- The use of R2, the coefficient of determination, also called the multiple correlation coefficient, is well established in classical regression analysis (Rao,1973)
- R2 is the square of the Pearson correlation between x and the coefficient score of the model p(), that is the derivative with respect to Beta of log{p(y¦Beta.x+lambda)} at Beta=0
- For discrete models does not go all the way to 1.
- Max(R2)=1-exp{2n-1l(0)}=1-L(0)2/n
- Nagelkerke rescales R2 so that it’s maximum is 1 such that R2 = R2 /max(R2)
- Just cosmetics.
A note on a General Definition of the Coefficient of Determination
Original by N.J.D Nagelkerke, Biometrika,, 1991, 2 pages
This summary note was posted on 20 February 2016, by Reinie
in Credit risk Finance
Latest Hamster Notes
- Myers Briggs Type Indicator posted in Personal Development
- Positive Influence posted in Management
- Start with Why posted in Management
- 4 steps to optimise product value posted in Agile Management
- 5 paradoxes of digital business leadership posted in Agile
- Product Vision, 10 tips posted in Agile
- Progress in adopting the Principles for effective risk data aggregation and risk reporting 2023 posted in Credit risk Finance
- Leadership styles by ChatGPT posted in Management
- Gen AI round table posted in Machine Learning
- Leadership in fully remote teams posted in Management