Timeline for MAPE vs R-squared in regression models
Current License: CC BY-SA 3.0
10 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jun 5, 2018 at 23:22 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| May 3, 2018 at 6:45 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Feb 8, 2018 at 8:40 | history | edited | Stephan Kolassa | CC BY-SA 3.0 |
edited title; edited tags
|
| Feb 8, 2018 at 8:39 | answer | added | Stephan Kolassa | timeline score: 7 | |
| Feb 8, 2018 at 6:59 | comment | added | Stephan Kolassa | Very much related: What are the shortcomings of the Mean Absolute Percentage Error (MAPE)? | |
| Feb 8, 2018 at 6:44 | comment | added | Alexis | Yes. For example, $R^{2}$ is, for a model with a single predictor, bounded by 0 and 1. Adjusted-$R^{2}$, which is a quantity one gets with more than one predictor variable breaks some of the interpretability of $R^{2}$. However, there are other measures, such as generalized $R^{2}$, which provides much of the interpretability, even for multiple predictors, and even for things like binomial-outcome link regressions (which don't have residuals in the same way as OLS regression). | |
| Feb 8, 2018 at 5:54 | comment | added | PagMax | @Alexis yes I have. I did not see any comparison with R^2 and more interested in comparing these two metrics. Does R^2 overcome any of the disadvantages which MAPE has? | |
| Feb 8, 2018 at 5:41 | comment | added | Alexis | Have your read the Wikipedia article on MAPE's list of disadvantages with the metric? | |
| Feb 8, 2018 at 5:21 | review | First posts | |||
| Feb 8, 2018 at 5:22 | |||||
| Feb 8, 2018 at 5:20 | history | asked | PagMax | CC BY-SA 3.0 |