Decathlon

This exercise examines the relationships among the performances in the decathlon for the best decathlon athletes in the world. Click on Data under Chapter 1 in the left panel and then select Open remote ... under the File menu in the right panel. Select decathlon.xml from the Open File Dialog and click OK. Note that Athletes is assigned the Label role.

The decathlon is a 10-event athletic contest consisting of the 100-meter, 400-meter, and 1500-meter runs, the 110-meter high hurdles, the javelin and discus throws, the shot put, the pole vault, the high jump, and the broad jump. For the three runs (100, 400, and 1500 meter) and the hurdles, the scores are times, so it is better to have a small number (a faster time). In the other events, it is better to have a large time.

1. For each of the following pairs of variables, guess whether their correlation is positive or negative: 100-meter and the 400-meter run; 100-meter and the 1500-meter run; 100-meter run and the high jump; 100-meter run and the discus throw; discus throw and the javelin; long (or broad) jump and the high jump; high jump and the pole vault.
2. For each of the above pairs, successsively choose the X role for the first variable and the Y role for the second and then select xy|z from the Graph menu. Once the plot appears, select Correlation from the Analyze menu to display the correlation in the lower panel. What are the correlations for the variable pairs in Question 1? How good were your guesses?
3. Can you explain why the correlation between the 100-meter and the 1500-meter run in the data set is what it is? Who had the fastest 100-meter run? What was his time? What was his time for the 1500-meter run?
4. Why is the correlation between the long jump and the high jump what it is? Who had the longest long jump? What was his distance?
5. Who had the most points for the decathlon?