Rarely pure and never simple: extracting the truth from self-reported data on substance use

Abstract

ACKNOWLEDGEMENTS: Oscar Wilde's contribution gratefully acknowledged. I am also extremely grateful to Gabriella Conti for drawing my attention to the OCJS and BCS70 recanting problem and to her, Annette Jäckle, Heather Laurie and Peter Lynn for helpful discussions. This work was supported by the Economic and Social Research Council through the ULSC and MiSoC Research Centres (award nos. H562255004 and RES518285001). I bear sole responsibility for the conclusions and any errors.ABSTRACT: We consider the misreporting of illicit drug use and juvenile smoking in self-report surveys and its consequences for statistical inference. Panel data containing repeated self-reports of 'lifetime' prevalence give unambiguous evidence of misreporting as 'recanting' of earlier reports of drug use. The identification of true initiation and reporting processes from such data is problematic in short panels, whilst more secure identification is possible in panels with at least five waves. Nevertheless, evidence from three UK datasets clearly indicates serious underreporting of cannabis, cocaine and tobacco use by young people, with consequent large biases in statistical modelling.

Modelling Illegal Drug Participation

“…of the small percentage of cocaine users in the population (recorded at 1.3% and estimated at just under 5%) 65% claimed not to be. This may appear high, but it is in line with previous studies (Pudney, ). This difference between cocaine and marijuana may reflect the greater risk that is associated with the former.…”

“…In addition, given the apparent complex interrelationships between the demand for different types of illicit drugs, it is apparent that the extent of misreporting may vary across different types of drugs, arguably being particularly serious in the case of harder drugs (such as heroin and cocaine). Pudney () analysed the consequences of misreporting of illicit drugs use for statistical inference by using UK panel data containing repeated questions on self‐reported lifetime drug use. The findings indicate serious underreporting of the use of marijuana and cocaine, which in turn leads to biases in statistical modelling.…”

“…Individuals may have an incentive to underreport activities which are regarded as socially undesirable or which are associated with perceived social stigma or legal consequences, such as smoking, alcohol, illicit drug consumption and sexual behaviours (e.g. Berg and Lien () and Pudney ()).…”

The Dynamic Risk of Heavy Episodic Drinking on Interpersonal Assault in Young Adolescence and Early Adulthood

“…Alongside measurement issues associated with secondary data, established concerns surrounding self-reports (see Thornberry and Krohn 2000;McVie 2003 andPudney 2006 for issues concerning the OCJS in particular), and the underreporting of alcohol use using survey measures and associated underestimation of alcohol-related harms (Goddard 2001;Bellis et al 2009), there remain concerns associated with missing data and attrition. Overall, attrition rates were relatively low and panel response rates ranged between 82 and 85%.…”

Misreporting and econometric modelling of zeros in survey data on social bads: An application to cannabis consumption

“…Here, it is clear that the researcher must be aware of the potential for misreporting. For example, there will be a strong incentive for individuals to misreport (presumably under‐report) their true consumption levels for fears of legal (and/or moral) repercussions (see, e.g., Pudney, ). This typically gives rise to a preponderance of “zero” observations in the data set.…”