ANNEX A -SUPPLEMENTARY NOTES ON THE REGRESSION analysis
A.1 The regression models used in this report have been composed in order to examine which of the selected measures of advantage and disadvantage appear to be more important in determining behaviours of mothers with young children in general and young mothers and lone mothers in particular. They have not been designed, as in many other research papers which use regression, to test or support a theoretically-based hypothesis. As such, we do not expect the models to have good predictive efficacy because they are likely to omit many measures which are important determinants of the behaviours being examined.
A.2 In chapter three, all of the regression models included the following independent variables: family type, household income, mother's educational qualifications, mother's employment status, mother's socio-economic classification 6, age of mother at birth of cohort child, sole reliance on benefits and tax credits for income, housing tenure and area deprivation 7. Models which examined attendance at ante-natal classes also included a measure of whether or not the respondent was a first-time mother. In chapter four, those models which were restricted to data on mothers aged under 25 did not include age of mother at birth of cohort child as an explanatory variable, and the models which were restricted to data on lone parents did not include family type. Further, this technique requires that the outcome variable of interest has two-categories therefore for each model, all cases were coded to reflect whether or not they fell into the category of interest.