The study was restricted to individuals sentenced following their conviction of an offense under section 233B of the Customs Act 1901 which deals with possession or sale of illegally imported drugs. Data from 257 cases in which a sentence of imprisonment was imposed during the period 1976-80 were analyzed. Results showed that when drug type and quantity of drug were taken into account, together with a further discrete number of other factors, differences between sentences were very slight. Refinements to the initial model are described, with attention to the methods used in a mini study of heroin offenders decided after 1978 which substantially improved the predictive ability of the regression model. The final model can be used not only to determine sentencing disparity, but as a guideline for future sentencing. Tables, graphs, and 6 references. (Author abstract modified)