The Durbin-Watson statistic, d, is defined as $d = \sum _ { i = 2 } ^ { n } \left( e _ { i } - e _ { i - 1 } \right) ^ { 2 } / \sum _ { i = 1 } ^ { n } e _ { i }$ , where e_i is the residual at time period i.

Question

Quizplus · Accepted Answer

The Durbin-Watson statistic is defined as $d = \sum _ { i = 2 } ^ { n } \left( e _ { i } - e _ { i - 1 } \right) ^ { 2 } / \sum _ { i = 1 } ^ { n } e _ { i }^2$, where $e_i$ is the residual at time period i. The denominator should be the sum of squared residuals, not just the sum of residuals.

The Durbin-Watson Statistic, D, Is Defined As d=∑i=2n(ei−ei−1)2/∑i=1neid = \sum _ { i = 2 } ^ { n } \left( e _ { i } - e _ { i - 1 } \right) ^ { 2 } / \sum _ { i = 1 } ^ { n } e _ { i }d=∑i=2n​(ei​−ei−1​)2/∑i=1n​ei​

The Durbin-Watson Statistic, D, Is Defined As $d = \sum _ { i = 2 } ^ { n } \left( e _ { i } - e _ { i - 1 } \right) ^ { 2 } / \sum _ { i = 1 } ^ { n } e _ { i }$