Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
Loyer discusses various paradoxes that arise when analyzing data sets and conditional probabilities. He highlights the phenomenon known as Loyers paradox, where the probability of an event appears to be larger or smaller than each of its mutually exclusive and exhaustive component conditional probabilities. The paradox is demonstrated using data on baseball batting averages and court case conviction rates. He explains that these paradoxes arise from the inappropriate pooling of data sets and the use of weighted and unweighted averages. He explores the extension of the paradox in the context of new rules in major league baseball and court cases involving different racial groups. He concludes that pooling different data sets can lead to artificial results that do not accurately represent the original sets. The paradoxes discussed have real-world applications and should be recognized and discussed in literature and classrooms.