Tobacco smoking and cannabis use in a longitudinal birth cohort: evidence of reciprocal causal relationships

Abstract

Background: There is evidence of associations between tobacco and cannabis use that are consistent with both a classical stepping-stone scenario that posits the transition from tobacco use to cannabis use ('gateway' effect of tobacco) and with the reverse process leading from cannabis use to tobacco abuse ('reverse gateway' effect of cannabis). The evidence of direct causal relationships between the two disorders is still missing.

Methods: We analysed data from the Christchurch Health and Development Study (CHDS) longitudinal birth cohort using advanced statistical modelling to control for fixed sources of confounding and to explore causal pathways. The data were analysed using both: (a) conditional fixed effects logistic regression modelling; and (b) a systematic structural equation modelling approach previously developed to investigate psychiatric co-morbidities in the same cohort.

Results: We found significant (p<0.05) associations between the extent of cannabis use and tobacco smoking and vice versa, after controlling for non-observed fixed confounding factors and for a number of time-dynamic covariate factors (major depression, alcohol use disorder, anxiety disorder, stressful life events, deviant peer affiliations). Furthermore, increasing levels of tobacco smoking were associated with increasing cannabis use (p=0.02) and vice versa (p<0.001) over time.

Conclusions: Our results lend support to the notion of both of 'gateway' and 'reverse gateway' effects. That is, the association between tobacco and cannabis use arises from a reciprocal feedback loop involving simultaneous causation between tobacco use disorder and cannabis use disorder.

Keywords: Cannabis; Longitudinal study; Structural equation Modelling; Tobacco.