Assessing the Statistical Evidence in the Shonubi Case

Abstract

A number of interesting statistical issues arose in determining the total amount of heroin smuggled into the United States by Charles O. Shonubi in his eight trips to and from Nigeria. Smuggling on each trip was accomplished by swallowing heroin-filled balloons. The only evidence of actual narcotics smuggled in those eight trips, however, was the 427.4 grams smuggled on the last trip. The case, United States a Shonubi, consists of a series of five opinions, three by the sentencing judge of the federal district (E.D.N.Y.) and two by the Court of Appeals for the Second Circuit. The primary issue in contention was the length of Shonubi’s sentence. The federal sentencing guidelines required that his sentence be based not just on the total quantity of drugs he carried internally at the time he was arrested, but also on “all such acts and omissions that were part of the same course of conduct or common scheme or plan as the offense of conviction.” The prosecution, therefore, argued that the total amount of drugs carried by Shonubi should include an estimate of the amount he carried on his seven previous trips. This latter estimate proved to be the most contentious part of the case. In this article we examine some of the statistical issues raised in the sentencing phase. These include whether the quantity of drugs carried by Shonubi on his last trip was correctly determined; the effects of using estimates of balloon weights of other smugglers in determining the amount of heroin carried by Shonubi on his seven previous trips; whether the modeling process should include a recognition of the existence of a learning curve for swallowing large numbers of heroin-filled balloons; the influence of covariates, such as age and gender, on the smuggling process; and the use of the bootstrap as a method of estimating drug amounts carried on prior trips. Three data sets on Nigerian heroin smugglers are used to provide information on constructing drug quantity estimates.