The Durbin-Watson statistic is designed to detect autocorrelation and is defined by [D W=frac{sum_{t=2}^{T}left(y_{t}-y_{t-1} ight)^{2}}{sum_{t=1}^{T}left(y_{t}-bar{y} ight)^{2}} .]

Question:

The Durbin-Watson statistic is designed to detect autocorrelation and is defined by

\[D W=\frac{\sum_{t=2}^{T}\left(y_{t}-y_{t-1}\right)^{2}}{\sum_{t=1}^{T}\left(y_{t}-\bar{y}\right)^{2}} .\]

a. Derive the approximate relationship between \(D W\) and the lag 1 autocorrelation coefficient \(r_{1}\).

b. Suppose that \(r_{1}=0.4\). What is the approximate value of \(D W\) ?

Fantastic news! We've Found the answer you've been seeking!

Step by Step Answer:

Question Posted: