Answer-
D. No, the points are in a curved pattern.
Solution-
The difference between the observed or given value of the dependent variable and the predicted value is called the residual. Each data point has one residual.
[tex]Residual\ value= Given\ value - Predicted\ value[/tex]
If the points in a residual plot are randomly dispersed around the horizontal or x-axis, a linear regression model is appropriate for the data. Otherwise, a non-linear model is more appropriate.
Plotting a graph, by taking the residual values on ordinate and values of given x on abscissa, a non-random U pattern is obtained.
So a non-linear model will be a better fit for this data set.