The dirichlet-multinomial model for multivariate randomized response data and small samples

In survey sampling the randomized response (RR) technique can be used to obtain truthful answers to sensitive questions. Although the individual answers are masked due to the RR technique, individual (sensitive) response rates can be estimated when observing multivariate response data. The beta-binomial model for binary RR data will be generalized to handle multivariate categorical RR data. The Dirichlet- multinomial model for categorical RR data is extended with a linear transformation of the masked individual categorical-response rates to correct for the RR design and to retrieve the sensitive categorical-response rates even for small data samples. This specification of the Dirichlet- multinomial model enables a straightforward empirical Bayes estimation of the model parameters. A constrained-Dirichlet prior will be introduced to identify homogeneity restrictions in response rates across persons and/or categories. The performance of the full Bayes parameter estimation method is verified using simulated data. The proposed model will be applied to the college alcohol problem scale study, where students were interviewed directly or interviewed via the randomized response technique about negative consequences from drinking(AU)

Prevalencia de trastornos relacionados con el consumo del alcohol en población penitenciaria condenada por delitos contra la seguridad vial / Prevalence of alcohol consumption related disorders in a prison population convicted of crimes against road safety

Introducción. El consumo de alcohol es la causa de un elevado número de accidentes de tráfico, por lo que se han endurecido las leyes para evitarlo. A pesar de ello hay personas que las infringen e ingresan en prisión por conducir bajo los efectos del alcohol. Se investiga si estas personas son bebedores ocasionales o bien son enfermos alcohólicos. Material y Método. Estudio transversal de 50 internos penitenciarios por delitos contra la seguridad vial, entrevistados acerca de su consumo alcohólico, antecedentes psicopatológicos y delictivos. Resultados. El 88% presenta indicadores de alcoholismo y la mayoría consume otras drogas. Sólo en el 10% se ha detectado psicopatología previa. El 72% tiene antecedentes penitenciarios, la mitad por delitos con violencia. Socialmente están adaptados, 39 años de edad media, son españoles (86%), tienen familia y trabajo regular (76%). Conclusiones. La mayoría de internos por delitos contrala seguridad vial son alcohólicos, pero pocos son detectados. Su enfermedad genera otras conductas delictivas, siendo necesario su tratamiento para evitar la reincidencia y un proceso de exclusión social (AU)

Introduction. Alcohol consumption is a major cause of traffic accidents, so that stricter laws have been enacted to avoid it. Despite this, there are still persons who break the law and go to prison because of driving under the effects of alcohol. We have investigated if these persons are occasionally alcohol drinkers or if they are alcoholics with difficult to modify alcohol patterns. Material and methods. A cross-sectional study including 50 inmates from two prisons who had committed traffic crimes were interviewed about their alcohol consumption habits and their criminal and psychopathological backgrounds. Results. 88% had indicators of alcoholism and most consumed other drugs. Previous psychopathology signs were only detected in 10% of the sample. A total of 72% had previous criminal records, half because of violent offences. They were socially adapted, with mean age 39 years, Spanish (86%), had a stable job and family (76%). Conclusions. Most of the inmates due to traffic rimes are alcoholic, but very few are detected. Their alcohol consumption generates other criminal conduct, treatment being necessary in order to avoid relapse and social exclusion (AU)