Pitfalls in Drawing Policy Conclusions from Retrospective Survey Data: The Case of Advertising and Underage Smoking.

Measuring the impact of potentially controllable factors on the willingness of youth to undertake health risks is important to informed public health policy decisions. Typically the only data linking these factors with risk-taking behavior are retrospective. This study demonstrates, by means of a recent example, that there can be serious pitfalls in using even longitudinal retrospective data to draw conclusions about causal relations between potentially controllable factors and risk-taking behavior. Copyright 2002 by Kluwer Academic Publishers