Chapter 9, Problem 29E

(a)

To determine

To explain how could you use the data graphed in exercise one to get a good prediction.

Explanation of Solution

It is supposed that we wanted to predict the trend in marriage age for American women into the early part of this century. Now, we can use the data graphed in exercise one to get a good prediction by many ways. So, using the data for $1955-2000$ results in a scatterplot that is relatively linear with some curvature. The residual plot shows a definite trend indicating that the data are not linear. If we used the regression line for $2010$ the predicted age is $26.07$ years.

(b)

To determine

To explain how much faith do you place in this prediction.

Explanation of Solution

It is supposed that we wanted to predict the trend in marriage age for American women into the early part of this century. Now, we do not have much faith in this prediction since the data are not truly linear and $2010$ is $10$ years from the last data point. Therefore, extrapolating is very risky due to this we can trust the prediction.

(c)

To determine

To explain do your model would produce an accurate prediction about your grandchildren, say, $50$ years from now.

Answer to Problem 29E

No, it would not produce accurate prediction.

Explanation of Solution

It is supposed that we wanted to predict the trend in marriage age for American women into the early part of this century. Now, our model would not produce an accurate prediction about your grandchildren, say, $50$ years from now because that extrapolation of more than $50$ yearswould be absurd. And there is no reason to believe the trend from $1955-2000$ will continue same as in the future. Thus, it will not be appropriate to use the same trend.