Hello everyone, this is Trol Satigas. Objective of this video lecture
is to obtain scatterplot for a bivariate data in R. In R, I'm going to generate
some data set which simulates some test scores in order you and
me to get the same data set. From these random generators,
in other words random generators. I'm going to set.seed=2016. In that way, you and
I both would get the same, quote unquote, random data from these random generators. And I'm going to call Test_1_scores. And I will say rnorm, let's say I'm going to generate
some data from normal distribution. Let's say 50 data points with average of 78. And with the standard deviation being 10. And I am going to round them so
that I would get whole integers. And then I will go back and generate
some simulates and test scores for the second test for the same students. Again, I have 50 students let's say
this time the average was 70, right? So there was some decrease in the average. But the standard deviation,
let's say was 14 this time. Okay, for example,
if I just look at test 1 scores, let's say this is my test 1 score. Somebody got a 101. Let's say there was some extra
credit problem and he or she get at some point out of
some extra credit problem. And if I do test 2 scores, and
I would have this data set, all right. So I am assuming that this is paired data,
or bivariate data. In other words,
student 1 got 66 in test 1, but he or she got 72 in the second exam,
and so forth, right. So what I would like to do,
is basically obtain a scatter plot. How do I do it? I just do plot, and
I do my y axis, x axis. So if I plot now, I will get
a scatter plot like the following. So here you see, we have x label by
default is the name of the data set, the name of the data
set without any title. So this is very bad,
we would like to have some title, and we would like to have some nicer
some nice x label and y label. So now, to do that, I will go back and say that my title should be, let's say, my test scores for two exams. And I will just write 50
students in parentheses. And the x label, let's say I'm
going to write Test 1 scores. In the y label we'll write Test 2 scores. If I do that I will get my title here,
Test 2 scores, Test 1 scores, and
this is basically the scatter plot in R. We could play with the colors
of this point as well. For example,
if I just write color = blue here, I might get a scatter plot
with blue dot points on it. What have you learned in this lecture? You have learned how to
plot bivariate data. Which is called scatterplotting,
you learn how to add titles and labels and colors to that scatterplot.