时间：2017年7月4日 星期二上午 9：00-11：10
地点：军工路334号管理学院10楼1010会议室
报告一
题目:基于可见图的Logistic时间序列分析
摘要:基于复杂网络的时间序列分析近年来取得了迅猛的发展. 把时间序列映射为复杂网络,可以研究从微观到宏观不同尺度上的特征变化. 我们给出了混沌时间序列logistic映射的可见图，针对不同的混沌态和确定态，分析所对应的谱的性质特点。实证数据分析表明，发现构造出来的这些网络能够反映这些动力学系统的结构和动力学特征.
时间：9：00-9：30
报告人：肖琴，博士，上海应用技术大学讲师，2015年毕业于红足1一世足球网，获理学博士学位，目前的主要研究兴趣是时间序列分析和复杂网络科学问题。在Physica A, Physica Chinese B等SCI期刊发表论文,目前主持上海市自然科学基金项目一项。
报告二
题目：Specification tests for Conditional Granger causality in quantiles
摘要：Granger causality analysis is a popular method for inference on directed interactions in economics of many variables. A shortcoming of the standard linear regression framework for Granger causality is that it only identifies the pair causal pattern. However, interactions do not necessarily take place between pair variables, but may be mediated by other variables. In this talk, we introduce a principled framework for conditional Granger causality test in the context of causal relationship among more multivariate variables. Building on Geweke’s (1984) and Troster’s (2016) seminal work, we offer additional justifications for one particular form of multivariate Granger causality based on the parametric dynamic quantile regressive models that evaluate nonlinear causality and possible causal relations in all conditional quantiles. We present Monte Carlo experiments and an application considering the causal relations between stock market trading volume, returns and exchange rates for both domestic and cross-country markets by using the daily data of the three financial markets: China, Japan, Korea. Taken together, our results support a comprehensive and theoretically consistent extension of Granger causality to the multivariate case.
时间：9：30-10：00
报告人：程宏，博士，上海立信会计金融学院统计与数学学院师资研究员，2015年毕业于上海交通大学数学与科学学院和自然科学研究院，获理学博士学位，目前的主要研究兴趣是计算神经科学领域的科学问题、统计分析分析方法及其在金融、计算机视觉中的应用。在Journal of computer science and technology、Italian Journal of pure and applied mathematics、Physical Review E等SCI/EI期刊发表论文多篇，CCF会员。目前主持上海市青年科技英才“杨帆计划”项目等两项，参与多项国家自然科学基金面上项目。
报告三
题目：Testing for change points due to a covariate threshold in quantile regression
摘要：We develop a new procedure for testing change points due to a covariate threshold in regression quantiles. The proposed test is based on the CUSUM of the subgradient of the quantile objective function and requires fitting the model only under the null hypothesis. The critical values can be obtained by simulating the Gaussian process that characterizes the limiting distribution of the test statistic. The proposed method can be used to detect change points at a single quantile level or across multiple quantiles, and can accommodate both homoscedastic and heteroscedastic errors. Simulation study suggests that the proposed method has higher computational efficiency and comparable power with the existing likelihood ratio-based method in the finite samples. The performance of the proposed method is further illustrated by the analysis of a blood pressure and body mass index dataset.
时间：10：10-10：40
报告人：张立文, 男, 博士（后），上海大学经济学院讲师、硕士生导师。分别于2010年和2014年在南京师范大学和复旦大学获得理学硕士和理学博士学位。2014-2015在香港中文大学统计学系从事博士后研究。 主要从事数理统计、计量经济、金融计量等方面的研究。 曾于2012.03-2013.05，2013.06-2013.08和2016.0-2016.08作为研究学者赴美国北卡州立大学、美国德州大学MD安德森癌症中心以及香港大学访学交流。在统计金融权威SCI/SSCI期刊上发表多篇学术论文，包括《Statistica Sinica》、《Biometrics》、《Economical Modelling》等。现担任《Biometrics》、《Emerging Markets Finance and Trade》、《Annals of the Institute of Statistical Mathematics》、《系统工程与数学》等期刊匿名审稿人。目前主持国家自然基金青年项目等两项，参与多项国家自然科学基金面上项目。
报告四
题目：Testing error heterogeneity in censored linear regression
摘要：In censored linear regression, a key assumption is that the error is independent of predictors. We develop an omnibus test to check error heterogeneity in censored linear regression. Our approach is based on testing the variance component in a working kernel machine regression model. The limiting null distribution of the proposed test statistic is shown to be a weighted sum of independent chi-squared distributions with one degree of freedom. A resampling scheme is derived to approximate the null distribution. The empirical performance of the proposed tests is evaluated via simulation and two real data sets.
时间：10：40-11：10
报告人：范彩云, 女, 上海对外经贸大学统计与信息学院讲师、硕士生导师，应用经济学高原学科骨干人员，2015年在上海财经大学统计与管理学院获统计学博士学位。2014-2015年赴美国北卡罗来纳州立大学访问，主要研究兴趣包括复杂数据建模，个性化处理，生存分析等。至今已在《Journal of the Royal Statistical Society Series B》、《Statistics and Its Interface》等上发表学术论文多篇。 目前主持主持国家自然基金项目两项、上海市浦江人才计划资助项目一项，参与多项国家自然科学基金面上项目，参与上海市软科学重点研究项目一项。
