Reduce the size of the sunspots data set by taking only the first m observations as was done in Problem 3. At what value of m do the cross-validation methods begin to provide reasonable estimates? Why is this occurring?

Problem 3

Reduce the size of the sunspots data from Problem 2 by taking only the first m observations:

Problem 2

Consider the data set sunspots from Andrews and Herzberg (1985) as a response variable. For the predictor data x, use

Apply Friedman's smoother using trial and error to find a span that seems to work well with the data. Then find an estimate using the span determined by cross-validation. Describe the results (taking into account Comment 5).