Using multiple measures of inequalities to study the time trends in social inequalities in smoking

Background: The time trends in social inequalities in smoking have been examined in a number of international publications; however, these studies have rarely used multiple measures of health inequalities simultaneously. Also the analytical approach used often did not account, as recommended, for the changes in the relative distribution of social groups and the changes in the absolute level of the health outcome within social groups. Methods: Data from four successive waves of the Belgian Health Interview Survey (1997, 2001, 2004, 2008) were used to study the time trends in educational inequalities in daily smoking for those aged between 15 and 74 years. We estimated two measures of relative inequalities: the OR and the relative index of inequality; and two measures of absolute inequalities: the population attributable fraction and the slope index of inequality. Three of these measures (relative index of inequality, population attributable fraction, slope index of inequality) account for the change in the relative size of the social groups over time. Results: The four measures of inequality were consistent in showing significant inequalities among educational groups. The time trends, however, were less consistent. Measures of trends in relative inequalities witnessed a small linear increase. However, no substantial over time change was observed with the measures of absolute inequalities. Conclusion: The time trends in social inequalities in smoking varied according to the measure of inequality used. This study confirms the importance of using multiple measures of inequalities to understand and monitor social inequalities in smoking.