• About Me

    Hi, I'm Motonori Oka (岡 元紀).

    I am pursuing an MPhil/PhD (Statistics) in the Social Statistics Group in the Department of Statistics at the London School of Economics and Political Science (LSE). I am very fortunate to have the great opportunity to do my PhD research under the supervision of Yunxiao Chen and Irini Moustaki in the Psychometrics Lab.

    Prior to the LSE, I received M.A. in Education from the University of Tokyo and B.A. in Psychology from University of Tsukuba, Japan.

     

    My primary research interests lie broadly in statistics and machine/deep learning for the education and social sciences, with specific devotion to methodological advancement in latent variable modeling that contributes to the better understanding of the complex phenomena behind human behaviors. The thrust of my research has been centered on scalable psychometrics, education data science, and statistics education. In particular, I am interested in scalable estimation algorithms and their theory of latent factor models and explainable deep learning models in educational/psychological measurements.
    Additionally, I like running and studying the philosophy of science.

  • Publications

    Referred Articles

    Preprints

    • Oka, M., & Okada, K. (2021). Assessing the performance of diagnostic classification models in small sample contexts with different estimation methods. arXiv. https://arxiv.org/abs/2104.10975

     

     

    Presentations

    Invited Presentations

    • Okada, K., Fukushima, K., & Oka, M. (2022). Diagnostic classification modeling for making the most use of item response data [Oral presentation]. Japanese Joint Statistical Meeting 2022 JSS-KSS-CSA Joint Session: Complex Data Analysis, Tokyo, Japan.
    • Saso, S., Oka, M., Shiba, S., & Uesaka, Y. (2022). The practical application of cognitive diagnostic models to encourage students’ deep understanding and use of effective learning strategies [Oral presentation]. The 11th Conference of the Asian Regional Section of the International Association for Statistical Computing (IASC-ARS) 2022, Kyoto, Japan.

    Referred Presentations

    • Saso, S., Oka, M., & Uesaka, Y. (accepted). Development of assessment tools for depth of understanding quantitatively with cognitive diagnostic models [Poster presentation]. Future of Information and Communication Conference (FICC) 2023, Online.
    • Hijikata, K., Oka, M., Yamaguchi, K., & Okada, K. (2022). The development of "variationalDCM" an R package performing variational Bayesian estimation for DCMs [Oral presentation]. The 15th International Conference of the ERCIM WG on Computational and Methodological Statistics (CMStatistics) 2022, London, United Kingdom.
    • Saso, S., Oka, M., & Uesaka, Y. (2021). How can we statistically gauge students’ deep understanding from high school regular tests? [Poster presentation]. Junior Researchers of European Association for Research on Learning and Instruction (JURE) 2021, Online. (equal contribution
    • Oka, M., & Okada, K. (2021). New iterative algorithm for the DINA Q-matrix estimation [Oral presentation]. International Meeting of Psychometric Society (IMPS) 2021, Online. 
    • Oka, M., Saso, S., & Okada, K. (2021). Parallelized variational Bayesian algorithm for the polytomous-attribute saturated diagnostic classification model [Oral presentation]. World Meeting of the International Society for Bayesian Analysis (ISBA) 2021, Online. 
    IN JAPANESE
    • Saso, S., Oka, M., & Uesaka, Y. (2022). Application of cognitive diagnostic models for quantitative assessment of depth of understanding and its proposed process: Q-matrix design utilizing the findings of psychology and mathematical education and Q-matrix estimation [Poster presentation]. The 39th Annual Meeting of Japanese Cognitive Science Society, Tokyo, Japan. (in Japanese)
     

    Non-Referred Presentations

    IN JAPANESE

    • Saso, S., Oka, M., Shiba, S., & Uesaka, Y. (2022). Quantatively evaluating the degree of student's understanding and instructing learning strategies: Practical applications of cognitive diagnostic models and student's responses [Poster presentation]. The 20th conference of the Japan Association for Research on Testing, Online. (in Japanese)
    • Oka, M., & Okada, K. (2021). Learning latent structures in Q-restricted latent class models with a non-compensatory assumption [Oral presentation]. Japanese Joint Statistical Meeting 2021 Competition Session, Online. (in Japanese)
    • Saso, S., Oka, M., & Uesaka, Y. (2021). An empirical analysis of deep understanding through cognitive diagnostic models: Analysis using a large-scale standardized achievement test and its comparison with traditional perspectives [Oral presentation]. The 19th conference of the Japan Association for Research on Testing, Online. (in Japanese)
    • Saso, S., Oka, M., & Uesaka, Y. (2021). Measuring deep understanding and its application to regular examinations: Applying cognitive diagnostic models to teaching practice and the responses from classroom teachers [Oral presentation]. Spring conference 2021 of the Japan Society of Educational Technology, Online. (in Japanese) 
    • Oka, M., & Okada, K. (2020). Assessing the performance of Q-matrix estimation in a large-scale assessment [Oral presentation]. Young Researchers’ Seminar 2020 of the Japanese Society of Computational Statistics, Online. (in Japanese) 
    • Oka, M., & Okada, K. (2020). Q matrix estimation algorithm using variational inference and stochastic optimization [Oral presentation]. The 48th annual meeting of the Behaviormetric Society, Tokyo, Japan. (Conference canceled) 
    • Oka, M., & Okada, K. (2020). Q matrix estimation algorithm combined with variational inference and sampling technique [Oral presentation]. The 34th conference of the Japanese Society of Computational Statistics, Online. (in Japanese)
  • Awards and Honors

    2022

    Scholarship for Postgraduate Study in UK

    Keidanren Ishizaka Memorial Foundation & The Tokyo Club

     

    2021 (offered/declined)

    Research Fellowship for Young Scientists (DC1)

    The Japan Society for the Promotion of Science (JSPS)

     

    2020

    Student Research Presentation Award

    The 34th conference of the Japanese Society of Computational Statistics

  • Contact

    EMAIL: m.oka1[at]lse.ac.uk

    Please replace [at] with @ when you send an email to me.