« Previous | Contents | Next »
Listen
Appendix 2: Description of regression
In the current analysis, backward logistic regression was run using the SPSS logistic regression procedure. Demographic factors were entered into the regression procedure to determine which were predictive of an adult being a carer. The following demographic factors were used: sex; age; marital status; ethnicity; household working status; household type; banded net annual income; local authority area; urban/rural classification; and housing tenure. The variables which proved to be significant were sex, age, marital status, household type, and household working status.
Logistic reqression is used to predict a dependent variable on the basis of continuous and/or categorical independents. The odds of a particular outcome or group membership are modeled. In this case, regression was used to create a model estimating the odds that an adult with particular characteristics will be a carer. Odds ratios are used to compare the likelihood of a subgroup being a carer compared with a 'control group'. The 'control group' was chosen randomly by SPSS. Logistic regression does not have an equivalent to the R-squared that is found in non-logistic regression; and so the p-value is the critical indicator that the model is significant. In this case, the model is statistically significant because the p-value is less than .000.
Table A.1 includes the odds ratio and p-value for each variable (except the control group). Only those variables which were significant in the regression analysis are included in the table. An odds-ratio of 1 means that there is no difference between the two groups, an odds ratio of more than 1 means that the group has greater odds of being a carer than the control group, and an odds ratio of less than 1 means that the group has lower odds of being a carer than the control group. The p-values indicate whether an odds ratio is significantly different from what would have been expected to be found by chance ( i.e. if there was no relationship between the variable and the outcome). A small p-value (less than 0.05) suggests that the true odds ratio is statistically different from 1.
« Previous | Contents | Next »