• ... Durbin-Watson statistic because this model uses a lag of Yt. We use a scatterplot instead. The plot of et on et − 1 does not indicate outliers and shows very little autocorrelation. Fits with more lagged variables did not improve the model.

A scatterplot shows residual percentage change and lag residuals. The graph shows a negative direction with wide distribution around the fitted line.

In addition, the timeplot of the residuals shows no patterns but highlights positive outliers from the holiday seasons of 2001 and 2008. The plot of the residuals on the fitted values does not indicate major problems.

A residual plot shows sharp rises and falls. A scatterplot shows wide distribution around zero.

  • ✓ Similar variances. The plot of residuals on fitted values has no tendency for changing the ...

Get Statistics for Business: Decision Making and Analysis, 3rd Edition now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial