Effect of Survey Conditions on Self‐reported Substance Use

This paper examines the impact of survey conditions on the self‐reported use of marijuana, cocaine, and alcohol in the 1984 and 1988 waves of the National Longitudinal Survey of Youth (NLSY). The analysis obtains probit estimates of lifetime and current participation rates and ordered probit estimates for the current frequency of use. The results clearly indicate that the manner in which the NLSY survey is administered significantly affects the self‐reported substance use data. The presence of others at administration, self‐administration, and data collection by telephone interview are particularly important influences.