Suchergebnisse

Traditional clustering algorithms are deterministic in the sense that a given dataset always leads to the same output partition. This article modifies traditional clustering algorithms whereby data are associated with a probability model, and clustering is carried out on the stochastic model parameters rather than the data. This is done in a principled way using a Bayesian approach which allows the assignment of posterior probabilities to output partitions. In addition, the approach incorporates prior knowledge of the output partitions using Bayesian melding. The methodology is applied to two substantive problems: (i) a question of stylometry involving a simulated dataset and (ii) the assessment of potential champions of the 2010 FIFA World Cup.

AbstractIn early 1996, Canada's federal government enacted a new constitutional amending process to provide provincial and regional vetoes over future amendments. This study compares the new process with the "7 and 50" formula found in the Constitution Act, 1982. Using the Banzhaf Index as well as separate measures for the power to prevent and the power to initiate amendments, the article examines the relative influence of the provinces under the two amending formulae. As well, it examines the relative voting power of each province's citizens in any future constitutional referendum. The results show that profound changes are produced by the regional veto amending formula, and the article discusses some remedies for the most negative effects.