WEBVTT

00:00:00.000 --> 00:00:16.560 align:middle line:90%


00:00:16.560 --> 00:00:17.060 align:middle line:90%
Hello.

00:00:17.060 --> 00:00:18.800 align:middle line:84%
Welcome to a brief
tutorial on how

00:00:18.800 --> 00:00:22.100 align:middle line:84%
to calculate a correlation
using R Commander.

00:00:22.100 --> 00:00:23.600 align:middle line:84%
First thing we want
to do is we want

00:00:23.600 --> 00:00:25.520 align:middle line:84%
to go ahead and type
in that library.

00:00:25.520 --> 00:00:27.050 align:middle line:90%
Whoops.

00:00:27.050 --> 00:00:28.700 align:middle line:90%
R Commander.

00:00:28.700 --> 00:00:32.405 align:middle line:84%
Make sure you capitalize that
R or it's not going to run.

00:00:32.405 --> 00:00:33.560 align:middle line:90%
As it is case sensitive.

00:00:33.560 --> 00:00:37.160 align:middle line:84%
Then we're going to come to
data, import data from SPSS

00:00:37.160 --> 00:00:38.060 align:middle line:90%
file.

00:00:38.060 --> 00:00:41.050 align:middle line:84%
What we want to do is find
the one that says correlation.

00:00:41.050 --> 00:00:42.340 align:middle line:90%
So then we can click OK.

00:00:42.340 --> 00:00:44.730 align:middle line:84%
And it's going to
import that data.

00:00:44.730 --> 00:00:46.136 align:middle line:90%
So let's look at that data set.

00:00:46.136 --> 00:00:47.510 align:middle line:84%
It's going to come
way over here.

00:00:47.510 --> 00:00:50.480 align:middle line:84%
If I maximize it it'll send it
up here to the upper left hand

00:00:50.480 --> 00:00:52.210 align:middle line:90%
corner for us to look at.

00:00:52.210 --> 00:00:54.430 align:middle line:84%
You'll notice that it--
again, the goal of this

00:00:54.430 --> 00:00:57.560 align:middle line:84%
is to correlate communication
apprehension with heart rate

00:00:57.560 --> 00:00:58.370 align:middle line:90%
change.

00:00:58.370 --> 00:01:00.110 align:middle line:84%
So we wanted to find
out whether or not

00:01:00.110 --> 00:01:02.630 align:middle line:84%
an individual's level of
communication apprehension

00:01:02.630 --> 00:01:05.090 align:middle line:84%
correlated with their
heart rate change

00:01:05.090 --> 00:01:09.140 align:middle line:84%
when they were asked to
give a public speech, which

00:01:09.140 --> 00:01:11.460 align:middle line:84%
is one of those things that
you would think make sense.

00:01:11.460 --> 00:01:13.210 align:middle line:84%
But let's go ahead and
actually test this.

00:01:13.210 --> 00:01:15.020 align:middle line:84%
So to actually run
a correlation you're

00:01:15.020 --> 00:01:18.150 align:middle line:84%
going to come up here to
Statistics, Summaries,

00:01:18.150 --> 00:01:19.555 align:middle line:90%
Correlation Matrix.

00:01:19.555 --> 00:01:22.010 align:middle line:84%
So that's the first step
that we're going to do.

00:01:22.010 --> 00:01:23.330 align:middle line:90%
So we're going to come up here.

00:01:23.330 --> 00:01:25.540 align:middle line:84%
We're going to click on
the variables that we want.

00:01:25.540 --> 00:01:26.956 align:middle line:84%
Now notice if I
just click on them

00:01:26.956 --> 00:01:28.340 align:middle line:90%
it's not going to pick two.

00:01:28.340 --> 00:01:30.750 align:middle line:84%
You need to click,
shift, and then hold

00:01:30.750 --> 00:01:32.850 align:middle line:90%
so that we actually give them.

00:01:32.850 --> 00:01:35.570 align:middle line:84%
And so this is going to give
us our basic Pearson product

00:01:35.570 --> 00:01:38.184 align:middle line:84%
moment correlation,
which is what we want.

00:01:38.184 --> 00:01:39.600 align:middle line:84%
And there you're
going to have it.

00:01:39.600 --> 00:01:42.990 align:middle line:84%
So we have CA with
heart rate change,

00:01:42.990 --> 00:01:44.240 align:middle line:90%
and CA with heart rate change.

00:01:44.240 --> 00:01:46.415 align:middle line:90%
So let's look at this real fast.

00:01:46.415 --> 00:01:49.040 align:middle line:84%
One of the things I want you to
notice is that in a correlation

00:01:49.040 --> 00:01:53.540 align:middle line:84%
matrix you're always going to
have this diagonal line of 1's.

00:01:53.540 --> 00:01:56.480 align:middle line:84%
That is we would call
a perfect correlation.

00:01:56.480 --> 00:01:58.880 align:middle line:84%
So in this case, it's
an individual's level

00:01:58.880 --> 00:02:02.450 align:middle line:84%
of CA being correlated with
that individual's level of Ca.

00:02:02.450 --> 00:02:04.350 align:middle line:84%
It's going to be the
exact same number.

00:02:04.350 --> 00:02:06.650 align:middle line:84%
Hence why you end up
with this diagonal

00:02:06.650 --> 00:02:08.390 align:middle line:90%
of perfect correlations.

00:02:08.390 --> 00:02:11.300 align:middle line:84%
Like the second one, here is an
individual's heart rate change

00:02:11.300 --> 00:02:14.210 align:middle line:84%
being correlated with that
individual's heart rate change.

00:02:14.210 --> 00:02:16.760 align:middle line:84%
For our purposes, we want
to look at the one that's

00:02:16.760 --> 00:02:19.020 align:middle line:90%
not in that diagonal line.

00:02:19.020 --> 00:02:21.860 align:middle line:84%
So in this case we have
CA with heart rate change.

00:02:21.860 --> 00:02:25.870 align:middle line:84%
And that correlation, you
can see here, is 0.91.

00:02:25.870 --> 00:02:28.280 align:middle line:84%
Now if you look on the
other side of that diagonal

00:02:28.280 --> 00:02:31.670 align:middle line:84%
you're also going to see
a different output there.

00:02:31.670 --> 00:02:35.690 align:middle line:84%
In this case it was heart
rate change with CA.

00:02:35.690 --> 00:02:38.030 align:middle line:84%
It is still the exact
identical thing.

00:02:38.030 --> 00:02:41.390 align:middle line:84%
What happens is is anytime
you run a correlation matrix

00:02:41.390 --> 00:02:44.335 align:middle line:90%
it reports those results twice.

00:02:44.335 --> 00:02:46.085 align:middle line:84%
You're always going
to have that diagonal.

00:02:46.085 --> 00:02:49.470 align:middle line:84%
One set of results are going
to get reported to the right.

00:02:49.470 --> 00:02:52.670 align:middle line:84%
And ones set are going to
get reported to the left.

00:02:52.670 --> 00:02:55.400 align:middle line:84%
You need to make sure that
you watch where that line

00:02:55.400 --> 00:02:58.940 align:middle line:84%
diagonal is so that you don't
end up accidentally reporting

00:02:58.940 --> 00:03:00.500 align:middle line:90%
all of these results twice.

00:03:00.500 --> 00:03:02.417 align:middle line:90%


00:03:02.417 --> 00:03:04.500 align:middle line:84%
So let's see what this
looks like if we're dealing

00:03:04.500 --> 00:03:06.460 align:middle line:90%
with a much larger data set.

00:03:06.460 --> 00:03:08.790 align:middle line:84%
So I'm going to come up
here to Data, Import data.

00:03:08.790 --> 00:03:11.130 align:middle line:84%
I'm going to import
it from an SPSS file.

00:03:11.130 --> 00:03:12.850 align:middle line:84%
I'm going to give
this one a new name.

00:03:12.850 --> 00:03:16.000 align:middle line:84%
We're just going to
add a 1 to that one.

00:03:16.000 --> 00:03:16.855 align:middle line:90%
All right, an 11.

00:03:16.855 --> 00:03:18.980 align:middle line:84%
And what we want to do is
open this one right here,

00:03:18.980 --> 00:03:21.420 align:middle line:90%
the textbook data set shortened.

00:03:21.420 --> 00:03:21.920 align:middle line:90%
OK.

00:03:21.920 --> 00:03:23.711 align:middle line:84%
So now we're going to
have that data set 11

00:03:23.711 --> 00:03:25.980 align:middle line:90%
that I just created.

00:03:25.980 --> 00:03:31.490 align:middle line:84%
So what we want to do is go
back to Tests, Summaries,

00:03:31.490 --> 00:03:33.002 align:middle line:90%
Correlation matrix.

00:03:33.002 --> 00:03:34.460 align:middle line:84%
Now what we want
to do is I'm going

00:03:34.460 --> 00:03:37.830 align:middle line:84%
to select a series of
different variables.

00:03:37.830 --> 00:03:40.080 align:middle line:84%
One of the things we've
looked at in other stuff

00:03:40.080 --> 00:03:43.110 align:middle line:84%
is looking at that relationship
between assertiveness.

00:03:43.110 --> 00:03:44.860 align:middle line:84%
Now I'm going to
hold the Control key.

00:03:44.860 --> 00:03:46.444 align:middle line:84%
So that I can not--
if I hit the Shift

00:03:46.444 --> 00:03:48.984 align:middle line:84%
and then try to hit things it's
going to highlight everything

00:03:48.984 --> 00:03:49.610 align:middle line:90%
in between.

00:03:49.610 --> 00:03:49.745 align:middle line:90%
Right.

00:03:49.745 --> 00:03:51.244 align:middle line:84%
So if I hit
assertiveness and then I

00:03:51.244 --> 00:03:54.660 align:middle line:84%
hit the Control key I can
select the ones I want.

00:03:54.660 --> 00:03:57.600 align:middle line:84%
So I want assertiveness, big
communication apprehension,

00:03:57.600 --> 00:03:59.515 align:middle line:84%
big willingness to
communicate, and then

00:03:59.515 --> 00:04:01.170 align:middle line:84%
I'm going to scroll down
here towards the bottom

00:04:01.170 --> 00:04:03.378 align:middle line:84%
because I know the last one
I want is responsiveness.

00:04:03.378 --> 00:04:04.614 align:middle line:90%
And there it is.

00:04:04.614 --> 00:04:06.030 align:middle line:84%
So what I've done
is I've selected

00:04:06.030 --> 00:04:09.840 align:middle line:84%
those four different
variables to correlate.

00:04:09.840 --> 00:04:12.550 align:middle line:84%
So let's go ahead and look
at that correlation matrix.

00:04:12.550 --> 00:04:14.640 align:middle line:84%
Now you're going to
notice that, again,

00:04:14.640 --> 00:04:17.640 align:middle line:84%
we're still going to have
that diagonal row of 1's.

00:04:17.640 --> 00:04:19.640 align:middle line:90%
So I'm showing you those.

00:04:19.640 --> 00:04:21.149 align:middle line:84%
And for our purposes
we only want

00:04:21.149 --> 00:04:24.000 align:middle line:90%
to report the 1's to the right.

00:04:24.000 --> 00:04:26.070 align:middle line:84%
Now you can report
the 1's to the left.

00:04:26.070 --> 00:04:27.490 align:middle line:90%
That's up to you.

00:04:27.490 --> 00:04:30.420 align:middle line:84%
It's just you need to be clear
in your own head as to which

00:04:30.420 --> 00:04:31.712 align:middle line:90%
ones that you're looking at.

00:04:31.712 --> 00:04:33.170 align:middle line:84%
So let's go ahead
and look at them.

00:04:33.170 --> 00:04:34.753 align:middle line:84%
One of the things I
want you to notice

00:04:34.753 --> 00:04:36.630 align:middle line:84%
that we didn't
mention previously

00:04:36.630 --> 00:04:39.810 align:middle line:84%
is that we don't actually
have the p values.

00:04:39.810 --> 00:04:41.850 align:middle line:84%
So you would want to
go ahead and check out

00:04:41.850 --> 00:04:46.470 align:middle line:84%
the textbook to see what
your p values actually are.

00:04:46.470 --> 00:04:51.380 align:middle line:84%
So you would need to compare the
calculated value to the actual

00:04:51.380 --> 00:04:52.350 align:middle line:90%
p-value--

00:04:52.350 --> 00:04:53.910 align:middle line:84%
to the critical
value table so that

00:04:53.910 --> 00:04:55.810 align:middle line:84%
you can know what
that p-value is.

00:04:55.810 --> 00:04:59.730 align:middle line:84%
So we know that in this case we
have Big-CA with assertiveness

00:04:59.730 --> 00:05:03.330 align:middle line:84%
is negatively correlated, Big
Willingness To Communicate

00:05:03.330 --> 00:05:06.300 align:middle line:84%
is positively related
to assertiveness.

00:05:06.300 --> 00:05:11.690 align:middle line:84%
Responsiveness is
correlated at 0.08.

00:05:11.690 --> 00:05:13.900 align:middle line:84%
We can go through
and look at all

00:05:13.900 --> 00:05:15.810 align:middle line:84%
of these different
relationships.

00:05:15.810 --> 00:05:18.910 align:middle line:84%
The one that we know is not
statistically significant,

00:05:18.910 --> 00:05:21.330 align:middle line:84%
having run it in some of the
other statistical software

00:05:21.330 --> 00:05:23.640 align:middle line:84%
packages, is this
one right here,

00:05:23.640 --> 00:05:26.790 align:middle line:84%
which is Responsiveness with
Big Communication Comprehension.

00:05:26.790 --> 00:05:28.500 align:middle line:84%
And again, there is
no way of knowing

00:05:28.500 --> 00:05:30.420 align:middle line:90%
that just looking at it.

00:05:30.420 --> 00:05:33.570 align:middle line:84%
It just happens to be that I've
run this in many other stats

00:05:33.570 --> 00:05:35.460 align:middle line:84%
packages over the
years and I know

00:05:35.460 --> 00:05:39.520 align:middle line:84%
that that one happens to not
be statistically significant.

00:05:39.520 --> 00:05:46.490 align:middle line:84%
So that is how you can run and
correlation using R Commander.

00:05:46.490 --> 00:06:00.094 align:middle line:90%