Height Weight In-Class Demo

Import the height and weight dataset. We will do this through a couple of different ways:

1. The command

height_weight_2 <- read.csv('Height_weight_male_female.csv', header = TRUE)

2. Alternatively, you can have R studio figure out this command for you with the “import dataset” button

Next, lets start by looking at our dataset:

View(Height_weight_2)

Notice there is nothing being assigned here, just running a command b/c we are not saving anything to a variable name.

What kind of variables? Can use the summary in R to quickly find out a lot of information abotu the data.

summary(Height_weight_2)

Lets start by just making a scatterplot of height and width:

plot(Height_weight_2$Height_in, Height_weight_2$Weight_lbs)

We can use the help function to find out things about the graph. For example, how to add labels:

plot(Height_weight_2$Height_in, Height_weight_2$Weight_lbs, xlab = 'Height (inches)', ylab = 'Weight (lbs)')

What if we want to color our graph by our sex? Below the code does that and the second line adds a legend to the code, which is not necessary but helpful.

plot(Height_weight_2$Height_in, Height_weight_2$Weight_lbs, xlab = 'Height (inches)', ylab = 'Weight (lbs)', col = Height_weight_2$sex)
legend('bottomright', legend =levels(Height_weight_2$sex), col = 1:3, cex = 0.8, pch = 1)

Now lets make a histogram of the heights:

hist(Height_weight_2$Height_in)

What if we want to change the bin sizes? We can tell R how many bins we want with “breaks” and I also like to include the xlim argument to make a nicer x-axis that goes from 65-90. We can also make the axes prettier like we did before.

hist(Height_weight_2$Height_in, breaks = 10, xlim = range(65,90), xlab = "Height (inches)", )

What abotu a box plot?

boxplot(Height_weight_2$Height_in)

It could be interesting to seperate the data into two box plots by sex. Lets see how we can do that. Here the “~” tells R how to seperate the data.

boxplot(Height_weight_2$Height_in~Height_weight_2$sex)

Could we use this same notation for the summary data to find the different means? TO do this with use “tapply” function which uses the notation: tapply(value, factor, function) In this case our value is the height (call that variable), factor is sex, and the function is mean. Could do the same this with median, mode, summary etc.

tapply(Height_weight_2$Height_in, Height_weight_2$sex, mean)