BACKGROUND: Count data collected in substance abuse research often come with an excess of "zeroes," which are typically handled using zero-inflated regression models. However, there is a need to consider the design aspects of those studies before using such a statistical model to ascertain the sources of zeroes. OBJECTIVES: We sought to illustrate hurdle models as alternatives to zero-inflated models to validate a two-stage decision-making process in situations of "excess zeroes." METHODS: We use data from a study of 45 cocaine-dependent subjects where the primary scientific question was to evaluate whether study participation influences drug-seeking behavior. The outcome, "the frequency (count) of cocaine use days per week," is bounded (ranging from 0 to 7). We fit and compare binomial, Poisson, negative binomial, and the hurdle version of these models to study the effect of gender, age, time, and study participation on cocaine use. RESULTS: The hurdle binomial model provides the best fit. Gender and time are not predictive of use. Higher odds of use versus no use are associated with age; however once use is experienced, odds of further use decrease with increase in age. Participation was associated with higher odds of no-cocaine use; once there is use, participation reduced the odds of further use. CONCLUSION: Age and study participation are significantly predictive of cocaine-use behavior. SCIENTIFIC SIGNIFICANCE: The two-stage decision process as modeled by a hurdle binomial model (appropriate for bounded count data with excess zeroes) provides interesting insights into the study of covariate effects on count responses of substance use, when all enrolled subjects are believed to be "at-risk" of use.
BACKGROUND: Count data collected in substance abuse research often come with an excess of "zeroes," which are typically handled using zero-inflated regression models. However, there is a need to consider the design aspects of those studies before using such a statistical model to ascertain the sources of zeroes. OBJECTIVES: We sought to illustrate hurdle models as alternatives to zero-inflated models to validate a two-stage decision-making process in situations of "excess zeroes." METHODS: We use data from a study of 45 cocaine-dependent subjects where the primary scientific question was to evaluate whether study participation influences drug-seeking behavior. The outcome, "the frequency (count) of cocaine use days per week," is bounded (ranging from 0 to 7). We fit and compare binomial, Poisson, negative binomial, and the hurdle version of these models to study the effect of gender, age, time, and study participation on cocaine use. RESULTS: The hurdle binomial model provides the best fit. Gender and time are not predictive of use. Higher odds of use versus no use are associated with age; however once use is experienced, odds of further use decrease with increase in age. Participation was associated with higher odds of no-cocaine use; once there is use, participation reduced the odds of further use. CONCLUSION: Age and study participation are significantly predictive of cocaine-use behavior. SCIENTIFIC SIGNIFICANCE: The two-stage decision process as modeled by a hurdle binomial model (appropriate for bounded count data with excess zeroes) provides interesting insights into the study of covariate effects on count responses of substance use, when all enrolled subjects are believed to be "at-risk" of use.
Authors: W Scott Comulada; Robert E Weiss; William Cumberland; Mary Jane Rotheram-Borus Journal: Am J Drug Alcohol Abuse Date: 2007 Impact factor: 3.829
Authors: Denise A Hien; Aimee N C Campbell; Therese Killeen; Mei-Chen Hu; Cheri Hansen; Huiping Jiang; Mary Hatch-Maillette; Gloria M Miele; Lisa R Cohen; Weijin Gan; Stella M Resko; Michele DiBono; Elizabeth A Wells; Edward V Nunes Journal: AIDS Behav Date: 2009-05-19
Authors: Lidia Z Meshesha; Kathryn E Soltis; Edward A Wise; Damaris J Rohsenow; Katie Witkiewitz; James G Murphy Journal: J Subst Abuse Treat Date: 2020-03-19
Authors: Keanan J Joyner; Alison M Pickover; Kathryn E Soltis; Ashley A Dennhardt; Matthew P Martens; James G Murphy Journal: Alcohol Clin Exp Res Date: 2016-11-02 Impact factor: 3.455
Authors: Stacia M DeSantis; Dipankar Bandyopadhyay; Nathaniel L Baker; Patrick K Randall; Raymond F Anton; James J Prisciandaro Journal: Drug Alcohol Depend Date: 2013-04-06 Impact factor: 4.492