I've been searching online for free data sets with which I would be able to apply cross validation techniques. Preferably, I'd like to find data with ≈30 (or more) observations that has significant curvature so that I can demonstrate how one can use cross-validation to perform model selection.

I'd also like to demonstrate the use of a gradient estimation algorithm to estimate the polynomial parameters.

I would use the dataset to perform my final course project. I'd like to demonstrate that I have a good handle on the topics I mentioned above- so I am working backwards and trying to fit the data to the technique. I haven't had much luck searching online- most of the data sets I've found are either practice applications for linear regression or include many variables- which I'd like to avoid if possible.

Does anyone have any suggestions? I'd greatly appreciate it!

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.