Question

CHAPTER 2 The Simple Regression Model 59 (iii) (iv) To predict a birth weight of 125 ounces, what would cigs have to be? Comment. The proportion of women in the sample who do not smoke while pregnant is about 85. Does this help reconcile your finding from part (iii)?

Answer 1

(iii) By solving 125 = 119.77 - 0.514 *cigs, we see that the number of cigarettes per week must be-10.18 cigarettes, which is not a sensible prediction.

(iv)
This fact suggests that the average number of cigarettes smoked per week is likely near 0. Hence, the estimate of the intercept is roughly the average birth weight in the sample (recall that ˆ β 0 = ¯ y - ˆ β 1 ¯ x ). As a result, we might expect to underestimate birth weights for children whose mothers did not smoke. Also, because our sample has few smokers, we might not observe many combinations of high birthweight/smoking mom outcomes - thus, the estimate of ˆ β 1 may not be well suited to estimate birth weights in this upper range.