Robust semiparametric model selection using the estimating functions

取得的主要成果有：(1)王俊（2006）。使用估计函数的二次人工似然函数。统计学报，33(2),16-35。[摘要]本文研究了最优估计函数框架下似然推理的一种模拟。提出了一种二次人工似然函数作为最优估计函数。人工似然函数在许多方面与真实似然函数相似。[2]王俊，田中宁。（2006）。正规化无偏估计函数。统计规划与推理，36(3),689-704。[摘要]本文通过对无偏估计函数进行归一化变换，研究了一种确定标量参数二阶精确置信区间的方法。[3]景平，王健（2006）。用自举法和综合经验过程检验多元分布的等式。统计通讯理论与方法，35(3),661-670。[摘要]本文介绍了检验两个多元分布相等性的投影综合经验过程。自举法用于确定近似临界值。自举测试显示是一致的。[4]王金芳（2006）。条件独立的硬币代数。京都大学数学科学研究所的Kokyuroku，“统计条件推理及其相关主题”（即将出现）。摘要：在统计因果推理中引入了一种新的通用代数——硬币代数。本文主要讨论了硬币代数的基础和概率条件独立的性质。

Main results achieved include(1) Wang, J. (2006). Quadratic artificial likelihood functions using estimating functions. Scandinavian Journal of Statistics, 33(2), 16-35. [Summary : This paper studies an analogue of the likelihood inference in the framework of optimal estimating functions. It proposes a quadratic artificial likelihood function for an optimal estimating function. The artificial likelihood function is shown to resemble a genuine likelihood function in a number of respects.](2) Wang, J. and Taneichi, N. (2006). Normalizing unbiased estimating functions. Journal of Statistical Planning and Inference, 136(3), 689-704. [Summary : The paper considers a method for setting second-order accurate confidence intervals for a scalar parameter by applying normalizing transformations to unbiased estimating functions.](3) Jing, P. and Wang, J. (2006). Testing the equality of multivariate distributions using the bootstrap and integrated empirical processes. Communications in Statistics-Theory and Methods, 35(3), 661-670. [Summary : The paper introduces some projected integrated empirical processes for testing the equality of two multivariate distributions. The bootstrap is used for determining the approximate critical values. The bootstrap test is shown to be consistent.](4) Jinfang Wang (2006). The coin algebra for conditional independence. Kokyuroku of the Research Institute for Mathematical Sciences, Kyoto University, 「Statistical Conditional Inference and Its Related Topics」 (to appear). [Summary : A new universal algebra, the coin algebra, is introduced to statisticl causal inference. This papers focuses on the foudations of the coin algebra and properties on probabilistic conditional independence.]