1

Whiles reading An Introduction To Statistical Learning under linear regression (Chapter 3), I found:

$$E(Y - \hat{Y})^2 = |f(X) - \hat{f}(X)|^2 + Var(ε)$$

where $E(Y - \hat{Y})^2$ represents the average, or expected value of the squared difference between the predicted and actual value of $Y$, and $Var(ε)$ represents the variance associated with the error term $ε$.

What does $Var(ε)$ mean? Can we just write $ε$ rather than $Var(ε)$?

Karolis Koncevičius
  • 4,282
  • 7
  • 30
  • 47
EA Lehn
  • 199
  • 8
  • can you share the author and the page? and edition if applicable. – gunes Feb 16 '19 at 18:49
  • @Gunes see https://stats.stackexchange.com/search?q=An+Introduction+To+Statistical+Learning. – whuber Feb 16 '19 at 20:03
  • Now I found it, thanks. It's in Page 19, not in Chapter 3. I was interested in finding some evidence about $X$ being fixed; and it is there. However, it appears the question is duplicate. – gunes Feb 16 '19 at 20:11

0 Answers0