Copyright Angela D’Auria Stanton, Ph.D. All Rights Reserved. Page 1 Opening a Data File in SPSS To open an existing SPSS file: 1. Click File Î Open Î Data. Go to the appropriate directory and find the name of the appropriate file. SPSS defaults to opening SPSS data files with the .sav extension. The SPSS Data Editor resembles the spreadsheet-like structure of Excel. The Data Editor window consists of: • Row: A horizontal collection of information that represents a case or an observation. For example, each individual respondent to a questionnaire is a case. It is the same as a record in Access. • Column: A vertical collection of information that represents a variable or characteristic being measured. For example, each item on a questionnaire is a variable. It is the same as a field in Access. • Cell: This is the intersection of a row and a column. It is where a value for a particular variable for a particular case is entered. Cells contain only data values. Unlike spreadsheet programs, cells in the Data Editor cannot contain formulas. Defining Variables in SPSS You can have SPSS define the variables for you, or preferably, you can do the defining yourself. By doing it yourself, you have much more control over the way things look and work. Having SPSS Define Variables If you enter data into a cell without defining a variable, SPSS will automatically name the variable. If the variable is in column 1, the variable name assigned would be var00001; if the variable name is in column 4, the name assigned would be var00004; etc. You should also note that right below the main menu in the upper left-hand corner of the Data Editor is an indicator of what cell is being highlighted. For example, in the figure below, you can see that 1:VAR00005 represents row 1, variable 5.Copyright Angela D’Auria Stanton, Ph.D. All Rights Reserved. Page 2 Defining SPSS Variables Yourself By custom defining variables yourself, it allows you for greater flexibility, such as: • providing your own names for variables, • providing descriptive labels • assigning special formats such as text or date or time. To define a variable name, make sure the Data View window is active and follow these steps: 1. Click on the Variable View tab at the bottom of the screen. 2. Name: Enter a name for the variable. The following rules apply to variable names: • The name you assign to a variable can have no more than 8 characters. • It must begin with a letter. The remaining characters can be of any letter, any digit, a period, or the symbols @, #, _, $. • Variable names cannot end with a period. • Variable names that end with an underscore should be avoided. • Blanks and special characters (for example, !, ?, ‘, and *) cannot be used. • Each variable name must be unique; duplication is not allowed. Variable names are not case sensitive. The names NEWVAR, NewVar, and newvar are all the same. 3. Type: The default variable type is Numeric. If you click within the Type cell, you will see the Define Variable Type dialog box (as shown below) You can choose from one of the following variable definitions, to include: • numeric (e.g., 3435.45) • comma (e.g., 3,435.45) • dot (e.g., align such as 3.43545) • scientific notation (e.g., 3.4E+03) • date (e.g., 12-FEB-2000) • dollar (e.g., $3,435.45) • custom currency (as you design it) • string (text such as William, JMU, 201 Friday Street, etc.) You can also set the width of the field as well as the number of decimal places you wish to use.Copyright Angela D’Auria Stanton, Ph.D. All Rights Reserved. Page 3 4. Label: The Label option allows you to provide descriptive variable labels (a variable label is makes it much easier to read your SPSS output. SPSS, by default, does not provide variable labels. A variable label allows you to more adequately describe a variable. It is hard to describe a variable in the 8 characters used in a variable name. A variable can be up to 256 characters long and these descriptive labels are displayed in output. To insert a variable label, click in the Label cell and type in your variable label. 5. Values: You can also assign descriptive value labels for each value of a variable. This is particularly useful if your data file uses numeric codes to represent non-numeric categories (for example, where a 1 = Male and a 2 = Female). Value labels can be up to 60 characters long. To assign or change a variable label, follow these steps: • Click inside the Values cell. • Click on the small gray box in the right corner. You will now see the following Value Labels box: • Enter a value for the variable. This is what will appear in the Data View window, such as 1, 2, or 3. • Enter the value label for the value. • Click Add. The value label will now appear. Now the same steps need to be taken to apply a label for the next value. • Click OK when you have added all of the labels for the variable and the new labels will take effect. 6. Missing: If you click inside the Missing cell, you can tell SPSS how to deal with the missing values that you specify. The No missing values option treats all values as being valid, such that no missing values are present in the data file (this is the SPSS default). That is, only blanks are treated as missing variables in the data file. The Discrete missing values option allows you to enter up to three values for a missing variable. The Range of missing values option allows you to define a range and include high and low values as missing. Finally the Range plus one discrete missing value option will identify as missing all the values between the low and high values you identify, plus one additional value outside the range. 7. Column: Column lets you control the width of the columns in the Data View Column widths can also be changed in the Data View by clicking and dragging the column borders.Copyright Angela D’Auria Stanton, Ph.D. All Rights Reserved. Page 4 8. Align: Align lets you line up the contents in a cell. You can set this up as left, right, or center. 8. Measurement: You can specify the level of measurement as scale (numeric data on an interval or ratio scale), ordinal, or nominal. Nominal and ordinal data can be either string (alphanumeric) or numeric. Measurement specification is relevant only for: • Chart procedures that identify