A quadrivariate triangular decomposition (also known as a Cholesky decomposition) was fitted to assess the degree of overlap in genetic and environmental influences between alcohol consumption, AD symptomatology, cannabis use, and cannabis dependence symptomatology. Models were fitted in Mx (Neale et al., 2003) using full information maximum likelihood estimation with raw categorical data. Cannabis use and alcohol consumption variables were recoded into ordinal variables, as Mx requires that all variables be in the same format (and dependence symptoms are ordinal in nature). Thresholds were adjusted for age at the time of interview using three dummy variables to represent ages 28-29, 30-31, and 32-35, with 24-27 years as the comparison group.
