Context: Taking time series levels and converting to 10 day changes in levels. Then doing a linear regression on the 10 day changes over a period of time eg 500 overlapping samples, where Y is the target and X is the explanatory variable(s).The result of the regression will be used to decompose the Y into fitted data and residue data for the in sample period.

Issue: Required to produce performance measurement of the quality of the fit using Adjusted R^2.

Question: Can the standard formula for adjusted R^2 be used or does there need to be an adjustment/allowance made for the fact that the data being used is overlapping.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.