Causal Model of the Rate of Doctoral Course Enrollment in Japan
Trial Analysis by Statistical Causal Discovery Algorithm ‘’LiNGAM’’
DOI:
https://doi.org/10.51094/jxiv.1Keywords:
STI policy, statistical causal inference, statistical causal discovery, LiNGAM, EBPM, HR policy in STIAbstract
In the context of strengthening the research capacity and supporting young researchers in Japan, increasing Ph.D. students is one of the most important political goals. Although many kinds of political variables such as financial support on Ph.D. students, research environment, and career paths after they graduate, are related to this goal, it is still an open question how the government should control these factors quantitatively, due to the lack of the causal graph in this problem.
In this paper, we estimate quantitatively the causal effects on the rate of doctoral course enrollment by the variables from the open statistical data using ‘’LiNGAM’’, a statistical causal discovery method. We also discuss the interpretation of the results with the domain knowledge of science, technology, and innovation(STI) policy, and compare this data-driven approach with the traditional statistical causal inference method in the domain of STI policy.
Downloads *Displays the aggregated results up to the previous day.
References
[Hyvarinen10] A. Hyva.inen and K. Zhang and S. Shimizu and P. O. Hoyer：Estimation of a structural vector autoregression model using non-gaussianity.Journal of Machine Learning Research,11:1709--1731,2010. [ https://www.jmlr.org/papers/volume11/hyvarinen10a/hyvarinen10a.pdf.]
[Hyvarinen13] A. Hyva.inen and S. M. Smith：Pairwise likelihood ratios for estimation of non-Gaussian structural equation models.Journal of Machine Learning Research,14:111--152,2013. [ https://jmlr.org/papers/v14/hyvarinen13a.html ]
[Igolkina20] Anna A. Igolkina and Georgy Meshcheryakov：semopy: A Python Package for Structural Equation Modeling, Structural Equation Modeling.A Multidisciplinary Journal,Vol.27, Issue 6, pp.952--963,2020. [ https://doi.org/10.1080/10705511.2019.1704289 ]
[Komatsu10] Yusuke Komatsu, Shohei Shimizu, and Hidetoshi Shimodaira：Assessing statistical reliability of LiNGAM via multiscale bootstrap.In Proc. International Conference on Artificial Neural Networks (ICANN2010), Thessaloniki, Greece, pp.309--314,2010. [ https://doi.org/10.1007/978-3-642-15825-4_40 ]
[Maeda20] T. N. Maeda and S. Shimizu：RCD: Repetitive causal discovery of linear non-Gaussian acyclic models with latent confounders.In JMLR Workshop and Conference Proceedings, AISTATS2020 (Proc. 23rd International Conference on Artificial Intelligence and Statistics), Palermo, Sicily, Italy.,735--745,2020. [ http://proceedings.mlr.press/v108/maeda20a/maeda20a.pdf ]
[Okamura19] Keisuke OKAMURA：Interdisciplinarity revisited: evidence for research impact and dynamism.Palgrave Commun,Vol.5, No.141,2019. [ https://doi.org/10.1057/s41599-019-0352-4 ]
[Pearl 85] Judea Pearl.：Bayesian Networks: a Model of Self-Activated Memory for Evidential Reasoning.Proceedings, Cognitive Science Society,329--334,1985. [ https://ftp.cs.ucla.edu/pub/stat_ser/r43-1985.pdf ]
[Shimizu06] Shohei Shimizu, Patrik O. Hoyer, Aapo Hyva.inen, and Antti Kerminen：A linear non-gaussian acyclic model for causal discovery.Journal of Machine Learning Research,7:2003-2030,2006. [ https://www.cs.helsinki.fi/group/neuroinf/lingam/JMLR06.pdf ]
[Shimizu11] S. Shimizu, T. Inazumi, Y. Sogawa, A. Hyva.inen, Y. Kawahara, T. Washio, P. O. Hoyer and K. Bollen：DirectLiNGAM: A direct method for learning a linear non-Gaussian structural equation model.Journal of Machine Learning Research,12(Apr): 1225--1248,2011. [ https://dl.acm.org/doi/10.5555/1953048.2021040 ]
[Thamvitayakul12] K. Thamvitayakul, S. Shimizu, T. Ueno, T. Washio and T. Tashiro：Bootstrap confidence intervals in DirectLiNGAM.In Proc., 2012 IEEE 12th International Conference on Data Mining Workshops (ICDMW2012), Brussels, Belgium, pp.659--668,2012. [ https://doi.org/10.1109/ICDMW.2012.134 ]
[赤池73] Akaike H.：Information theory and an extension of the maximum likelihood principle.Proceedings of the 2nd International Symposium on Information Theory,267--281,1973.
[枝村16] 枝村 一磨：環境規制と経済的効果-製造事業所の VOC 排出に関する自主的取組に注目した定量分析.NISTEP DISCUSSION PAPER,No.133,2016. [ http://hdl.handle.net/11035/3132 ]
[浦田05] 山野井敦徳, 藤村正司, 浦田広朗：日本の大学教員市場再考--現在・過去・未来.広島大学高等教育研究開発センター,第5章:47--54,2005.
[浦田01] 浦田広朗：1990年代における大学院拡大.麗澤学際ジャーナル,第9巻第2号:52--75,2001.
[汪92] 汪 金芳; 大内 俊二; 景 平; 田栗 正章.：ブートストラップ法-最近までの発展と今後の展望-.行動計量学,19巻第2号 50--81,1992. [ doi:10.2333/jbhmk.19.2_50 ]
[高橋22] 高橋将宜：統計的因果推論の理論と実装.共立出版,2022.
[加藤09] 加藤真紀, 角田英之：日本の理工系修士学生の進路決定に関する意識調査.文部科学省 科学技術政策研究所 調査資料(Research Material),No.165,2009. [ http://hdl.handle.net/11035/895 ]
[川村22] 川村真理, 星野利彦：博士人材追跡調査-第4次報告書-.文部科学省 科学技術・学術政策研究所 調査資料(Research Material),No.317,2022. [ https://doi.org/10.15108/rm317 ]
[治部21a] 治部眞里, 星野利彦：修士課程（6 年制学科を含む）在籍者を起点とした追跡調査（2020 年度修了（卒業）者及び修了（卒業）予定者に関する報告）.文部科学省 科学技術・学術政策研究所 調査資料(Research Material),No.310,2021. [ https://doi.org/10.15108/rm310 ]
[治部21b] 治部眞里, 星野利彦：博士離れの要因についての一考察.文部科学省 科学技術・ 学術政策研究所 STI Horizon,Vol.7, No.2,2021. [ https://doi.org/10.15108/stih.00260 ]
[清水17] 清水昌平：統計的因果探索.講談社 機械学習プロフェッショナルシリーズ,2017.
[高山DP21] 高山正行，星野利彦：博士人材の年齢別人材流動モデルと試行的な将来予測.NISTEP Discussion Paper, No.193,] Feb 2021. [ https://doi.org/10.15108/dp193 ]
[高山21] 高山正行, 小柴等, 前田高志ニコラス, 三内顕義, 清水昌平, 星野利彦：EBPMと統計的因果探索・数理モデルの利活用.研究・イノベーション学会 第36回年次学術大会(予稿集).,公演番号2G02,2021.
[鳥海18] 鳥海 航, 生方 裕一, 久野 譜也, 岡田 幸彦：地域健康政策へのベイジアンネットワークの応用.統計数理,Vol.66, No.2, pp.267--278,2018. [ https://www.ism.ac.jp/editsec/toukei/pdf/66-2-267.pdf ]
[中山10] 中山 保夫, 細野 光章, 長谷川 光一, 永田 晃也：産学連携データ・ベースを活用した国立大学の共同研究・受託研究活動の分析.文部科学省 科学技術・学術政策研究所 調査資料(Research Material),No.183,2010. [ http://hdl.handle.net/11035/887 ]
[野村総研10] 野村総合研究所：博士課程進学の環境を改善するためのノンアカデミック・キャリアパスに関する調査最終報告書.野村総合研究所,2010.
[福澤15] 福澤 尚美, 伊神 正貫：科学技術の状況の俯瞰的可視化に向けて―NISTEP 定点調査 2011〜2014 のパネルデータを用いた質問項目間の関係性についての定量分析―.NISTEP DISCUSSION PAPER,No.128,2015. [ http://hdl.handle.net/11035/3112 ]
Downloads
Posted
Submitted: 2022-03-24 01:21:10 UTC
Published: 2022-03-25 10:58:37 UTC
License
Copyright (c) 2022
Masayuki TAKAYAMA
Hitoshi KOSHIBA
Takashi Nicholas MAEDA
Akiyoshi SANNAI
Shohei SHIMIZU
Toshihiko HOSHINO
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
