There must be a lot of ways to handle this problem.
But, it would be easier to split
wdiff first.
We can split
wdiff by using the similar way in
"A little more on subsetting" part:
subset(wdiff,cdc$gender=="m")
subset(wdiff,cdc$gender=="f")Name these two separated data as like "mwdiff" and "fwdiff".
Then, use
summary function separately to obtain descriptive statistics.
Also,
boxplot(mwdiff,fwdiff) will give you the side-by-side boxplots.
While you are making the boxplot, take a look at this
POST to deal with the outliers issue.
Hope this was a bit helpful!
Locked
