How to Calculate Pearson's R (Pearson Correlations) in SPSS / PASW Statistics

Pearson correlations, also known as Pearson's R, can be tiresome to calculate by hand. However, the statistical software suite known as SPSS (now also known as PASW Statistics) makes it easy.

Difficulty: Easy

Instructions

Things You'll Need:

• SPSS (aka PASW Statistics 17), any version

1. To calculate a Pearson correlation between two variables in SPSS (PASW Statistics), first load up your data in SPSS. You'll need at least two numeric variables to correlate with each other.
   
   (SPSS identifies numeric variables by putting tiny ruler icons next to them. If you see three multicolored balls next to your variable, it means that SPSS has misidentified your variable as a nominal variable--if this is the case, you'll need to go into Variable View and change your variable to a numeric variable before continuing.)

2. Go to the Analyze menu, and select "Correlate -> Bivariate..." You'll be presented with a screen with two boxes. Click on a variable in the box on the left, and click the arrow between the boxes to move the variable over to the box on the right. Repeat this process for at least one additional variable. The "Variables" box on the right should now contain at least two items.

3. If you care about significance levels, select whether you want either a one or two-tailed test from the option buttons at the bottom of the window. Recall that directional hypotheses call for one-tailed tests, while non-directional hypotheses call for two-tailed tests. If determining the significance level of your correlation is not important to you, don't worry about it--the value of your final R statistic will be the same either way.

Tips & Warnings

• If you wish to see additional statistics, then before clicking "OK", click the "Options..." button at the top left hand corner of the window. You'll be presented with options to view additional descriptives such as means, standard deviations, cross-product deviations, and covariance statistics.
• The "Options" button also allows you to exclude cases "pairwise"--which means any pair of data points being compared will be excluded if one of these points is missing--or "listwise," which means that the entire row will be excluded. There's not much difference between these options if you are only correlating two variables. However, if you are comparing three or more variables at once, excluding cases pairwise retains more data.