Help
SPSS is a general-purpose statistical computing package sold by SPSS, Inc., which was first released in 1968. It is widely used by social scientists (the name originally meant Statistical Package for the Social Sciences) and is also used extensively in other areas including health research, business, and education. SPSS might be characterized as offering capabilities somewhere between Minitab and SAS: it is more complex and offers many more analytical possibilities than Minitab, but is more limited than SAS. On the other hand, many beginners find SPSS easier to learn than SAS, as SPSS offers both syntax and a menu interface, offers a spreadsheet interface as its default, and is superior in data formatting and documentation.
SPSS can import and export data in many formats and in nonrectangular configurations; however, the data set is always translated to an SPSS rectangular data file, known as a system file (which uses the extension *.sav). Metadata (information about the data) such as variable formats, missing values, and variable and value labels are stored with the data set. Two views are offered of the data: the spreadsheet-like Data View (Figure B-3) and the Variable View (Figure B-4), which shows the metadata.You can type directly into either window, so data may be entered directly into the Data View, and variable names, labels, and so on into the Variable View window.
SPSS can be operated entirely through syntax (computer code), which may be typed directly into the syntax window, or written using any text or word processing program and pasted into the syntax window (Figure B-5). SPSS syntax files are stored with the extension *.sps.This is a great advantage over programs that are entirely menu-driven because the syntax preserves a record of how an analysis was performed, can be shared with others (for instance, by emailing the text file to a collaborator), and can be reused (for instance, to produce daily or weekly reports). SPSS syntax is easy to write and interpret (at least relative to many other programs!), as should be evident in the code excerpt in Figure B-6. You can probably guess what this code is doing without ever having used SPSS.
Figure B-3. SPSS Data View
Figure B-4. SPSS Variable View
Here's a hint: lines beginning with * are comments, i.e., notes to the programmer rather than executable lines of code. The actual program recodes the continuous variable exercise into the dichotomous variable exerc_cat, adds labels to the new variable and its values, and creates a cross-tabulation table of the two variables to check that the coding was executed correctly.
However, some people prefer to use the menu interface, and almost any statistical analysis or data management function in SPSS can be accomplished by either means. I prefer to think of the menu system as an alternative way of generating code that can be saved in a syntax file. This lets me enjoy the best of both worlds: I can use the menus to write the syntax for an unfamiliar command, then save the syntax as a record of the analysis performed, which I can also reuse or alter if I desire.The second paragraph of syntax in Figure B-5 was created this way: the tell-tale sign of menu-generated syntax is the capitalized commands (RECODE, VARIABLE LABELS, etc.). To generate syntax using the menu system, make all relevant selections in the menu command interface, then select “Paste” rather than “OK” as the final step, as shown in Figure B-6. This results in the syntax being saved in a syntax file, or appended to an existing syntax file, if one is already open.On the other hand, if you simply want to run an analysis and don't care about saving the syntax, click “OK” instead and the analysis executes immediately. The statistical results are the same either way.
Figure B-5. SPSS syntax window
Figure B-6. Using the SPSS menu system to generate syntax
It would be impossible in this brief space to enumerate all the types of analyses available; an overview of SPSS capabilities can be found on the SPSS web page (http://www.spss.com). It is an expensive program beyond the range of most individuals, but educational prices are lower and often universities obtain a site license so they are able to provide students and employees with access to SPSS for free or at much lower cost.
For someone who wants to learn SPSS using the menu system, a useful series of books written by Marija Norusis have been published by SPSS, Inc.: these include the SPSS 15.0 Guide to Data Analysis (2007), the SPSS 15.0 Statistical Procedures Companion (2006), and the SPSS 15.0 Advanced Statistical Procedures Companion (2007). Note that slightly older versions of these books may also be useful, particularly at the beginning level, since many of the changes in new versions of SPSS involve adding new programs rather than changing the more basic procedures. For those wishing to learn SPSS syntax, books available include Boslaugh's An Intermediate Guide to SPSS Programming: Using Syntax for Data Management (Sage) and Levesque's SPSS Programming and Data Management: A Guide for SPSS and SAS Users (which may be downloaded in PDF format or ordered in book format from http://www.spss.com/...gement_book.htm). Tutorials, sample code, and guidance about using SPSS are available from a number of web sites: two of the best are located at UCLA (http://www.ats.ucla.edu/STAT/spss/) and Texas A & M University (http://www.stat.tamu.edu/spss.php).
Need to learn statistics as part of your job, or looking for help to pass a statistics course? Statistics in a Nutshell is a clear and concise introduction and reference for anyone with no previous background in the subject. You get a firm grasp of the basics before moving into increasingly advanced material. Each chapter presents you with easy-to-follow descriptions illustrated by graphics, formulas, and plenty of solved examples.
