Psych. 280: Statistics in Psychological Research
Fall 2004
Computer Assignment 3: Correlation and Multiple Regression
due: Friday, 12/10/04
For this assignment, you will collect a single data set with which to conduct correlational and multiple
regression analyses. To complete this assignment, you will need to undertake three tasks: (a) collect a
data set, (b) conduct appropriate analyses, and (c) write a laboratory paper reporting your study and the
results that you obtained. Please note that you will be using an alpha level of = .05 for all of your
analyses. While you may conduct your study and complete your analyses in small groups, you
must write your laboratory report on your own.
Collect a Data Set
You may work in small groups (no more than six of you may work together in a single group) to collect
your data. You will need to design a small study that includes two independent variables and a
dependent variable. While technically the term independent variable applies to variables that have been
manipulated, the statistical analyses we are working with are appropriate for use with non-manipulated
variables. For instance, you might ask participants to report the amount of conflict (perhaps using a four
point scale, where 1 = not at all, 2 = a little bit, 3 = quite a bit, and 4 = very much) they are currently
experiencing with their mother, father, and a same-sex friend using a single question for each
relationship category. You must collect data from at least 48 individuals.
Conduct Appropriate Analyses
To conduct these analyses, you will first need to enter the data that you collected for your study. Using
the SPSS Data Editor window, define two columns for your independent variables and one column for
your dependent variable. Remember, you will need to define your independent and dependent variables.
To do this, click on the “variable view” icon at the bottom of the SPSS Data Editor window. Type in an
eight character label in the “name” column for each of your two variables.
Here is an example of what your data might look like for your first 10 participants:
To begin your analyses, you will need to compute the mean and standard deviation for each of your
variables. To do this, simply click on the “Analyze” icon at the top of the window to get the available
options, and then select “Descriptive Statistics” and then the “Descriptives” option. Your window will
look like this:
Select the three variables and transfer them to the “Variable(s)” box, then click “OK”. Your output
window will look like this:
You will need to prepare a summary table for your paper that reports the mean and standard deviation
for each of the three variables. Remember, you should use labels in your paper that will be easy for the
reader to understand; you are NOT limited to only 8 characters for a label to be used in your paper. So,
for example, you might use the phrase “Maternal Conflict” to refer to the variable labeled “mom_con”
in your SPSS file.
You will next need to compute the correlations between each of the pairs of variables in your study. To
do this, click on the “Analyze” icon, then click on “Correlate” and then “Bivariate”. Your window will
now look like this:
Transfer the three variables to the “Variables” box, and then click “OK”. Your output will window will
look like this:
In this table, the correlation between maternal conflict and paternal conflict is .692, and that the p-value
is less than .001 (the p-value, printed directly below the correlation, is written as .000). The printout
also informs you that this correlation was computed using data from 48 individuals. You will need to
provide a table reporting your correlations in your paper; you can use asterisks to indicate the statistical
significance of the correlations (e.g., *p .05, report that the difference was NONsignificant, not INsignificant.
Correct way to report nonsignificant differences: t(31) = .38, n.s.
Round everything to 2 decimal places.
The word “data” is plural, hence, “The data WERE collected,” NOT “The data WAS collected.”
Unless you used a random number table or otherwise ensured random selection, you cannot say that
you “randomly” chose participants.
Use “men” and “women,” rather than “males” and “females” when talking about human subjects.
Don’t use the word “condition” unless you conducted an experiment and manipulated something.
Typing instructions: You can get the symbol by typing an “m” in symbol font. Similarly, a is
an s in symbol font. You can get subscripts (and superscripts) by going under the “Format” menu in
Microsoft Word and choosing “Font.” Highlight the letter or number and click on subscript (e.g.,)
or superscript (e.g., t2).