A company fits a regression to predict monthly Orders over a period of 50 months

Question

A company fits a regression to predict monthly Orders over a period of 50 months. The only predictor is time (in months). The Durbin-Watson statistic on the residuals is 1.075. a) At alpha = 0.01, what are the values of d_L and d_U? b) Please use an appropriate test for any evidence of positive autocorrelation? Explain. c) Please use an appropriate test to check if there is any evidence of negative autocorrelation? Suppose that the Durbin Watson test is applied to a regression containing two explanatory variables plus a constant (e.g. equation 2 above) with 50 data points. The objective is to test for with any kind of autocorrelation. The D-W test statistic takes a value of 1.63. What is the appropriate conclusion, at alpha = 0.05?

Explanation / Answer

2.

a) dL = 1.32441

dU = 1.40313

b)

Here d value < dL , we reject H0 : 0 (and so accept H1 : > 0)

c) we conclude that conclude that there is a significant positive autocorrelation.

3.

dL = 1.46246 dU = 1.6283

d-value = 1.63

Here d value >  dU = 1.6283 so we do not reject H0 : 0

Thus we conclude that there exist no auto correlation between them

Related Questions

Navigate

• Browse (All)
• Browse A
• Subjects

---

---

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.