- Welcome
- Important notice
- About the author
- About this site
- Site guide + Search box
- Dedications
- Acknowledgments
- My personal pantheon (of the great and the good in survey research)
- Recent and planned activities
- Textbooks for Research Methods and Data Analysis
- 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
- Origins of the British Crime Survey
- British Crime Survey
3.1 Two variables (CROSSTABS)
[Page last updated 14 Sep 2017
Joint frequency distributions of two variables displayed in contingency tables.
Dependent and independent variables: rules for percentaging.
3.1.1 Introduction to tabulation
Recommended reading
3.1.2 Analysing two variables [Revised 12 Sep 2017]
Preliminary reading: progression from frequency counts via conditional frequency counts to joint
frequency counts [contingency tables]
3.1.3 Contingency tables from SPSS
Tabulation of two variables. Introduction to the CROSSTABS command. The SPSS CROSSTABS command creates 2-way contingency tables for two variables, and nested sub-tables when controlling for one or more test variables. It also provides percentages based on row, column and global totals, a range of measures of statistical (non-) association and various controls over table content and format.
The tutorials below are very much beta versions as of 12th July 2013. Getting all the reciprocal hyperlinks into uploaded files is very complex and doesn't always work, despite extensive editing. You may need to come back to this page to access some files.
They address the research question:
Is there a difference between the earnings (from paid work) of men and women? What other variables might account for differences in earnings? What other variables might affect earnings regardless of gender? What effect do they have by themselves? What happens to any differences in earnings between men and women when controlling for these other variables?
3.1.4.1 Income differences work-through
Previous exercise 2.3.1.6.2 Specimen answer for conditional frequencies homework [Tasks 3 and 4]
produced conditional frequencies of earnings separately for men and women. In this work-through cutting points are chosen to reduce earnings from fourteen categories to three and save them in a derived variable. The new variable is then tabulated by sex. Candidates for test variables are chosen and their distributions examined.
3.1.4.2 Income differences - Build working file
Builds up a working file by reading in raw data from raw data file bsa89.txt for dependent, independent and the chosen test variables, adding dictionary information and checking file contents. The syntax and working files are then saved as 3.1.4.2.sps and 3.1.4.2 .sav
3.1.4.3 Income differences for test variables
Uses saved file 3.1.4.2 .sav above; reduces gross earnings from 14 categories to 3 : produces two-way contingency tables to display distributions of earnings within categories of the test variables. The syntax and working files are then saved as 3.1.4.3.sps and 3.1.4.3.sav.
3.1.4.4 Income differences - Choose test variables and cutting points
Decide which test variables to use and choose cutting points; recode test variables into derived variables with fewer categories; add dictionary information. The SPSS files are saved as 3.1.4.4 sps and 3.1.4.4.sav.
3.1.4.5 Income differences for derived test variables
Using file 3.1.4.4.sav produces two-way contingency tables to display distributions of earnings within categories of the derived test variables.
Forward to 3.2: Three (or more) variables
Back to Block 3 : Analysing two variables
Back to Block 2.3 Data transformations
Dependent and independent variables: rules for percentaging.
3.1.1 Introduction to tabulation
Recommended reading
3.1.2 Analysing two variables [Revised 12 Sep 2017]
Preliminary reading: progression from frequency counts via conditional frequency counts to joint
frequency counts [contingency tables]
3.1.3 Contingency tables from SPSS
Tabulation of two variables. Introduction to the CROSSTABS command. The SPSS CROSSTABS command creates 2-way contingency tables for two variables, and nested sub-tables when controlling for one or more test variables. It also provides percentages based on row, column and global totals, a range of measures of statistical (non-) association and various controls over table content and format.
The tutorials below are very much beta versions as of 12th July 2013. Getting all the reciprocal hyperlinks into uploaded files is very complex and doesn't always work, despite extensive editing. You may need to come back to this page to access some files.
They address the research question:
Is there a difference between the earnings (from paid work) of men and women? What other variables might account for differences in earnings? What other variables might affect earnings regardless of gender? What effect do they have by themselves? What happens to any differences in earnings between men and women when controlling for these other variables?
3.1.4.1 Income differences work-through
Previous exercise 2.3.1.6.2 Specimen answer for conditional frequencies homework [Tasks 3 and 4]
produced conditional frequencies of earnings separately for men and women. In this work-through cutting points are chosen to reduce earnings from fourteen categories to three and save them in a derived variable. The new variable is then tabulated by sex. Candidates for test variables are chosen and their distributions examined.
3.1.4.2 Income differences - Build working file
Builds up a working file by reading in raw data from raw data file bsa89.txt for dependent, independent and the chosen test variables, adding dictionary information and checking file contents. The syntax and working files are then saved as 3.1.4.2.sps and 3.1.4.2 .sav
3.1.4.3 Income differences for test variables
Uses saved file 3.1.4.2 .sav above; reduces gross earnings from 14 categories to 3 : produces two-way contingency tables to display distributions of earnings within categories of the test variables. The syntax and working files are then saved as 3.1.4.3.sps and 3.1.4.3.sav.
3.1.4.4 Income differences - Choose test variables and cutting points
Decide which test variables to use and choose cutting points; recode test variables into derived variables with fewer categories; add dictionary information. The SPSS files are saved as 3.1.4.4 sps and 3.1.4.4.sav.
3.1.4.5 Income differences for derived test variables
Using file 3.1.4.4.sav produces two-way contingency tables to display distributions of earnings within categories of the derived test variables.
Forward to 3.2: Three (or more) variables
Back to Block 3 : Analysing two variables
Back to Block 2.3 Data transformations