The course requires no previous knowledge of statistics or experience with SPSS. That being said, previous exposure to basic statistical concepts and the SPSS interface will allow for an easier understanding and possibly fuller comprehension of the topics covered within the course. As such, the course is suitable for both, those without such experience as well as those seeking to refresh their knowledge.
SPSS is one of the most widely used statistical software programs in the world. A main reason for this is its intuitive interface that allows users to learn how to conduct statistical analyses within very little time. Of course, SPSS can not compensate for the need to understand the statistical methods that are being executed by the program. However, using the easy-to-use point-and-click interface is a rewarding experience after the often painstaking process of learning the basics of statistics. In addition, SPSS offers excellent data editing capabilities that allow for quick entry and manipulation of data.
Within the three days of the course, participants are introduced to the SPSS interface and learn how to enter, manipulate, present, and analyze data. Throughout the course many statistical concepts are reviewed before we proceed to the implementation within the software. Data presentation focuses on usage of tables and graphs. Data analysis covers basic operations (univariate, bivariate), and if time permits more advanced analyses (multivariate) are introduced. The course consists of many small lectures (elaborating concepts and applications) that are complemented by frequent practical exercises. Active participation at all times is encouraged.
The first day of class begins with a review of basic concepts in statistics. We discuss the most common data sources in the social sciences and how they relate to research design. Then, the structure and terminology used to describe standard data sets is introduced (row-column-structure, unit/level of analysis, levels of measurement). During the second half of the day, we begin working with SPSS. First, the program’s interface (Data/variable viewer, output viewer) is introduced. Then, we learn how to enter, code, edit, and transform data. Through various exercises all participants get a first feeling of the software and at the end of the day should be able to enter their own data and to perform subsequent transformations (including the recoding of existing variables and setting up new variables). As time permits, we might also cover further data operations such as aggregating data or merging different data sets.
During the second day, we focus on data presentation, including descriptive statistics and data visualization. We again begin with a review of some basic statistical concepts (measures of central tendency and variation, frequencies). After that we learn how these concepts are implemented in SPSS and how to produce respective outputs. In the process of doing so, participants are also introduced to how data is read into SPSS and subsequently saved; this is shown for different data formats including the standard SPSS (sav) and some others (i.e. csv, xls). The second half of this day introduces how different kinds of tables and graphs can be produced from SPSS. Again, we discuss some basic issues first and then learn how to implement them in SPSS. Participants will learn how to set up and edit univariate and bivariate tables (frequency tables, contingency tables) and graphs (including bar charts, histograms, pie charts, scatter plots).
On the third and last day, we learn how to conduct first statistical analyses in SPSS. This day will be the most demanding day as we move from descriptive statistics to the world of inferential statistics. Throughout the day we learn how to test different kinds of relationships between variables and observations, such as tests of independence, differences in means, and correlations. In particular, chi-square tests, different kinds of t-tests (i.e. paired, independent), and correlation tests (bivariate, partial) are introduced. As during the first two days, we first review the statistical concepts and procedures that we subsequently execute in SPSS. The focus is on the interpretation and presentation of test results. As time permits and depending on interest, we will also look into some more advanced statistical applications such as multivariate regression or ANOVA.
There are no mandatory readings for this class. That being said, participants are encouraged to consult one of the recommended textbooks (or one of their choice) as this will greatly facilitate their learning experience in class. Reviewing basic statistical concepts before class should allow everyone to easily follow through the material presented in class and to quickly utilize the full capacity of SPSS. This is especially true for the third day, as due to the complexity of the tests we limit ourselves to understanding their underlying intuition, but they cannot be explained in full detail. For participants with previous knowledge this should suffice as a refresher. However, those without such knowledge should consult some of the recommended reading or their preferred statistics textbook to fully comprehend the concepts and procedures discussed in class.
At the end of the course, participants will have learned how to execute a wide set of data operations in SPSS from entering new data to administering large-scale data sets. Beyond that, participants will be able to compactly present their data in various ways as tables or graphs, and understand how to adjust them to their individual needs. Last but not least, participants will learn how to perform basic statistical analyses within SPSS. After the course, participants should have gained a good working knowledge of SPSS that allows them to quickly explore more advanced operations within the program not covered in this course.