|
I’m going to use this example to
help you understand how to enter the data. Suppose you want to study the
effect of caffeine (IV) on the number of hours participants sleep (DV). You
have two conditions in your experiment, caffeine administered to
participants and no caffeine administered. Each participant participates in
both conditions of the experiment. Each condition is separated by one
week’s time. Because the participants in each condition are related, they
are actually the same exact participants in each condition, we will use the
Paired Samples T-Test. Here are the data. You can see participants in each
condition and the average number of hours they sleep each night.
|
Condition 1: Caffeine |
Condition 2: No Caffeine
|
|
Participant 1 = 6 hours
Participant 2 = 5 hours
Participant 3 = 4 hours
Participant 4 = 7 hours
Participant 5 = 5 hours |
Participant 1 = 9 hours
Participant 2 = 10 hours
Participant 3 = 8 hours
Participant 4 = 9 hours
Participant 5 = 11 hours |
In this experiment, you want to know
if there is a significant different between the data collected from each
condition, caffeine administered and no caffeine administered. You want to
know if caffeine really does have an effect on the amount of sleep that
participants get. Does caffeine intake significantly increase or decrease
the amount of sleep that people get? Is there no difference in the amount of
sleep for caffeine and no caffeine conditions?
Just looking at the data, you can
probably see that there is a difference in amount of sleep between the two
conditions. You can probably see that amount of sleep in the no caffeine
condition appears to be much greater than the amount of sleep in the no
caffeine condition. People generally appear to get more sleep when they have
not consumed caffeine. So why do I have to conduct this t-test? The reason
is that we are not just trying to figure out if there is a difference in
amount of sleep between each group. We want to know if there is a
statistically significant difference. That is, a real difference as
defined by statistics. The paired samples t-test will be able to tell us
that.
Like the Independent Samples T-test,
you will use the first two columns of your SPSS data file to enter the data
for the Paired Samples T-test. However, you will be using these two columns
in a different way. Both columns will contain data points collected in your
experiment.
In this column, you will enter the
DV data collected in the first condition of the experiment. In our example
experiment, the first condition was one in which participants were
administered caffeine. So, we enter all the data collected for this
condition. See the number 6 in the first cell? That indicates that the first
participant in condition 1 (caffeine) averaged 6 hours of sleep.
When you are finished entering the
data, double click on the top of the first column to name it. The Define
Variable box will pop up and you can enter a new name for the variable in
the Variable Name area. Give the variable a meaningful name. This will make
your life a lot easier when you analyze the data and interpret the results.
Because this column represents DV
data collected from the first condition of this experiment, it is a good
idea to name the variable after this condition. In the below example, I
decided to name my variable “cafdta.” I decided on this name because this
column has data that was collected in the caffeine conditions. Click OK when
you are finished using the Define Variable box and it will disappear.
In this column, you should type in
the DV data collected in the second condition of the experiment. In our
example, this would be the data collected in the no caffeine condition. See
how the first data point in the second column is a 9? This tells SPSS that
the first participant in the no caffeine condition averaged 9 hours of sleep
per night.
Name
the second column
Double click on the top of the
second column to name it. Enter a name into the variable name box. The
second column represents your DV data collected in the second condition.
Give this column a meaningful name. In our example, I name the variable
“nocafdta” to indicate that this column contains data from the no caffeine
condition. Click OK when you are finished.
Always remember to save your data
file to a meaningful place with a meaningful name. You don’t want to lose
this file and enter the data all over again. I decided to name my data file
“Effect of Caffeine on Number of Hours of Sleep Data.sav.” It’s a long name
but this file will be very easy for me to identify in the future.
Background |
Enter Data |
Analyze Data |
Interpret Data |
Report Data
|