WEBVTT

00:00:00.000 --> 00:00:01.996 align:middle line:90%
[MUSIC PLAYING]

00:00:01.996 --> 00:00:15.980 align:middle line:90%


00:00:15.980 --> 00:00:16.640 align:middle line:90%
Hello.

00:00:16.640 --> 00:00:18.890 align:middle line:84%
In this video, we're going
to discuss how to calculate

00:00:18.890 --> 00:00:22.740 align:middle line:90%
a one-way ANOVA using SPSS.

00:00:22.740 --> 00:00:24.460 align:middle line:84%
Now, we're using
the exact same data

00:00:24.460 --> 00:00:28.190 align:middle line:84%
set that is available for you
that corresponds with the case

00:00:28.190 --> 00:00:30.710 align:middle line:90%
study in the textbook.

00:00:30.710 --> 00:00:33.170 align:middle line:84%
In this case, we have three
different color rooms,

00:00:33.170 --> 00:00:36.360 align:middle line:84%
and we're seeing how long
it took to take a quiz.

00:00:36.360 --> 00:00:38.270 align:middle line:84%
Let's go ahead and
do the analysis.

00:00:38.270 --> 00:00:40.310 align:middle line:90%
I want to scroll up to Analyze.

00:00:40.310 --> 00:00:43.970 align:middle line:84%
I'm going to go down to
the General Linear Model.

00:00:43.970 --> 00:00:48.694 align:middle line:84%
I'm going to scroll over to
Univariate and click on Area.

00:00:48.694 --> 00:00:50.610 align:middle line:84%
From there, I need to
know a couple of things.

00:00:50.610 --> 00:00:52.735 align:middle line:84%
One, I need to know which
is the dependent variable

00:00:52.735 --> 00:00:56.030 align:middle line:84%
and which is what's called
the fixed factors variable.

00:00:56.030 --> 00:00:59.180 align:middle line:84%
For our purposes, the room
color, or the nominal variable,

00:00:59.180 --> 00:01:02.103 align:middle line:84%
is going to be your
fixed factors variable.

00:01:02.103 --> 00:01:04.519 align:middle line:84%
So I'm going to go ahead and
make sure that is highlighted

00:01:04.519 --> 00:01:06.080 align:middle line:90%
and click on the arrow.

00:01:06.080 --> 00:01:07.610 align:middle line:84%
Then we have the
dependent variable.

00:01:07.610 --> 00:01:09.950 align:middle line:84%
In this case, it is
the time in minutes.

00:01:09.950 --> 00:01:12.326 align:middle line:84%
It's usually going to be your
interval or ratio variable.

00:01:12.326 --> 00:01:14.450 align:middle line:84%
And then I'm going to go
ahead and click that over.

00:01:14.450 --> 00:01:15.690 align:middle line:90%
But we're not done yet.

00:01:15.690 --> 00:01:17.440 align:middle line:84%
There's a couple other
things that we want

00:01:17.440 --> 00:01:19.080 align:middle line:90%
to make sure that we look at.

00:01:19.080 --> 00:01:22.970 align:middle line:84%
For example, one thing we
want to look at is Options.

00:01:22.970 --> 00:01:25.160 align:middle line:84%
So we want to go to
the Univariate Options,

00:01:25.160 --> 00:01:30.440 align:middle line:84%
click on Color, and get that
over to the Display Means for.

00:01:30.440 --> 00:01:34.220 align:middle line:84%
And then we can click on
Descriptive statistics

00:01:34.220 --> 00:01:36.890 align:middle line:90%
and Estimates of effect size.

00:01:36.890 --> 00:01:39.740 align:middle line:84%
This is going to get us
those descriptive statistics,

00:01:39.740 --> 00:01:42.150 align:middle line:84%
and it's also going to
get us our eta squared.

00:01:42.150 --> 00:01:43.940 align:middle line:90%
Then we can click Continue.

00:01:43.940 --> 00:01:47.720 align:middle line:84%
We also want to go ahead and
run our post-hoc analysis.

00:01:47.720 --> 00:01:50.160 align:middle line:84%
So I'm going to go ahead and
click on the Post Hoc button.

00:01:50.160 --> 00:01:51.890 align:middle line:84%
And again, I'm going to
make sure Color is selected,

00:01:51.890 --> 00:01:53.973 align:middle line:84%
and I'm going ahead and
click the arrow to send it

00:01:53.973 --> 00:01:56.680 align:middle line:90%
to the Post-hoc Tests for.

00:01:56.680 --> 00:01:58.640 align:middle line:84%
And then you have a bunch
of different options.

00:01:58.640 --> 00:02:01.130 align:middle line:84%
For our purposes
right now, I am just

00:02:01.130 --> 00:02:03.500 align:middle line:84%
going to run the most
conservative one, which

00:02:03.500 --> 00:02:04.610 align:middle line:90%
is the Scheffe test.

00:02:04.610 --> 00:02:06.680 align:middle line:90%
And then I can click Continue.

00:02:06.680 --> 00:02:08.419 align:middle line:84%
Once I have done
all of that, I am

00:02:08.419 --> 00:02:10.789 align:middle line:90%
ready to run the one-way ANOVA.

00:02:10.789 --> 00:02:12.650 align:middle line:90%
Let's click OK.

00:02:12.650 --> 00:02:15.640 align:middle line:84%
Now, as you already know, there
is a lot of different data

00:02:15.640 --> 00:02:17.810 align:middle line:84%
that gets presented
to you whenever

00:02:17.810 --> 00:02:19.580 align:middle line:90%
you run a one-way ANOVA.

00:02:19.580 --> 00:02:22.040 align:middle line:84%
The first box is going to be
your descriptive statistics.

00:02:22.040 --> 00:02:24.899 align:middle line:84%
So you have the white room, the
yellow room, and the blue room,

00:02:24.899 --> 00:02:27.440 align:middle line:84%
and it lets you know what the
mean was, the number of minutes

00:02:27.440 --> 00:02:29.190 align:middle line:84%
it took to finish the
test, and of course,

00:02:29.190 --> 00:02:30.920 align:middle line:90%
your standard deviations.

00:02:30.920 --> 00:02:35.225 align:middle line:84%
From there, you have the test
of between-subjects effects.

00:02:35.225 --> 00:02:37.100 align:middle line:84%
This is the one that's
going to basically let

00:02:37.100 --> 00:02:39.860 align:middle line:84%
us know whether or not the
overall model was statistically

00:02:39.860 --> 00:02:41.100 align:middle line:90%
significant.

00:02:41.100 --> 00:02:43.340 align:middle line:84%
So we want to look
for the word "color."

00:02:43.340 --> 00:02:45.135 align:middle line:90%
In this case, here it is.

00:02:45.135 --> 00:02:46.760 align:middle line:84%
And then, of course,
it's going to have

00:02:46.760 --> 00:02:48.740 align:middle line:84%
your degrees of
freedom, which is

00:02:48.740 --> 00:02:52.010 align:middle line:84%
going to be that 2 and the
one right below that, 9.

00:02:52.010 --> 00:02:54.200 align:middle line:84%
Then it's going to
have your F-value here.

00:02:54.200 --> 00:02:56.810 align:middle line:90%
In this case, it's 7.20.

00:02:56.810 --> 00:02:58.460 align:middle line:84%
It's going to have
our significance

00:02:58.460 --> 00:03:03.800 align:middle line:84%
level, our p-value, which
is p is equal to 0.014.

00:03:03.800 --> 00:03:06.340 align:middle line:84%
And last, we have our
partial eta squared.

00:03:06.340 --> 00:03:10.190 align:middle line:84%
And in this case,
that number is 0.615.

00:03:10.190 --> 00:03:12.860 align:middle line:84%
So we now know that
that overall model

00:03:12.860 --> 00:03:15.000 align:middle line:90%
was statistically significant.

00:03:15.000 --> 00:03:17.632 align:middle line:84%
So we do know that there is
a difference between people

00:03:17.632 --> 00:03:20.090 align:middle line:84%
in the white, yellow, and blue
rooms and the amount of time

00:03:20.090 --> 00:03:22.520 align:middle line:90%
it took to take the test.

00:03:22.520 --> 00:03:25.970 align:middle line:84%
The next box is going to be
the estimated marginal means

00:03:25.970 --> 00:03:27.000 align:middle line:90%
for our purposes.

00:03:27.000 --> 00:03:29.690 align:middle line:84%
We don't need to spend too
much time looking at that.

00:03:29.690 --> 00:03:32.050 align:middle line:84%
There are two last
boxes here, and they

00:03:32.050 --> 00:03:34.490 align:middle line:84%
are going to show us
some of the same things.

00:03:34.490 --> 00:03:36.710 align:middle line:84%
I prefer the Multiple
Comparisons box,

00:03:36.710 --> 00:03:39.080 align:middle line:90%
just because it's easier to see.

00:03:39.080 --> 00:03:42.080 align:middle line:84%
How this actually works is,
here we have one of the rooms,

00:03:42.080 --> 00:03:44.090 align:middle line:84%
and then we're comparing
it to the other rooms.

00:03:44.090 --> 00:03:45.860 align:middle line:84%
So in this case,
we have white being

00:03:45.860 --> 00:03:48.660 align:middle line:84%
compared to the yellow
room and the blue room.

00:03:48.660 --> 00:03:52.400 align:middle line:84%
If there is a star
next to it, that

00:03:52.400 --> 00:03:55.010 align:middle line:84%
means that there is a
statistically significant

00:03:55.010 --> 00:03:56.600 align:middle line:90%
difference there.

00:03:56.600 --> 00:03:58.790 align:middle line:84%
So let's go ahead and look
at the white and yellow.

00:03:58.790 --> 00:04:00.810 align:middle line:84%
There is no star, so
there is no difference.

00:04:00.810 --> 00:04:03.170 align:middle line:84%
The white and the
blue, there is.

00:04:03.170 --> 00:04:04.730 align:middle line:84%
So if we scroll back
up here and look

00:04:04.730 --> 00:04:06.470 align:middle line:84%
at those descriptive
statistics, we

00:04:06.470 --> 00:04:09.620 align:middle line:84%
have the white, which
had a mean of 5,

00:04:09.620 --> 00:04:13.220 align:middle line:90%
and blue, which had a mean of 9.

00:04:13.220 --> 00:04:15.410 align:middle line:84%
In other words, people
in the white room

00:04:15.410 --> 00:04:19.310 align:middle line:84%
took less time than
people in the blue room.

00:04:19.310 --> 00:04:21.620 align:middle line:84%
Now, if we go back
down here, you'll

00:04:21.620 --> 00:04:23.270 align:middle line:84%
also see that there
is no difference

00:04:23.270 --> 00:04:26.960 align:middle line:84%
between the yellow room
with either white or blue.

00:04:26.960 --> 00:04:29.567 align:middle line:84%
And then the last one basically
does the same comparison,

00:04:29.567 --> 00:04:32.150 align:middle line:84%
except in this case, it looks
at the blue with the white room,

00:04:32.150 --> 00:04:35.280 align:middle line:84%
which you'll notice is the
same, and then yellow and blue,

00:04:35.280 --> 00:04:37.095 align:middle line:84%
which, again, there
is no difference.

00:04:37.095 --> 00:04:39.470 align:middle line:84%
So if you come down here and
look at the time in minutes,

00:04:39.470 --> 00:04:42.050 align:middle line:90%
it also is a very similar test.

00:04:42.050 --> 00:04:43.880 align:middle line:84%
From looking at the
Scheffe, it just

00:04:43.880 --> 00:04:47.570 align:middle line:84%
does it in a slightly
different way, which

00:04:47.570 --> 00:04:50.222 align:middle line:84%
is why I don't think this
one is as easy to understand,

00:04:50.222 --> 00:04:51.680 align:middle line:84%
which is why I
always say just look

00:04:51.680 --> 00:04:53.270 align:middle line:84%
at the multiple
comparisons test,

00:04:53.270 --> 00:04:55.940 align:middle line:84%
and you're going to get all
the information you need.

00:04:55.940 --> 00:04:59.050 align:middle line:84%
So yes, there is a statistically
significant difference

00:04:59.050 --> 00:05:01.100 align:middle line:84%
in the amount of
time it took to take

00:05:01.100 --> 00:05:03.500 align:middle line:84%
the test between the
white, yellow, and blue.

00:05:03.500 --> 00:05:06.050 align:middle line:84%
But the only
significant difference

00:05:06.050 --> 00:05:08.870 align:middle line:84%
really was between the white
room and the blue room.

00:05:08.870 --> 00:05:11.030 align:middle line:84%
Yellow was not
different from white,

00:05:11.030 --> 00:05:13.310 align:middle line:84%
and yellow was not
different from blue.

00:05:13.310 --> 00:05:18.720 align:middle line:84%
And that is how you can use SPSS
to calculate a one-way ANOVA.

00:05:18.720 --> 00:05:21.470 align:middle line:90%
[MUSIC PLAYING]

00:05:21.470 --> 00:05:32.926 align:middle line:90%