论文标题
可交换二进制变量的建模总和
Modeling Sums of Exchangeable Binary Variables
论文作者
论文摘要
我们介绍了一个新模型，用于可交换二进制随机变量的总和。所提出的分布是与确切分布形式的近似值，并依赖于完全单调函数的理论和γ分布函数的拉普拉斯变换。使用Monte Carlo方法，我们表明该新模型与β二项式模型相比，就估计Bernoulli试验的成功概率以及可交换集中任何两个变量之间的相关性而言。我们将新方法应用于两个经典数据集，并总结了结果。
We introduce a new model for sums of exchangeable binary random variables. The proposed distribution is an approximation to the exact distributional form, and relies on the theory of completely monotone functions and the Laplace transform of a gamma distribution function. Using Monte Carlo methods, we show that this new model compares favorably to the beta binomial model with respect to estimating the success probability of the Bernoulli trials and the correlation between any two variables in the exchangeable set. We apply the new methodology to two classic data sets and the results are summarized.
