The Child Health and Development Studies investigate a range of topics. One study, in particular, considered all pregnancies between 1960 and 1967 among women in the Kaiser Foundation Health Plan in the San Francisco East Bay area. The goal is to model the weight of the infants (bwt, in ounces) using variables including length of pregnancy in days (gestation), mother’s age in years (age), mother’s height in inches (height), whether the child was the first born (parity), mother’s pregnancy weight in pounds (weight), and whether the mother was a smoker (smoke).
9.3
Multiple Linear Regression
Predicted Average Birth Weight = -80.41 + 0.44(gestation) -3.33 (parity) -0.01 (age) + 1.15(height) + 0.05(weight) -8.40 (smoke)
The average predicted birth rate for a baby increases by 0.44% the longer the gestation period and decreases by 0.01% the older the mother is.
Actual <- 120
Predicted <- -80.41 +0.44*284-3.33*0-0.01*27+1.15*62+0.05*100-8.40*0
Residual <- Actual-Predicted
Predicted
## [1] 120.58
Residual
## [1] -0.58
The actual weight for baby 1 is 120 ounces and the predicted birth weight is 120.58. Our residual is -0.58.
R2
Var1<-249.28
Var2 <- 332.57
n<-1236
k <- 6
R2 <- 1-(Var1/Var2)
R2
## [1] 0.2504435
Adjusted R2
x<- (n-k-1)
y<- (n-1)
Adj <- 1-((Var1/Var2)*(y/x))
Adj
## [1] 0.2467842