Introduction to SPSS and how to use it
SPSS is an acronym for “Statistical Package for Social Science” and is a Windows-based program that is used to perform different tasks like, data entry, analysis and further presentation of results through tables and graphs. SPSS as software is available to handle large amounts of data in order to perform the analysis. The software finds its application most in terms of Social Sciences and the Business World.
The software can be used to conduct the following operations:
- Data Transformation
- Data Examination
- Descriptive Statistics
- Reliability Tests
- Correlation Tests
- Regression Tests
- Factor Analysis and many more
SPSS has scores of statistical and mathematical function with a flexible data handling capability. It can read a number of data, i.e. numeric, alphanumeric, binary, dollar, date, time, and further it also has data manipulation utilities.
- Click of the SPSS Shortcut on the desktop, by simply putting the cursor on the icon and double-click the left mouse button.
- However, if you do not have a shortcut on the desktop then, click the Start button on your desktop, and Click on All Programs. Search for SPSS 19.0 and Click with the left mouse button to open.
How to work on SPSS?
- Once the SPSS file (new file within the software) is open, a new dialogue box opens, which gives user 6 options to choose from.
- Run a Tutorial: which allows the user to run SPSS tutorial which explains basic tools and tests which can be used within SPSS.
- Type in data: When the user needs to conduct a new analysis based on a survey, they need to choose this option.
- Run an existing query: When the user wants to open an existing query and run it in the SPSS software along with data on it which may have been obtained from other sources or your friend.
- Create a new query using Database Wizard: This provides the user with an opportunity to create a new query or new data set using a formulated database wizard
- Open an Existing data: When the user wants to open a data saved in a folder and run it on software
- Open another type of file: This is similar to option “e” only here one can open a different type of files like MS Excel file.
Generally, we select “TYPE IN DATA” or “CANCEL”.
- Now here for this example, the user will choose, Type in Data in order to develop new query on SPSS, which is mostly applicable since we need to develop new query with every new statistical assignment. Once you select that there will be two views i.e. DATA VIEW and VARIABLE VIEW.
- DATA view: It displays the actual data (i.e. responses from respondents who participated in the survey) of the variables which you have created (See Figure 2 given below)
- VARIABLE view: It displays the variables which are defined by name, type, size, alignment, decimal including other information (See Figure 3 given below)
Further, what each of these parameters signifies is described in Figure 4 given below:
- Name: Name of the variable. For example, in the case of demographic factors, “name” will be Age, Income, Gender, etc.
- Type: Indicates if the data is Numerical, String (alphabet), date, currency, etc. “age” is represented in number. Usually, since we do coding/ calculations for all the questions in a questionnaire, we do not use the “String” option. We only use “Numerical” option. Therefore for example, even if “Gender” is ideally “M’ or “F”, we will code them as “1” and “2” respectively for calculation purposes.
- Width: Defines the Width of the value in the “Data View” sheet of SPSS. The width will impact the representation of really big words such as “arachnophobia” or “cardiovascular disease” in the tables or graphs. Generally, we keep the Width at “8”.
- Decimals: Defines up to how many decimal levels the value is to be considered. Usually, it should be 0. Only in case of complex scientific experiments where even .001 difference in result matters, we define the decimal points.
- Label: Signifies the name or label of the variable (“Age of respondent”, “gender of respondent”, etc.). The exact label described in this column will appear in the tables/ graphs.
- Values: The Coded value of the variable for each question is signified. For example, if one question in the questionnaire has 5 options (Strongly agree, Agree, Neutral, Disagree, Strongly Disagree), then they will be represented as the following values:
- Strongly agree (Label)= 1 (Value)
- Agree= 2
- Neutral= 3
- Disagree= 4
- Strongly Disagree= 5
- Missing: There could be instances within data, where the respondent has not replied due to one or more reasons like “Not applicable” or “Don’t know”, in such cases it is important to define the missing value (i.e. blank in the datasheet/view). Steps to define Missing value have been explained in detail in Article: Introducing Data. However, in most of the cases, these sections are untouched in most of the studies.
- Columns: Defines the width of the column in Data view. This is generally left untouched.
- Align: Signifies the alignment in the box in Data View. This can be left, right or centre.
- Measure: Options to choose from, scale, ordinal and nominal. For details about the difference between all the 3, refer to the article (Difference between Ordinal, Nominal and Scale).
This article presented the basics of what SPSS is actually about. In the next article, Introducing Data, I will be discussing how the SPSS sheet is filled for the new query.