Q$11($Multiple graphs$)$: The function ggarrange in the package ggpubr can be used to organize multiple

graphs in a single plot. For example,

library$($ggpubr$)$ # install this first

library $($MASS$)$

library $($tidyverse$)$

plot$\_$no$\_$smoke birthwt $\%\%$

filter $($smoke $==0)\%>\%$

aes $(x=bwt)$

geom$\_$histogram$()$

plot$\_$smoke birthwt $\%>\%$

filter$($smoke $==1)\%>\%$

ggplot$(aes(x=bwt))+$

geom$\_$histogram$()$

ggarrange$($plot$\_$no$\_$smoke, plot$\_$smoke$)$

Recall that

the boxcar kernel: $,K(x)=\frac{1}{2}I(|x|1)$

the Gaussian kernel: $,K(x)=\frac{1}{\sqrt[\phantom{2}]{2}}{e}^{-\frac{x^2}{2}}$

the Epanechnikov kernel: $,K(x)=\frac{3}{4}(1-x^2)I(|x|1)$

the tricube kernel: $,K(x)=\frac{70}{81}(1-|x{|}^3{)}^{3}I(|x|1),$

where $I(|x|1)=1$ if $|x|1$ and equals $0$ otherwise.

Use ggarrnage to create the following plot.