SPSS Tutorial
SPSS Tutorial
SPSS is available on most machines at Georgetown; it can also be purchased through the school for $180.
The Basics:
Setting up data:
Open SPSS
Either open an existing data set, or create a new one if you’re entering data for the first time.
How to enter data:
It isn’t as easy as Excel, but you can do a lot more with the data.
On the bottom right side of the window, there’s a file tab marked “variable view.” Click it.
That will take you to a screen that looks like this:
This data set was created using a sample available on SPSS, but you’d do pretty much the same for your data. If you want to follow along and use the data shown above, when you open SPSS and a window pops up
(SPSSstartwindow.bmp)
Hit “Open existing data set” and open the “Breast cancer survival” data.
Variables are defined in the variable view folder. Here, you tell the computer what each of your variables look like. All the entries in the first column will end up being column headers in the “data view” tab. For example, in row 1 is the variable “id,” or identification. It is simply the identification number of a person in the study. Also in this folder, you define the scale of measurement as nominal, ordinal, or scale (which refers to either interval or ratio).
“Name” is simply the variable that you’re defining.
“Type” is what kind of variable it is: numeric, comma, dot, scientific notation, date, dollar, custom currency, or string. Usually you’ll use “numeric” as a type, and each level of the variable gets assigned a number.
For example, if you’re doing a study looking at the differences between Blondes and Brunettes, which is nominal data, you’d assign a number to Blonde and a number to Brunette. Assigning numbers to nominal data is helpful down the line, when you start doing inferential statistics.
Once your variables are defined, go back to the Data View tab. All the entries in column one of the Variable View tab should now be heading each column on the chart. Then all you have to do is enter the data.
Frequency Distributions
To view a frequency distribution, go to the top of the screen and click on the Analyze tab.
Analyze > Descriptive Statistics > Frequencies
This will open up a window. In the window, select the variables you want to use for the distribution by double clicking them.
Then hit OK and SPSS will start running a frequency table. In this example, I used Age vs. Pathological Tumor Size. This is what it came up with:
Notice the scroll bars—this table goes down for a while.
Presenting data in Graphic Form:
Like above, you’re going to want to go to the frequencies window. So go to Analyze > Descriptive Statistics > Frequencies
Frequency charts allow you to pick what your data is going to look like. Try a histogram.
From the frequency table window, hit “chart.” Then, click histogram, check the “normal curve” box, and click “continue.” Run the frequency table again by clicking OK in the frequency window. A new tree of files will appear with your frequency table:
This chart shows the age distribution of the subjects. Notice on the right that it also displays the standard deviation, mean, and number of subjects.
Printing Data
Go to FILE> Print
From here, you can specify the style of printout by clicking on the Properties box.
Important! When printing, make sure the SPSS VIEWER window is active. This will cause only the results of your analyses to print. If the SPSS Data Editor is active when you choose to print, all of your data will print, but no analyses.
Back to Computer Page
References:
All images and data acquired from SPSS for Windows.
Pavkov, Thomas W., & Pierce, Kent A. (2003). Ready, set, go! A Student guide to SPSS(R) 11.0 for Windows. Boston: McGraw-Hill.
