The Applied Statistics Workshop 2025

担当教員:大森裕浩 (Yasuhiro Omori)・下津克己 (Katsumi Shimotsu)、入江 薫 (Kaoru Irie)・奥井亮 (Ryo Okui)

日時
2025年6月13日(金 Friday) 16:50-18:35
場所
東京大学大学院経済学研究科棟 3階 第3教室
Lecture Hall No. 3 on the 3rd floor of the Economics Research Building [MAP]

※対面のみでの開催です。東京大学以外で参加をご希望の方は、CIRJE (cirje[at mark]e.u-tokyo.ac.jp) までご連絡ください。

報告
Shuangzhe Liu (University of Canberra)
"Matrix differential calculus with applications in statistical learning"
Abstract Matrix differential calculus plays a very important role in statistical learning and data science. In this talk, we start with a big picture of mathematics (including calculus, linear algebra, probability, and statistics), useful to statistical learning. We then pay particular attention to matrix differential calculus and its applications to the multivariate linear model, including efficiency comparisons, sensitivity analysis, and statistical diagnostics.
日時
2025年6月20日(金 Friday) 16:50-18:35
場所
東京大学大学院経済学研究科棟 3階 第3教室
Lecture Hall No. 3 on the 3rd floor of the Economics Research Building [MAP]

※対面のみでの開催です。東京大学以外で参加をご希望の方は、CIRJE (cirje[at mark]e.u-tokyo.ac.jp) までご連絡ください。

報告
Tevfik Aktekin (University of New Hampshire)
TBA
Abstract
日時
2025年7月4日(金 Friday) 16:50-18:35
場所
東京大学大学院経済学研究科棟 3階 第3教室
Lecture Hall No. 3 on the 3rd floor of the Economics Research Building [MAP]

※対面のみでの開催です。東京大学以外で参加をご希望の方は、CIRJE (cirje[at mark]e.u-tokyo.ac.jp) までご連絡ください。

報告
今井耕介 (Harvard University)
Kosuke Imai (Harvard University)

"Generative AI Powered Inference" joint with Kentaro Nakamura
Abstract
日時
2025年7月11日(金 Friday) 16:50-18:35
場所
東京大学大学院経済学研究科棟 3階 第3教室
Lecture Hall No. 3 on the 3rd floor of the Economics Research Building [MAP]

※対面のみでの開催です。東京大学以外で参加をご希望の方は、CIRJE (cirje[at mark]e.u-tokyo.ac.jp) までご連絡ください。

報告
清水健一 (University of Alberta)
Kenichi Shimizu (University of Alberta)

TBA
Abstract
日時
2025年7月18日(金 Friday) 16:50-18:35
場所
東京大学大学院経済学研究科棟 3階 第3教室
Lecture Hall No. 3 on the 3rd floor of the Economics Research Building [MAP]

※対面のみでの開催です。東京大学以外で参加をご希望の方は、CIRJE (cirje[at mark]e.u-tokyo.ac.jp) までご連絡ください。

報告
Jun Yu (University of Macao)
TBA
Abstract
日時
2025年10月10日(金 Friday) 16:50-18:35
場所
東京大学大学院経済学研究科棟 3階 第3教室
Lecture Hall No. 3 on the 3rd floor of the Economics Research Building [MAP]

※対面のみでの開催です。東京大学以外で参加をご希望の方は、CIRJE (cirje[at mark]e.u-tokyo.ac.jp) までご連絡ください。

報告
Fang Han (University of Washington)
TBA
Abstract

以下本年度終了分

日時
2025年4月18日(金 Friday) 16:50-18:35
場所
東京大学大学院経済学研究科棟 3階 第3教室
Lecture Hall No. 3 on the 3rd floor of the Economics Research Building [MAP]

※対面のみでの開催です。東京大学以外で参加をご希望の方は、CIRJE (cirje[at mark]e.u-tokyo.ac.jp) までご連絡ください。

報告
太田悠太(慶應義塾大学)
Yuta Ohta (Keio University)

"Causal inference with auxiliary observations" with Takahiro Hoshino (Keio University), Taisuke Otsu(London School of Economics)
Abstract In the evaluation of social programs, it is often difficult to conduct randomized controlled experiments due to non-compliance; therefore the local average treatment effect (LATE) is commonly applied. However, the LATE identifies the average treatment effect only for a subpopulation known as compliers and requires the monotonicity assumption. Given these limitations of the LATE, this paper proposes a nonparametric strategy to identify the causal effects for larger populations (such as the ATT and ATE) and to remove the monotonicity assumption in the cases of non-compliance. Our strategy utilizes two types of auxiliary observations, one is an outcome before assignment and the other is a treatment before assignment. These observations do not require specially designed experiments, and are likely to be observed in baseline surveys of the standard experiment or panel data. We show the results for the random assignment and those of multiply robust representations in the case where the random assignment is violated. We then present details of the GMM estimation and testing methods which utilize over-identified restrictions. The proposed strategy is illustrated by empirical examples which revisit the studies by Thornton (2008), Gerber et al. (2009), and Beam (2016), as well as the data set from the Oregon Health Insurance Experiment and that from an experimental data on marketing in a private sector.
【臨時】
日時

(臨時応用統計ワークショップ)

2025年5月23日(金 Friday) 16:50-18:35
場所
東京大学大学院経済学研究科 学術交流棟 (小島ホール)1階 第1セミナー室
in Seminar Room 1 on the 1st floor of the Economics Research Annex (Kojima Hall) [MAP]
※場所にご注意ください

※対面のみでの開催です。東京大学以外で参加をご希望の方は、CIRJE (cirje[at mark]e.u-tokyo.ac.jp) までご連絡ください。

報告
Josu Arteche (University of the Basque Country UPV/EHU)
"Local Inference in General Long Memory Series"
Abstract A generalization of the Exact Local Whittle estimator in Shimotsu and Phillips (2005) was proposed in Arteche (2020) for jointly estimating all the memory parameters in general long memory time series that possibly display standard, seasonal and/or other cyclical strong persistence. Its asymptotic properties permit straightforward standard inference based on Wald statistics of interesting hypotheses such as the existence of unit roots and equality of memory parameters at some or all seasonal frequencies, which can be used as a prior test for the application of seasonal differencing filters. Lagrange Multiplier-type tests, which avoid the need to estimate the memory parameters, are proposed here as a means of testing for the existence of long memory of any degree at any set of frequencies. The tests are applicable to both stationary and non-stationary as well as to invertible and non-invertible series exhibiting any type of standard, cyclical or seasonal persistence. No estimation of parameters or specification of short memory behaviour is required, as the tests are based on a local spectral specification around the frequencies of interest. Standard inference can be implemented thanks to the chisquared asymptotic distribution under the null hypothesis. The testing strategy is shown to be consistent against constant departures from the null hypothesis and the asymptotic distribution of the test statistics under local alternatives is also shown. Finally, the robustness of the tests to the presence of some deterministic components is shown.
【臨時】
日時

(臨時応用統計ワークショップ)

2025年5月30日(金 Friday) 16:50-18:35
場所
東京大学大学院経済学研究科 学術交流棟 (小島ホール)1階 第1セミナー室
in Seminar Room 1 on the 1st floor of the Economics Research Annex (Kojima Hall) [MAP]
※ 会場が変更いたしましたのでご注意ください。The venue has been changed.

※対面のみでの開催です。東京大学以外で参加をご希望の方は、CIRJE (cirje[at mark]e.u-tokyo.ac.jp) までご連絡ください。

 

報告
大和田孝 (Purdue University)
Takashi Owada (Purdue University)

"Stochastic Topology and Topological Data Analysis"
Abstract Topological data analysis (TDA) is a rapidly growing field focused on extracting meaningful and robust topological features from high-dimensional data. This talk relates to stochastic topology as a significant interaction between probability theory and algebraic topology.In the first part, we examine how the heaviness of the tails of probability distributions affects topological structures, by examining a phenomenon called topological crackle. Topological crackle refers to layers of extraneous topological features. We analyze this phenomenon via the behavior of Betti numbers, which is a key measure of topological complexity.In the second part, we turn to multi-parameter random simplicial complexes, which generalize Erdros-Renyi graphs to higher dimensions. We present results showing that their Betti numbers follow strong laws of large numbers and central limit theorems. We also discuss large deviations of these Betti numbers.
【臨時】
日時

(臨時応用統計ワークショップ)

2025年6月6日(金 Friday) 16:50-18:35
場所
東京大学大学院経済学研究科棟 3階 第3教室
Lecture Hall No. 3 on the 3rd floor of the Economics Research Building [MAP]

※対面のみでの開催です。東京大学以外で参加をご希望の方は、CIRJE (cirje[at mark]e.u-tokyo.ac.jp) までご連絡ください。

 

報告
Ji Zhu (University of Michigan)
"A Latent Space Model for Hypergraphs with Diversity and Heterogeneous Popularity"
Abstract While relations among individuals make an important part of data with scientific and business interests, existing statistical modeling of relational data has mainly been focusing on dyadic relations, i.e., those between two individuals. This work addresses the less studied, though commonly encountered, polyadic relations that can involve more than two individuals. In particular, we propose a new latent space model for hypergraphs using determinantal point processes, which is driven by the diversity within hyperedges and each node's popularity. This model mechanism is in contrast to existing hypergraph models, which are predominantly driven by similarity rather than diversity. Additionally, the proposed model accommodates broad types of hypergraphs, with no restriction on the cardinality and multiplicity of hyperedges. Consistency and asymptotic normality of the maximum likelihood estimates of the model parameters have been established. The proof is challenging, owing to the special configuration of the parameter space. Simulation studies and an application to the What's Cooking data show the effectiveness of the proposed model. 

 

[ English Top ]