Using SPSS and PASW/Descriptives

From Wikibooks, open books for an open world
Jump to: navigation, search

Descriptive statistics are used to describe variables. Examples of descriptive statistics include: mean, median, mode, standard deviation, and range. Here we'll describe how to have SPSS calculate three of them, the mean, median and mode, for a variable “age”, plus introduce the concept of skewed distribution.

In order to generate descriptives in SPSS, you first need to open up a data set. In this book a Genetic Counseling example data set is utilized.

Once it's open, we click “Analyze” → “Descriptive Statistics” → “Frequencies...”:


A Frequencies Window will appear on the screen. Select the variable labeled “age” on the left and click the blue arrow to move it into the Variable(s) box:


Please then click on the Statistics... button. A new window will appear, with a grouping named "Central Tendency." There, select Mean, Median, and Mode and click Continue:


Once the box disappears, click “OK” in the Frequencies Box. The valid versus missing breakdown, along with the mean (average), median (middle), and mode (most common) age of participating genetic counselors will appear at the top of the Output window:


In the example above, the mean age of participants is 35.93. The data set's median age is 33, and the mode is 28.

Distribution Curves in SPSS[edit]

If you want to see where the mean, median, and mode fall on a frequency distribution curve, SPSS can show you. This is useful when you are trying to determine if your value's distribution is normal or skewed. (A discussion of skewness statistics is beyond the scope of this book).

Please repeat the above example, again utilizing the variable of “age”, until the “Frequencies” window is open again. Click the button labeled “Charts...” to open a window offering Chart Type:


Select the radio button labeled “Histograms” and check “With normal curve.” Click “Continue” then “OK” and your chart will pop up in the Output box:


The frequency curve in this example shows a positively skewed distribution, i.e., values off the normal curve in a positive direction.

Chapter 15 contributed by Kristin Mraz.