Getting Started With SPSS Statistics

I am using IBM SPSS Statistics 27 for this tutorial. This post serves two main objectives:

• 1. Acquainting you with the SPSS Statistics Data Editor
• 2. Guiding you through the steps of creating a basic SPSS Statistics data file

Data Set Overview

In the Variable View tab, you define characteristics for each variable in your data file. These include the variable’s:

• Name (no spaces or special characters, can’t start with a number)
• Type (usually Numeric)
• Width (default is “8”)
• Decimals (decimal points in Data View)
• Label (detailed description not limited like Names)
• Values (for Value Labels in categorical variables)
• Missing (numeric codes for missing data)
• Columns (characters/numbers displayed in Data View)
• Align (Left, Right, or Center)
• Measure (Scale, Ordinal, or Nominal, with Scale covering interval and ratio data)
• Role (predefined roles for sorting in SPSS dialogues, default is Input)

I am going to use a student satisfaction survey that includes:

• Gender: Male or Female.
• Age
• Course of Study: Physiotherapy, Psychology, Speech Therapy, Nursing, Public Health, Occupational Therapy, Biomedical Sciences.
• How much do they enjoy the course?
• How easy is the course to get good grades?

1. This study data is exclusively consists of numerical values. Numbers will be employed to denote various gender and course of study categories. You can utilize labels to offer more comprehensive descriptions of variables than what the Name field allows. If you include a variable label, it will be utilized consistently in your SPSS Statistics output.
2. Here, you’ll find the definitions for the values (or codes) we employ to depict the levels of each categorical variable. More detailed discussions can be found on the next page.
3. Occasionally, participants in research may skip or choose not to respond to specific questions, as seen with our second participant who opted not to disclose their age. Alternatively, recording equipment may malfunction, leading to some data becoming unintelligible. In such situations, we can utilize Missing Values Codes, which are explained in greater detail on the following page. Simply tap the Measure cell and choose the right measurement scale from the drop-down menu.

Value Labels

In SPSS Statistics, numeric values are commonly used to signify different levels of categorical variables such as gender or course of study. These codes are defined in the Value Labels dialogue. To access it, select a Values cell in the Variable View, then click . Enter the number for the first category and its name, then click Add. Repeat for other categories and click OK to close the dialogue. In this example, values “1” through “7” represent the seven courses our student participants are enrolled in.

Missing Values

In research, encountering missing data is inevitable due to various reasons like participants skipping questions or equipment failures. To address this, Missing Values codes are used to signify such instances. One approach is using a single numeric code for all types of missing data, or up to three unique codes to differentiate reasons (e.g., refusal to answer versus equipment failure). Any numeric code outside the actual data range can be used, and “9” is chosen here to avoid confusion with real data, ensuring it doesn’t overlap with participant responses or variables like gender in a 5-point rating scale.

Appendix

Data Set Summary

Strongly Disagree	1
Strongly Agree	5

ID	Question 1	Question 2	Question 3	Question 4	Question 5
1	Male	17	Speech Therapy	5	5
2	Male	N/A	Physiotherapy	4	3
3	Female	18	Occupational Therapy	5	4
4	Male	17	Physio	4	4
5	Female	20	Physiotherapy	4	4
6	Female	21	Psychology	3	3
7	Female	19	Speech Therapy	3	2
8	Male	18	Speech Therapy	2	1
9	Male	19	Nursing	3	3
10	Female	21	Public Health	5	4
11	Female	24	Occupational Therapy	4	3
12	Female	17	Occupational Therapy	1	1
13	Female	38	Nursing	3	3
14	Male	19	Occupational Therapy	4	5
15	Female	18	Occupational Therapy	5	4