Question 1: Using SPSS, cross-tabulate housing tenure by prematurity and carry out a chi-squared test.
We choose Analyze, Descriptive Statistics, Crosstabs. Put the variable 'Housing tenure' into Row(s): and 'Prematurity' into Column(s):. Click Statistics, Chisquare, Continue. Click OK.
You should get the case processing summary and then the following:
| Housing tenure * Prematurity Crosstabulation | ||||
|---|---|---|---|---|
| Count | ||||
| Prematurity | Total | |||
| Term | Preterm | |||
| Housing tenure | Owner-occupier | 849 | 50 | 899 | 
| Council tenant | 229 | 29 | 258 | |
| Private tenant | 164 | 11 | 175 | |
| With parents | 66 | 6 | 72 | |
| Other | 36 | 3 | 39 | |
| Total | 1344 | 99 | 1443 | |
| Chi-Square Tests | |||
|---|---|---|---|
| Value | df |  Asymp. Sig.  (2-sided)  | |
| Pearson Chi-Square | 10.495a | 4 | .033 | 
| Likelihood Ratio | 9.466 | 4 | .050 | 
| Linear-by-Linear Association | 1.894 | 1 | .169 | 
| N of Valid Cases | 1443 | ||
|  a	2 cells (20.0%) have expected count less than 5. 
 The minimum expected count is 2.68.  | |||
As often happens, SPSS prints out more than you need. We should ignore the likelihood ratio (beyond the scope of our course) and the linear-by-linear association (not appropriate for this table).
Back to Exercise: Premature delivery and housing tenure.
To Applied Biostatistics index.
To Martin Bland's M.Sc. index.
This page maintained by Martin Bland. 
Last updated: 10 November, 2006.