时间：2018年3月28（星期三）13：30-15：30

地点：学院南路校区，学术会堂603

报告一题目：Efficient rank-based two-sample tests for partially paired data

报告人：北京师范大学统计学院、郭旭副教授

摘要：In this paper, we consider efficient rank-based two-sample tests for partially paired data. We first propose the optimal weighted linear combination of the test statistics comparing all four paired and unpaired data sets and propose the optimal weighted linear combination of the test statistics comparing only two paired and independent subsamples. We prove formally that making additional two comparisons is helpful, which can enhance powers. We also find that the weights introduced in a recent paper are not the optimal choice. Their weights do not account for the effect of covariance between the test statistics. Numerical studies and a real data example are used to illustrate the performance of our proposed optimal weighted combinations of test statistics and compare with some existing methods.

报告人简介：

郭旭现任北京师范大学统计学院副教授。2014年于香港浸会大学获统计学博士学位，研究方向为模型检验、缺失数据、不确定下的行为决策等。在统计学顶级期刊Journal of the Royal Statistical Society: Series B和 Biometrika，统计学主流期刊Statistics and Computing, Journal of Multivariate Analysis, Computational Statistics & Data Analysis，Scandinavian Journal of Statistics和经济学主流期刊Insurance: Mathematics and Economics, North American Journal of Economics and Finance, Economics Letters, 和Economic Modelling等SCI和SSCI期刊发表论文近30篇。

报告二题目：Existence of global smooth solution and long time behavior for nonlinear system with degenerate viscosity in 2-dimensional space

报告人：威尼斯wns885566、陈静副教授

摘要：This topic concerns the existence of global smooth solution and long time behavior for nonlinear system with degenerate viscosity in 2-dimensional space. The analysis is based on successive approximation, maximum principle, L^2-energy method and the decay property of rarefaction wave.