Training error versus fresh-noise error
You fit an OLS regression with observations. The design matrix is held fixed and has an intercept column plus regressors (full column rank); the errors are i.i.d. with mean and variance .
After fitting, you draw a fresh response vector at the same design points, with new noise independent of the old and of the same law. By how much does the expected error on the fresh responses exceed the expected training error? That is, compute
Show hints (3)+
- Write with the hat matrix .
- For white noise, , and is the number of columns of - intercept included.
- The fresh error is , two independent pieces.
Answer
Reveal answer →Final answer
20
Create a free account to see the full worked solution and track your progress.
Interview format: Hedge Fund Quant, Systematic & Data-Driven Trading