Question

Suppose we have the following 25 residuals, 8, ?5, 7, 1, ?3, ?3, 3, ?5, 1, 9, 8, ?5, 7, 1, ?3, ?3, 3, ?5, 1, 9, 8, ?5, 7, 1, ?3 from the linear model: y = ?0 + ?1x1 + ?2x2 + .

(a) Please use Durbin-Watson statistic to test H0 : ? = 0 at 5% level of significance.

(b) Please use run test to examine if there are too many runs at 5% level of significance.

Answer 1

I am Using Excel for this question.

2.

To perform run test I am using SPSS

Steps

(i) Enter data as follows

(ii) Analyze-> Non-Parameteric-> Runs-> put 'Residuals' in test variable list-> cut point(median) -> continue.

The output is as follows

Since, p-value is greater than 0.05 hence we do not reject H0 and conclude that data is random and there are too many runs.