SPSS for
Windows: Getting Started
This document is the first of a series of four modules
intended for beginning SPSS users, providing an overview of SPSS
for Windows. This first module introduces readers to the SPSS
for Windows environment, and discusses how to create or import a dataset,
transform variables, manipulate data, and perform descriptive statistics. The second module
describes some commonly used inferential statistics, the third module discusses graphical
display of output, and the fourth module
covers other advanced topics. All
modules can be found on the Statistical Support website http://www.utexas.edu/its/rc/tutorials/
. Throughout these modules, a single dataset, Employee data.sav, is used
for all examples.This example dataset is provided with recent versions of SPSS.
Thus, you will have access to the dataset and will be able to use SPSS
to test your knowledge by replicating the examples contained in this document.
Although the present documentation assumes SPSS Version 14, it
will still be useful to users of SPSS on the Macintosh platform
as well as many earlier, similar versions of SPSS. If you are a
University of Texas affiliate and do not have access to SPSS
or would like the software for your personal computer, visit the Software
Distribution Services Web page at http://www.utexas.edu/its/sds/
to get more information about obtaining the latest version of SPSS.
SPSS
is a software package used for conducting statistical analyses, manipulating
data, and generating tables and graphs that summarize data. Statistical
analyses range from basic descriptive statistics, such as averages and
frequencies, to advanced inferential statistics, such as regression models,
analysis of variance, and factor analysis. SPSS also contains several tools for
manipulating data, including functions for recoding data and computing new
variables, as well as for merging and aggregating datasets. SPSS also has a
number of ways to summarize and display data in the form of tables and graphs.
1.2. Overview of SPSS for Windows
SPSS
for Windows consists of five different windows, each of which is associated
with a particular SPSS file type. This document discusses the two windows most
frequently used in analyzing data in SPSS, the Data Editor and the Output
Viewer windows. In addition, the Syntax Editor and the use of SPSS
command syntax is discussed briefly. The Data Editor is the window that is open
at start-up and is used to enter and store data in a spreadsheet format. The
Output Viewer opens automatically when you execute an analysis or create a
graph using a dialog box or command syntax to execute a procedure. The Output
Viewer contains the results of all statistical analyses and graphical displays
of data. The Syntax Editor is a text editor where you compose SPSS commands and
submit them to the SPSS processor. All output from these commands will appear
in the Output Viewer. This document focuses on the methods necessary for
inputting, defining, and organizing data in SPSS.
Section 2: Entering Data in SPSS
To
start SPSS, go to the Start icon on your Windows computer. You should
find an SPSS icon under the Programs menu item. You can also start SPSS
by double-clicking on an SPSS file. When the program opens, it will present you
with a “What would you like to do?” dialog box. For now, hit “Cancel” to
dismiss the box.
The
Data Editor window displays the contents of the working dataset. It is arranged
in a spreadsheet format that contains variables in columns and cases in rows.
There are two sheets in the window. The Data View is the sheet that is
visible when you first open the Data Editor; this sheet contains the data. You
can access the second sheet by clicking on the tab labeled Variable View.
While the second sheet is similar in appearance to the first, it does not
actually contain data. Instead, this second sheet contains information about
the variables in the dataset. Beginning with version 14, you can have multiple
datasets open at one time in the Data Editor (however, this can be confusing,
and we recommend keeping only one dataset open at a time while you are first
getting familiar with the program.)
Datasets that are currently open are called working datasets; all
data manipulations, statistical functions, and other SPSS procedures operate on
these datasets. Data can be directly entered in SPSS, or a file containing data
can be opened in the Data Editor. From the menu in the Data Editor window,
choose the following menu options:
File
Open
Data...
The Open File dialog box should
automatically open to the SPSS directory of example files. Choose Employee
data.sav from the list and click Open.
Your Data Editor should now look like this:
If
the file you want to open is not an SPSS data file, you can often use the Open
menu item to import that file directly into the Data Editor. If a data file is
not in a format that SPSS recognizes, then try using the software package in
which the file was originally created to translate it into a format that can be
imported into SPSS (e.g., Excel).
Another
important window in the SPSS environment is the Syntax Editor. In earlier
versions of SPSS, all of the procedures performed by SPSS were submitted
through the use of syntax, which instructed SPSS on how to process your data.
More recent versions contain pull-down menus with dialog boxes that allow you
to submit commands to SPSS without writing syntax. This SPSS for Windows
tutorial focuses on the use of dialog boxes to execute procedures; however,
there are at least two reasons why you should be aware of SPSS syntax, even if
you plan to primarily use the dialog boxes. First, not all procedures are
available through the dialog boxes. Therefore, you may occasionally have to
submit commands from the Syntax Editor. Second, the Syntax Editor is a useful
way to save a log of what you have done, and to re-run what you have done at a
later date. The dialog boxes available through the pull-down menus have a
button labeled Paste, which will print the syntax for the procedure you
are running in the dialog box environment to the Syntax Editor. Thus, you can
easily generate SPSS syntax without typing in the Syntax Editor. This process
is illustrated below.
The
following dialog box is used to generate descriptive statistics. (You can get
this dialog box by choosing Analyze,
then Descriptive Statistics, then Descriptives, then clicking over the
two variables using the arrow button.)
By
clicking on the Paste button, the procedure that the above dialog box is
prepared to run will be written in the form of SPSS syntax to the Syntax
Editor. Thus, clicking the Paste button in the above example would
produce the following syntax:
DESCRIPTIVES
VARIABLES=salbegin salary
/STATISTICS=MEAN STDDEV MIN MAX .
This
syntax will produce exactly the same output as would be generated by clicking
the OK button in the above dialog box. The syntax that is printed to the
Syntax Editor can then be saved and run at a later time, as long as the same
dataset (or at least a dataset containing the variables with the same names) is
active in the Data Editor window. Saving syntax is useful if you think you may
want to rerun your analysis after you add more data, or if you want to run the
same analysis on another dataset that contains the same variables.
When
you execute a command for a statistical analysis, regardless of whether you
used syntax or dialog boxes, the output will be printed in the Output Viewer.
An example of the output viewer is shown below:
The
left frame of the Output Viewer contains an outline of the objects contained in
the window. For example, the icon labeled Log represents the command
syntax shown at the top of the figure. Everything under Descriptives in
the outline refers to objects associated with the descriptive statistics. The Title
object refers to the bold title Descriptives in the output. The Active Dataset object refers to the line
in the output that designates which dataset was used to run the analysis. The
highlighted icon labeled Descriptive Statistics refers to the table
containing descriptive statistics. The Notes icon has no referent in the
above example, but it would refer to any notes that appeared between the title
and the table. This outline can be useful for navigating in your Output Viewer
when you have large amounts of output. By clicking on an icon, you can move to
the location of the output represented by that icon in the Output Viewer. You
can also copy, paste, or delete objects by first highlighting them in the
outline and then performing the operation you want.
You
can control what is displayed in your output by using the Options menu
item on the Edit menu:
Edit
Options...
Selecting
this option will produce the following dialog box:
This
figure shows the Options dialog box with the Draft Viewer tab
selected, to choose which options you want to appear in the Output Viewer. Most
commands are selected by default. Here, the Display commands in log
option, normally unselected, was selected so that the command syntax will be
written to the log in the Output Viewer. This can be useful for keeping track
of which procedures you have executed.
2.5. Importing Data from Excel Files
Data
can be imported into SPSS from Microsoft Excel and several other applications
with relative ease. This document describes a method for importing an Excel
spreadsheet into SPSS. If you are working with a spreadsheet in another
software package, you may want to save your data as an Excel file, then import
it into SPSS. If you have a spreadsheet that is arranged in a database format
(e.g., you have several tables in your Workbook that are related through
identification fields), there is another method for importing Excel file that
you might consider that will merge tables within your database as part of the
import procedure. It is described in our online tutorial SPSS Data
Manipulation, in the Database
Capture section (see http://www.utexas.edu/its/rc/tutorials/stat/spss/spss4/index.html).
In
order to easily import Excel data into SPSS, make sure your Excel spreadsheet
is formatted as follows: (1) the spreadsheet should have a single row of
variable names across the top of the file, and each variable name should begin
with ordinary letters, rather than with any special characters, (2) the data
should begin in the first column and second row of the Excel file, and (3) any
graphs, labels, or extra text that is not part of the dataset should be
deleted. To open an Excel file, select the following options from the menu in
the Data Editor window in SPSS:
File
Open
Data...
First,
select the desired location on disk using the Look in option. Next,
select Excel from the Files of type drop-down menu. The file you want
should now appear in the main box in the Open File dialog box. You can
open it by double-clicking on it. You will be presented with one more dialog
box:
Your
Excel spreadsheet should have all variable names on the top row, so leave the Read
variable names option checked. Since Excel files can consist of multiple
worksheets, the Worksheet drop-down
menu allows you to choose which worksheet you wish to open. You may ignore the
remaining options and choose OK. You
should now see data in the Data Editor window. Check to make sure that all
variables and cases were read correctly. Next, save your dataset in SPSS format
by choosing the Save option in the File menu.
2.6. Importing data from ASCII files
Data
are often stored in an ASCII file format, alternatively known as a text or flat
file format. Typically, columns of data in an ASCII file are separated by a
space, tab, comma, or some other character. To open these files, choose:
File
Read Text Data
The
Text Import Wizard will first prompt you to select a file to import. After you
have selected a file, you will go through a series of dialog boxes that will
provide you with several options for importing data. Once you have imported
your data and checked it for accuracy, be sure to save a copy of the dataset in
SPSS format by selecting the Save or Save As options from the File
menu:
File
Save
Save As...
Section 3:
Creating and Modifying Data in SPSS
3.1. Creating and Defining Variables
After
data are in the Data Editor window, there are several things that you may want
to do to describe your data. Before describing the process for defining
variables, an important distinction should be made between two terms that are
often confused: variable and value. A variable is a measure or
classification scheme that can have several values. Values are the numbers or
categorical classification representing individual instances of the variable
being measured. For example, a variable could be created for employment
classification status. Each individual in the dataset would be assigned a value
representing their job classification. For instance, we could assign clerks the
value 1, custodial workers the value 2, and managers the value 3.
One
reason to define information about your variables is to help you interpret the
output. For example, if your employment categories are coded as either 1, 2, or
3, it may be unwieldy to read the output if you are constantly trying to
remember which number represents which categories. One advantage of defining
variables is that these values can be assigned labels that will appear in your
output, thus making it much easier to interpret. Another aspect of defining
variable information is to provide SPSS with information about the type of data
in your dataset, which is often critical for SPSS to correctly process
analyses.
You
can define information about your variables by clicking the Variable View
tab. Doing so will bring the Variable Information sheet to the
foreground. You can also access this sheet by double-clicking one of the
variable names at the top of the columns in the Data Editor. The advantage of
the second method is that it takes you to the row for the variable whose column
head you clicked. Using the Employee
data.sav dataset, you will see a spreadsheet organized as the one below:
Many
of the cells in the spreadsheet contain hidden dialog boxes that can be
activated by clicking on a cell. If you see a gray box appear on the right side
of the cell when you first click on the cell, this indicates that there is a
hidden dialog box which can be accessed by clicking on that box. For example,
clicking on the box in the cell for the Type column for the variable jobcat
produces the following dialog box:
This
box allows you to define the type of data for variables. For example, you will
be presented with Numeric, String, and Date options. Thus,
if you wanted to define jobcat as a string variable rather than the
default numeric variable type, you would choose the String option.
Looking
back at the Variable View, the Missing Values column allows you to
define which values of a variable should be treated as missing data. The Label
column is used to define labels for variables. The Values column is used
to assign labels to the particular values of a variable. For example, the
following dialog box shows that the jobcat
variable that has been assigned the values 1, 2, and 3 for the labels Clerical,
Custodial, and Manager.
To
define variables as shown above, you should first enter the value (e.g., 1) in
the box labeled Value, then enter the label associated with that value
(e.g., Clerical), and click on the Add button. Repeat this
process for each value you want to label.
3.2. Inserting and Deleting Cases and Variables
You
may want to add new variables or cases to an existing dataset. For example, you
may want to add data about participants' ages to an existing dataset. To insert
a new variable, go to the Data View and right-click on the variable name next
to the place that you would like to insert a new variable, then choose Insert Variables. To insert a case,
right-click the row number below the place that you would like to insert the
new row, and choose Insert Case.
You
may also want to delete cases or variables from a dataset. To do that, select a
row or column, and use the Delete key on your keyboard to delete the
highlighted area. Alternatively, you can use the Clear option in the Edit
menu.
You
may want to create new variables in your datasets. For example, Employee data.sav contains employees'
salaries in terms of their beginning and current salaries, but you may also
want the difference between starting salary and present salary; this new
variable could be computed by subtracting the starting salary from the present
salary. Alternatively, you may want to transform an existing variable. For
example, the variable jobtime represents
months of experience on the job, but you may wish to analyze data in terms of
years on the job; in this case, you could compute the new variable by dividing jobtime by 12.
In
both situations, the new variable can be created using the Compute
option available from the menu in the Data Editor:
Transform
Compute...
To
create a new variable, type its name in the box labeled Target Variable.
The expression defining the variable being computed will appear in the box
labeled Numeric Expression. This expression can either be typed into the
box directly, or you can use the buttons located below the Numeric
Expression box to input values or operators.
The
example shown above demonstrates the computation of a new variable. This new
variable, salchange, will be the difference between an employee's
current salary and the employee's beginning salary. The new variable will
appear in the rightmost column of the working dataset.
Variables
can also be computed conditionally. For instance, if in the above example, you
were only interested in the change in salaries for people who began working for
the company within the last six years, you could create a condition that would
compute a new variable only if an employee had begun employment within the last
72 months. To do this, first click on the button labeled If, which will
produce the following dialog box:
First,
click on the button labeled Include if case satisfies condition to
activate the grayed-out areas of the dialog box. Then, specify the condition for
computing a new variable in the box at the top right. You can either type in
the condition or click on variables in the list on the left side of the dialog
box and use the buttons on the bottom middle of the dialog box. Variables can
be moved to the conditional box by clicking on the variable's name, then
clicking the arrow button between the two boxes. Clicking on the buttons on the
bottom left of the dialog box will cause the character on the button to be
displayed at the location of the cursor in the input box.
The
above example illustrates the definition of a condition that requires cases to
have less than 72 months’ experience in order to be included in the computation
of the new variable. The variable jobtime represents the number of
months since an employee has been hired. Here, only employees with jobtime
< 72, or who have been working at the company for less than 72 months,
will be included. Click the Continue button to return to the previous
dialog box, then click OK. The new
variable should appear in the rightmost column of your dataset. The first
several rows for this variable will be blank because these people have more
than 72 months of experience; scroll down about 2/3 of the way down the
dataset, and you will see the values for those with less than 72 months of
experience.
You
can also modify the values of existing variables in your dataset. For example,
the variable jobcat codes an
employee's status in three categories, but for a particular analysis you may
want to combine two of these classifications into a single category. To do
this, use the Recode option from the menu in the Data Editor:
Transform
Recode
You
will be offered two options for recoding variables in the Recode
submenu. The Into Same Variables option changes the values of the
existing variables, whereas the Into Different Variables option is used
to create a new variable with the recoded values. Both options are essentially
the same, except that recoding into a different variable requires you to supply
a new variable name. We typically recommend using the Into Different
Variables option, so that you do not overwrite your original data.
The
following example illustrates the use of the Recode Into Different Variables
option to recode jobcat into a new
two-category variable jobcat2.
First,
a variable from the existing dataset should be selected by clicking on that
variable, then clicking the arrow button in the middle of the dialog box. This
will result in the selected variable being displayed in the box labeled Numeric
Variable -> Output Variable. Next, you must supply the name of the new
variable, and optionally you can supply a label for the new variable. Then
click Change. After a new variable name has been supplied, click
on the button labeled Old and New Values.
The
original value of the variable being recoded is entered in the box labeled Old
Value, and the new value is entered in the box labeled New Value.
After values are entered in these boxes, click on the button labeled Add
to complete the recode process.
Here,
the old variable jobcat has 3 values, and we wish to recode it into only
two values. In the example dataset, jobcat has three values: 1, 2,
and 3. If the goal were to combine cases with the values 2 and 3, this could be
accomplished by recoding cases with the value 3 into 2's. Enter 3 in the box
labeled Old Value and enter 2 in the box labeled New Value, then
click Add.This can be repeated for as many of the values as necessary.
In this case, we want to simply copy all the other values; under Old Value, click on All other values, and under New
Value, click Copy old values,
then choose Add. Now that all the
old values have been accounted for, you may click Continue and then OK.
Values
can also be recoded conditionally. The process for recoding values on the basis
of a condition is essentially identical to the process for conditionally
computing new variables discussed in the previous section: when you click on
the If button in the main Recode dialog box, the same dialog box
that was obtained from clicking If in the Compute dialog box will
appear with the same options.
Sorting
cases allows you to organize rows of data in ascending or descending order on
the basis of one or more variable. For example, the data could be sorted by job
category, so that all of the cases coded as job category 1 appear first in the
dataset, followed by all of the cases that are labeled 2 and 3 respectively.
The data could also be sorted by more than one variable. For example, within
job category, cases could be listed in order of their salary. The Sort Cases
option is available under the Data menu item in the Data Editor:
Data
Sort Cases...
The
dialog box that results from selecting Sort Cases presents only a few
options:
To
choose whether the data are sorted in ascending or descending order, select the
appropriate button. You must also specify on which variables the data are to be
sorted. The hierarchy of such a sorting is determined by the order in which variables
are entered in the Sort by box. Variables are sorted by the first
variable entered, then the next variable is sorted within that first variable.
Here, jobcat was the first variable entered, followed by salary;
accordingly, the data would first be sorted by jobcat, then, within each
of the job categories, data would be sorted by salary.
You
can analyze a specific subset of your data by selecting only certain cases in
which you are interested. For example, you may want to do a particular analysis
on employees only if the employees have been with the company for greater than
six years. This can be done by using the Select Cases menu option, which
will either temporarily or permanently remove cases you don't want from the
dataset. The Select Cases option is available under the Data menu
item:
Data
Select Cases...
Selecting
this menu item will produce the following dialog box. This box contains a list
of the variables in the active data file on the left and several options for
selecting cases on the right.
Selecting
one of these options will produce a second dialog box that prompts you for the
particular specifications in which you are interested. For example, selecting
the If condition is satisfied option and clicking on the If
button (as was done in the example) results in a second dialog box, as shown
below. The portion of the dialog box labeled Output gives you the option
of temporarily or permanently removing data from the dataset. The Filter
option will remove data from subsequent analyses until the All Cases
option is reset, at which time all cases will again be active and used in
further analyses. The Copy option
will save the selected cases to a new dataset. The Delete option will
remove unselected cases from the working dataset; be very careful with this
option, because if the dataset is subsequently saved, these cases will be
permanently deleted. Here, we have chosen to use the Filter option.
Clicking
on the If button opens the Select Cases: If dialog box. Here, we
select all of the cases in the dataset that meet a specific criterion:
employees that have worked at the company for greater than six years (72
months) are selected. After this selection has been made, subsequent analyses
will use only this subset of the data. Because we selected the Filter
option in the previous dialog box, SPSS will indicate the inactive cases in the
Data Editor by placing a slash over the row number. To select the entire
dataset again, return to the Select Cases dialog box and select the All
Cases option.
You
may sometimes want to print a list of your cases and the values of variables
associated with each case, or perhaps a list of only some of the cases and
variables. For example, if you want to visually examine the gender and minority
status of each person in your dataset, you can generate a list of only these
variables in the Output Viewer. This can done by using the Summarize Cases
menu option, available under the Analyze menu item:
Analyze
Reports
Case Summaries . . .
The
above example requests a listing of each person’s gender and minority status.
The option Limit cases to first has
been checked, which allows you to request a listing of only the first 10 cases.
If you sorted the dataset earlier in this tutorial, then the Output Viewer
would show this table:
Conclusion
We
hope you found this introductory SPSS class enjoyable and useful! To explore
further topics in SPSS, you may wish to consult the following resources:
Our
SPSS FAQs
(http://www.utexas.edu/its/rc/answers/faqs.html): Scroll down to the bottom of
the FAQ list to find over fifty
answers to SPSS questions we've answered for the
Our
SPSS tutorials (www.utexas.edu/its/rc/tutorials/): Many of the topics
covered in this course are included in our online SPSS tutorials; however, the
online tutorials also contain additional information not covered in this
course, such as how to run a General Linear Model.
The SPSS website (www.spss.com):
The SPSS site contains a variety of useful information, including the SPSS
Answer Net (which you can search for technical FAQs) and listings of SPSS
macros and algorithms.
Garson’s
Statnotes (www2.chass.ncsu.edu/garson/pa765/statnote.htm):
Includes in-depth discussions of a variety of introductory, intermediate, and
advanced statistical topics; most are illustrated using SPSS, including
annotated SPSS output.
The University
of
And,
finally, University of Texas students, faculty, and staff can receive
a limited amount of free consulting from us (see www.utexas.edu/its/rc/services/free_consulting.html);
professors on grants, researchers within the University of Texas system, and
other research bodies can receive intensive contractual assistance from our
group as well (see www.utexas.edu/its/rc/services/contracts.html).
If
you have any questions or comments, please feel free to email us at stats@its.utexas.edu.