Abstract
This note examines the purported impact of conventional socioeconomic and social environment factors on annual, state-level suicide rates. Results from an inductive fixed-effects (covariance) analysis, of state-level time-series/cross-section data for the period 1985-95, do little to support Durkheim's social causes hypothesis that aggregate socioeconomic factors matter in explaining state suicide rates. A possible source of heterogeneity-aggregation bias is identified raising questions surrounding past inferences made in aggregate suicide research. The data and empirical method support a mounting sentiment of an abiding ecological fallacy in the suicide literature. Implications of this investigation call for a shift in research focus and method to a smaller unit of analysis (for example, individual-level, controlling for key social processes).
Get full access to this article
View all access options for this article.
