Econ 427, Spring 2010

Problem Set 1 -- Due Thursday, January 28, 2010

Ch 1. Problems and Complements:

2. Parts (a) and (b) (p. 9)

Ch 2. Problems and Complements:

7. (p. 31) Note: you will need the data from the Diebold data sets. See the Supplements page for the link. Depending on where you install the Diebold files, it should have a path like ...\Data Sets\fcst4-02\PC2_7_xyz.dat.

9. (p. 31)

Ch 4. Problems and Complements:

6. (p. 69) Note: you will need the data from the Diebold data sets. See the Supplements page for the link. Depending on where you install the Diebold files, it should have a path like ...\Data Sets\fcst4-04\PC4_06_EXCHRATE.DAT.

Additional Problem:

In the first week of class, we looked at several measures of the goodness of forecast fit.

(a) Using the data below, calculate "mean absolute percent error" (MAPE) and "root mean squared percent error" (RMSPE) for both forecast series. (See textbook, page. 261-262.) Which model is better according to each measure? Why?

(b) Why might these percent error measures be more useful than mean absolute error or mean squared error?

Note: you can do this problem by hand with a calcuator, but it will probably be easier if you download the Excel forecast accuracy worksheet file that I used in class (see Supplements web page) and modify it for this problem.