论文检索

蝾螈交配数据的再分析：修正 Laplace 近似方法AI 解读

The salamander mating dataset of McCullagh and Nelder has drawn the attention of statisticians because of its challenging structure: the design is crossed rather than nested. The standard Laplace approximation used to evaluate marginal likelihood functions fails in this case because the dimension of the integral is the square root of the sample size. A modification has been proposed by Shun and McCullagh. This article reanalyzes the salamander data using this modified…

SUMMARY It is shown that the usual Laplace approximation is not a valid asymptotic approximation when the dimension of the integral is comparable with the limiting parameter n. The formal Laplace expansion for multidimensional integrals is given and used to construct asymptotic approximations for high dimensional integrals. One example is considered in which the dimension of the integral is O(n 1/2) and the relative error of the unmodified Laplace approximation is O(1).…