0

How do I report the $R^2$ that takes the number of covariates in the model into account?

Richard Hardy
  • 54,375
  • 10
  • 95
  • 219
Linh
  • 1
  • 1
    it's called adjusted $R^2$. it's calculation for the case of $p$ covariates + an intercept is $R_{adj}^2= R^2-(1-R^2)\frac{p}{n-p-1}$. – chRrr Sep 11 '17 at 10:35
  • Search this site for "adjusted R-squared", might be a duplicate. See https://stats.stackexchange.com/questions/52517/why-is-adjusted-r-squared-less-than-r-squared-if-adjusted-r-squared-predicts-the https://stats.stackexchange.com/questions/92081/what-happens-to-adjusted-r-squared-as-sample-size-increases https://stats.stackexchange.com/questions/12900/when-is-r-squared-negative – kjetil b halvorsen Sep 11 '17 at 10:36
  • 1
    It doesn't look like a duplicate to me, but I'm not sure it's a good question. – Peter Flom Sep 11 '17 at 10:40
  • 1
    When you say "how do you report" can you clarify exactly what you mean? – mdewey Sep 11 '17 at 10:42

0 Answers0