- Welcome
- Important notice
- Site guide + Search box
- Dedication
- My personal pantheon (of the great and the good in survey research)
- Acknowledgments
- About the author
- About this site
- Recent and planned activities
- Textbooks
- 1: Survey Analysis Workshop (SPSS)
- 1a: Statistical concepts and methods
- 1b: Teaching with Survey Data
- 1c: Developing research projects using survey data
- 1d: Workshop and presentations for ASSESS (SPSS users in Europe)
- 2: Survey Research Practice
- 2a: Survey Research Methodology, Practice and Training
- 2b: Major survey series
- 3: Subjective Social Indicators (Quality of Life)
- 4: Survey Unit, Social Science Research Council (UK)
- 5a: Polytechnic of North London (1976-1992)
- 5b: Survey Research Unit (1978-1992)
- Village life in Normandy
- Contact
Block 3: Analysing two variables (and sometimes three)
[Page last updated: 25 July 2016]
Up to now all my tutorials are about familiarisation with the language of survey research and survey analysis, covering the mechanics of basic data capture, processing, management and descriptive analysis using tabulations and selected charts. SPSS is in a sense incidental, but it’s what I’ve been using since 1972 and there’s still nothing to touch it (including R, Stata, SAS and other software).
The next stage will introduce much more logic and the notion of dependent, independent and test variables, but in the context of social policy and/or social theory, and still using only tabulation. Inferential statistics and hypothesis testing will follow much later, once users have grasped the basic concepts and logic and acquired at least a modicum of confidence and technical skill in handling data and a grasp of SPSS syntax. To date I’ve avoided anything with equations in (there's one for calculating chi-square at the end of 4.2.1 Income differences – Statistical significance) but have already felt the need to add a paragraph or two on statistical concepts, with links to some very nice sites (one non-SPSS) for beginners.
A number of files for Block 3 are still in their original 1990 or 1991 format (ie WordStar 4, VMS, EDT and with syntax for interactive SPSS-X 4 on a Vax cluster: all the output is in lineprinter format) It's
interesting to see how the syntax and output formats have changed. Some sample output dates from the late 1980s and early 1990s using SPSS -X releases 4 to 8 on a Vax mainframe: all jobs need re-running with SPSS 21. This is very time-consuming, but I'll get them converted and uploaded as quickly as I can. The numbering system for the files below is subject to change, but the numbers in the downloaded document titles may be different. Don't worry: the links are to the correct files. .
3.1 Two variables (CROSSTABS)
Joint frequency distributions of two variables displayed in contingency tables. Dependent and independent variables. Rules for percentaging.
3.2 Three (or more) variables
Introducing a third variable. Controlling for test variables. Elaboration.
3.3 Multiple response
Explanation of multiple response questions, examples from real surveys, and exercises in analysis using
SPSS command MULT RESPONSE.
3.4 Conditional data transformations (IF and DO IF)
3.5 Derived variables (COUNT and COMPUTE)
Set of tutorials (with fully worked examples using data from a real survey of 15 year-olds) on the use of COUNT and COMPUTE to construct scores from simple attitude scales designed to measure "attachment to the status quo" and "sexism".
Back to: page Block 2: Analysiing one variable
Back to: page Block 1: From questionnaire to SPSS saved file
Back to: page Summary guide to SPSS tutorials
Back to: page Detailed guide to SPSS tutorials
Up to now all my tutorials are about familiarisation with the language of survey research and survey analysis, covering the mechanics of basic data capture, processing, management and descriptive analysis using tabulations and selected charts. SPSS is in a sense incidental, but it’s what I’ve been using since 1972 and there’s still nothing to touch it (including R, Stata, SAS and other software).
The next stage will introduce much more logic and the notion of dependent, independent and test variables, but in the context of social policy and/or social theory, and still using only tabulation. Inferential statistics and hypothesis testing will follow much later, once users have grasped the basic concepts and logic and acquired at least a modicum of confidence and technical skill in handling data and a grasp of SPSS syntax. To date I’ve avoided anything with equations in (there's one for calculating chi-square at the end of 4.2.1 Income differences – Statistical significance) but have already felt the need to add a paragraph or two on statistical concepts, with links to some very nice sites (one non-SPSS) for beginners.
A number of files for Block 3 are still in their original 1990 or 1991 format (ie WordStar 4, VMS, EDT and with syntax for interactive SPSS-X 4 on a Vax cluster: all the output is in lineprinter format) It's
interesting to see how the syntax and output formats have changed. Some sample output dates from the late 1980s and early 1990s using SPSS -X releases 4 to 8 on a Vax mainframe: all jobs need re-running with SPSS 21. This is very time-consuming, but I'll get them converted and uploaded as quickly as I can. The numbering system for the files below is subject to change, but the numbers in the downloaded document titles may be different. Don't worry: the links are to the correct files. .
3.1 Two variables (CROSSTABS)
Joint frequency distributions of two variables displayed in contingency tables. Dependent and independent variables. Rules for percentaging.
3.2 Three (or more) variables
Introducing a third variable. Controlling for test variables. Elaboration.
3.3 Multiple response
Explanation of multiple response questions, examples from real surveys, and exercises in analysis using
SPSS command MULT RESPONSE.
3.4 Conditional data transformations (IF and DO IF)
3.5 Derived variables (COUNT and COMPUTE)
Set of tutorials (with fully worked examples using data from a real survey of 15 year-olds) on the use of COUNT and COMPUTE to construct scores from simple attitude scales designed to measure "attachment to the status quo" and "sexism".
Back to: page Block 2: Analysiing one variable
Back to: page Block 1: From questionnaire to SPSS saved file
Back to: page Summary guide to SPSS tutorials
Back to: page Detailed guide to SPSS tutorials