Simple Histograms with R Software

Teaching - Curtis Kephart‎ > ‎Econometrics Notes & R Code (UCSC Econ113)‎ > ‎

Simple Histograms with R Software

Creating a Histogram with R Software
14:09 http://youtu.be/wGW9M93YswY
In this intro to R statistics video, we discuss the r script that makes histograms in R statistical software (R's hist function), creating a kernal density plot, and (briefly) comparing two kernal densities.

Getting Started, Loading Data

Load Sample Data: First, we need to load data, here's some data (it's going to automatically download a csv file),
Here are instructions to load data into R (YouTube).

I called my data data1

I might first be curious about basic descriptive & summary statistics about your data.

By typing str(data1), you can see that the R object "data1", has three variables; section, class & final. (This happens to be data of student section attendance, lecture attendance and final exam scores for a class at Michigan State University.)

Simple Histogram

Let's create a histogram for their final exam grades:

hist(data1$final)

This says, "draw a histogram by going into 'data1' and looking at the column 'final'". Note that you need the dollar-sign to link your R object 'data1' to the variable 'final'.

We get the following histogram:

Notice that there are only 9 bins to form the histogram above.

Since the maximum score was 166 points. let's set 166 bins so we have a vertical line for each possible exam score.

Adding More Bins (Adding more detail to a histogram)

hist(data1$final,166)

Well, it doesn't look great (I think my screen resolution was just really bad as I took the screen shot), but has a bit more information in it.

Adding Labels to a Histogram in R

Now, let's add some useful labels:

hist(data1$final,100, main="Final Exam Test Scores", xlab="Exam Scores", ylab="Frequency")

Comments