values are -0.7857143 for 0 and 0.2142857 for 1. You can interpret the mean that was subtracted from those. | |
| Sep 8, 2016 at 14:56 | comment | added | mdewey | When you say you centered your predictor given that it is zero or one what values were you left with? | |
| Sep 8, 2016 at 14:52 | history | asked | mavavilj | CC BY-SA 3.0 |