07 - 11 - 2014
Save $25 on orders of $100+, $50 on orders of $150+, and save $100 on orders of $250+ by entering code AFF2014 at store.elsevier.com!
Main menu
Orphus system

Introduction to SPSS

Before starting any statistical analysis, experimental data should by typed or imported to the statistical packet.

There are two stages in creating a new SPSS data file:

1) Defining variables;

2) Entering the data.

Defining variables is an important process as it influences next stage in performing statistical analysis. After the variables have been defined, only then the data should be added.

Data must be arranged in a table view where lines correspond cases (objects used in a study) and columns correspond variables (properties of objects measured in an experiment). In our example cases are 24 bacterial isolates, while properties – characteristics of isolates, such as species, and MICs of oils against isolates.

SPSS has two main windows – Data Editor and Data Output. The Data Editor includes Data View and Variable view, they can be switched by clicking Data View and Variable View tabs in the lower left corner of the Data Editor, and also by keyboard shortcut keys Ctrl+T (for more information see http://publib.boulder.ibm.com/infocenter/spssstat/v20r0m0/index.jsp and http://www.calstatela.edu/its/docs/pdf/pasw17p1.pdf).

Data Editor

First, variable names based on the research should be chosen. Variable names must begin with a letter, e.g. V1 is allowed but 1V is not. If variable names are not assigned, SPSS will assign default names but they are usually not recognizable. Second, the type should be specified for each variable.

Both type and measure will be important during the selection of statistical criteria. The role of a variable (last column) is especially important in the prognosis analysis, when we select, which variable is the target of the prognosis and which variables are independent predictors.

If the data are typed in another software, for example, in MS Excel, they can be opened by clicking the Open button in the Tool Bar. Sometimes this way is more convenient because names of variables and all other their properties are filled automatically. Data for our example we already typed in MS Excel so we will simply open .xls file:

Data from MS Excel

1) Click the Open button on the Data Editor toolbar. The Open Data dialog box opens.

2) In Files of type click triangular  button and from opened list of file types choose Excel (*.xls, *.xlsx, *.xlsm).

3) Locate “Example.xls” file and click Open. After this Opening Excel Data Source dialog opens.

Variable names

4) Select Read variable names from the first row of data check box, this will fill variable names and other properties in the Data Editor automatically.

5) Click the OK button.

After opening data from the MS Excel file, we will have the following dataset: MICs of two essential oils, tea tree oil and thyme oil, without antibiotic gatifloxacin and in the presence of gatifloxacin against clinical isolates of bacteria belonging to two species, E. faecalis and E. coli.

The first example

Simultaneously with the Data Editor, the Output Viewer also appears. In this window we can see the results of the analyses and also we can choose the format of the output.

blog comments powered by DISQUS back to top