At the invitation of the school of Mathematical Sciences, Professor Lin Jinguan, president of School of statistics and mathematics, Nanjing Audit University, delivered an academic report entitled "Adaptive semiparametric estimation for single index models with jumps " at Tencent Conference in the afternoon of December 10, 2020. Liu Guoxiang, professor of statistics and financial mathematics institute, presided over the meeting. Professor Xie Fengchang, Professor Liu Guoxiang, Professor Gao Qibing, Professor Zhou Xiuqing, Professor Liang Zhibin, Associate Professor Yao Yi, Associate Professor Du Xiuli, Associate Professor Xu Xiaoming, Associate Professor Li Qicai, Associate Professor Mi Hui, Associate Professor Yin Rongcheng, Dr. Sun yuan, and some graduate students majoring in probability theory and mathematical statistics attended the meeting.
Professor Lin Jinguan is a well-known statistical expert in China. He was the head of the Department of statistics of Southeast University. He is currently the president of the school of statistics and mathematics, Nanjing Audit University, and the president of the Institute of statistical science and big data. Mainly engaged in nonlinear statistics, econometrics, financial statistics and risk measurement, statistical diagnosis, panel data analysis and statistical application. He graduated from East China Normal University with a bachelor's degree and a master's degree in mathematics and mathematical statistics, and a doctor's degree in system engineering of Southeast University. Since 2000, more than 100 papers have been published in core journals at home and abroad, including nearly 100 papers in SCI and SSCI. At present, he is a member of the Statistical Teaching Steering Committee of the Ministry of education in 2018-2022, vice president of the National Industrial Statistics Teaching Research Association, vice president of the engineering probability and statistics society of the China Field Statistics Research Association, vice president of the resources and environment society of the China Field Statistics Research Association, Secretary General of the Jiangsu probability and statistics society, and Chinese core journals system science and mathematics, and application probability "Statistics" and "mathematical statistics and management" magazine editorial board. He has presided over 18 projects above the provincial and ministerial level, including 5 National Natural Science Foundation and national social science foundation.
At the report meeting, Professor Lin Jinguan introduced that the single index model is one of the most popular semiparametric models in applied quantitative sciences. This report studies a single index model with unknown jumps (SIMJ) that occur in the link function. An adaptive semiparametric estimation procedure is proposed for estimating the index coeﬃcient and link function. The asymptotic normality of the resulting estimators for both the parametric and nonparametric parts can be established under some mild conditions and without specifying the error distribution. They show that the resulting estimators are robust and eﬃcient for diﬀerent error distributions. In particular, a modiﬁed EM algorithm is developed to implement the adaptive semiparametric estimation in practice. Numerical simulations and real data analysis are conducted to illustrate the ﬁnite sample performance of the proposed approach. Finally, Prof. Lin Jinguan looks forward to the related problems.
After the report, the teachers and students had a heated discussion with Professor Lin Jinguan on the content of the report. Throughout the report, Professor Lin Jinguan's language is humorous and witty, and the explanation is clear and easy to understand, which broadens our academic vision. Finally, the report was successfully concluded in warm applause.
（From Du Xiuli）