Analysing Drug Abuse with British Crime Survey Data: Modelling and Questionnaire Design Issues

Abstract

We use the British Crime Survey (BCS) to analyse the demand for illicit drugs, and the implications of drug use for the probability of subsequent unemployment. We demonstrate that the BCS questionnaire has a serious design ‡aw for this purpose, and propose some simple modi…cations. We also develop a modelling technique suitable for existing BCS data, and apply it to the 1994/96 sample. We …nd evidence that soft drug use is associated with a greatly increased probability of later hard drug use, and that past drug use is associated with increased probabilities of unemployment.JEL classi…cation: C51; I12; J24

The Impact of Alcohol Consumption on Occupational Attainment in England

“…The results of this experiment are quite revealing. Whereas previous studies of the relationship between drug abuse and occupational attainment have shown that there tends to be some noticeable differences between the labour market experiences of younger and older cohorts (Burgess and Propper 1998;MacDonald and Pudney 2000a), the results for the current data show no significant difference between age groups. Apart from some very slight differences in the magnitude of the estimated coefficients and the t-statistics, the only noticeable difference is with respect to the variables introduced to control for changes in alcohol consumption over time (model 4).…”

The Wages of Sin? Illegal Drug Use and the Labour Market

“…The first, and most important, of our conclusions can therefore be stated immediately: that this very commonly-used question structure is a serious barrier to statistical modelling of drug use at the individual level, and that survey designers should give serious attention to alternative designs (see MacDonald and Pudney [18]). …”

“…As such, we use the pooled data from the 1994 and 1996 surveys (the 1998 survey is not yet in the public domain). In addition, for this analysis we only focus on BCS respondents aged 16 to 25, although we have considered the labour market outcomes of older drug users elsewhere [18]. It is quite clear, however, that drug use is concentrated amongst younger people and that the majority of people 'mature out' of drug use in their late twenties or early thirties [19,20].…”

What Price Drug Use? The Contribution of Economics to an Evidence‐Based Drugs Policy

“…In this process, cannabis is seen as the stepping-stone in the transition from licit to illicit drug use, and this is typically motivated by the observation that very few hard drug users have not used cannabis. The basic problem is discussed in MacDonald and Pudney (2000a), and centres around the following probability difference: Á 1 ¼ Prðcurrent use of hard drugsjprevious use of soft drugsÞ À Prðcurrent use of hard drugsjno previous drug useÞ ð7Þ…”