How do you suppose that least squares coefficient estimates, standard errors, t values, and R² would be affected by a doubling of the number of observations, with the new data exactly replicating the original data? Use the data in Exercise 8.18 test your theory.

Exercise 8.18

The effective delivery and care of newborn babies can be aided by accurate estimates of birth weight. A study [6] attempted to predict the birth weight of babies for 11 women with abnormal pregnancies by using echo-planar imaging (EPI) up to 1 week before delivery to estimate each baby’s fetal volume. Draw a scatter diagram and use least squares estimates of the regression model to see if there is a statistically significant relationship at the 1 percent level between the child’s estimated fetal volume X (decimeters cubed) and the birth weight Y (kilograms), both of which are in Table 8.4. Summarize your findings, and be sure to interpret the estimated slope of your fitted line.

Transcribed Image Text:

X 3.11 1.54 2.88 2.15 1.61 2.71 3.35 2.22 3.42 2.31 3.22 Y 3.30 1.72 3.29 2.30 1.62 3.00 3.54 2.64 3.52 2.40 3.40