library(Stat2Data)
library(dplyr)
library(ggplot2)
data(Kids198)
ggplot(Kids198, aes(x = Age, y = Height,
color = factor(Sex), shape = factor(Sex))) +
geom_point() +
labs(
title = "Age vs. Height for Children",
x = "Age (months)",
y = "Height (inches)",
color = "Sex (0 = boy, 1 = girl)",
shape = "Sex (0 = boy, 1 = girl)"
)
model1 <- lm(Height ~ Age, data = Kids198)
summary(model1)
##
## Call:
## lm(formula = Height ~ Age, data = Kids198)
##
## Residuals:
## Min 1Q Median 3Q Max
## -10.434 -2.181 0.073 2.247 9.380
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 37.077279 1.145824 32.36 <2e-16 ***
## Age 0.149109 0.007076 21.07 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 3.357 on 196 degrees of freedom
## Multiple R-squared: 0.6938, Adjusted R-squared: 0.6922
## F-statistic: 444 on 1 and 196 DF, p-value: < 2.2e-16
Question 1: What are R-squared and the residual standard error? How do boys and girls compare in the scatterplot: does one group sit higher, is one group’s pattern steeper, or both?
R-squared = 0.6938
Residual Standard Error = 3.357 on 196 degrees of freedom
In the beginning, both boys and girls sit relatively in the same spot, but at around the 183 month mark (roughly 15 years old) boys peak.
Kids198 <- mutate(Kids198, FemaleIND = ifelse(Sex == 1, 1, 0))
Kids198 %>%
select(Age, Height, Sex, FemaleIND) %>%
head()
## Age Height Sex FemaleIND
## 1 210 67.8 0 0
## 2 144 63.0 1 1
## 3 119 50.1 0 0
## 4 130 55.7 1 1
## 5 157 63.2 0 0
## 6 102 48.8 0 0
model2 <- lm(Height ~ Age + FemaleIND, data = Kids198)
coef(model2)
## (Intercept) Age FemaleIND
## 38.7275347 0.1466626 -2.4514034
ggplot(Kids198, aes(x = Age, y = Height,
color = factor(Sex), shape = factor(Sex))) +
geom_point() +
geom_abline(intercept = 32.728, slope = 0.147, color = "#F8766D") +
geom_abline(intercept = 30.277, slope = 0.147, color = "#00BFC4") +
labs(
title = "Age vs. Height, with an Indicator for Girls",
x = "Age (months)",
y = "Height (inches)",
color = "Sex (0 = boy, 1 = girl)",
shape = "Sex (0 = boy, 1 = girl)"
)
Question 2: What are the three coefficients, and what is each group’s equation? Interpret the FemaleIND coefficient and the Age coefficient in context. Predict the height of a boy and a girl who are each 180 months old. How does the difference between your predictions compare to the FemaleIND coefficient?
Boys Intercept: 32.728 Girls Intercept: 30.277 Age/Slope: 0.147 FemaleIND: -2.451
For every additional year of age (age + 1), while only considering individuals of the same gender, we would expect the height to increase by 0.147 inches
My predictions were not far off.
Kids198 <- mutate(Kids198, FemaleINT = FemaleIND * Age)
model3 <- lm(Height ~ Age + FemaleIND + FemaleINT, data = Kids198)
coef(model3)
## (Intercept) Age FemaleIND FemaleINT
## 32.96091632 0.18254275 7.72784644 -0.06413432
ggplot(Kids198, aes(x = Age, y = Height,
color = factor(Sex), shape = factor(Sex))) +
geom_point() +
geom_abline(intercept = 32.961, slope = 0.183, color = "#F8766D") +
geom_abline(intercept = 40.691, slope = 0.120, color = "#00BFC4") +
labs(
title = "Age vs. Height, with an Interaction",
x = "Age (months)",
y = "Height (inches)",
color = "Sex (0 = boy, 1 = girl)",
shape = "Sex (0 = boy, 1 = girl)"
)
Question 3: What are the four coefficients, and what is each group’s equation? Do the two lines cross within the data? If so, at about what age, and what does that mean for boys and girls?
BInt: 32.961 Age/Slope: 0.183 FemaleIND: 7.730 FemaleINT: -0.064 GInt: 40.691 GSlope: 0.120
The lines do cross at roughly around 10 years old. This means that both girls and boys were about the same height at that age.
summary(model2)
##
## Call:
## lm(formula = Height ~ Age + FemaleIND, data = Kids198)
##
## Residuals:
## Min 1Q Median 3Q Max
## -9.1019 -1.9756 -0.0169 2.0227 8.1599
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 38.727535 1.110526 34.873 < 2e-16 ***
## Age 0.146663 0.006617 22.164 < 2e-16 ***
## FemaleIND -2.451403 0.446458 -5.491 1.24e-07 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 3.133 on 195 degrees of freedom
## Multiple R-squared: 0.7348, Adjusted R-squared: 0.7321
## F-statistic: 270.1 on 2 and 195 DF, p-value: < 2.2e-16
summary(model3)
##
## Call:
## lm(formula = Height ~ Age + FemaleIND + FemaleINT, data = Kids198)
##
## Residuals:
## Min 1Q Median 3Q Max
## -7.3834 -2.0663 0.0506 1.7862 8.4161
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 32.960916 1.537781 21.434 < 2e-16 ***
## Age 0.182543 0.009383 19.454 < 2e-16 ***
## FemaleIND 7.727846 2.034957 3.798 0.000195 ***
## FemaleINT -0.064134 0.012545 -5.112 7.6e-07 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 2.948 on 194 degrees of freedom
## Multiple R-squared: 0.7663, Adjusted R-squared: 0.7626
## F-statistic: 212 on 3 and 194 DF, p-value: < 2.2e-16
Question 4: What are R-squared and the residual standard error for each model? Did adding the indicator help? Did adding the interaction help? Which of the three models would you use, and why? Then answer our question: do boys and girls grow taller at the same rate?
R squared(Model 12): 0.735
R squared(Model 13): 0.766
Boys and girls do grow at around the same rate in early childhood, but as they get older, boys grow at a faster rate.