科学技術政策研究：経済学系（Data Science for Public Policy）

Module 1: How to Run Statistical Software (3 weeks) Week 1: The Easy Way to Code and Useful Tools Week 2: Acquiring Data through APIs Week 3: Data Manipulation and Cleaning Techniques Module 2: Visualization (3 weeks) Week 4: Introduction to Data Visualization Week 5: Interactive and Geographic Visualizations Week 6: Data Visualization for Policy Communication Module 3: Text Analysis (3 weeks) Week 7: Text as data (the basics to ChatGPT) Week 8: Using Deepseek-like open source LLMs via Hugging Face Module 4: Modeling (4 weeks) Week 9: Basic Statistical Models (OLS) Week 10: Panel Data (Fixed Effects) Week 11: Time Series Analysis Week 12: Machine Learning Week 13: Presentations

Students will watch instructor-made YouTube tutorials covering coding demonstrations and lecture content before class meetings, enabling more time for hands-on practice during our sessions All course materials and code will be hosted on GitHub, giving students experience with professional version control tools while ensuring easy access to content

Milestone 1 (Due after Module 1): Data Selection and Research Question (20%) - Choose a dataset relevant to the course content. - Formulate a specific, testable research question that can be addressed using the chosen dataset. - Import and manipulate the data and show descriptive statistics in table or graphs - Submit a brief (1-2 paragraph) written description of the research question, explaining its significance and how the dataset will be used to investigate it. Milestone 2 (Due after Module 2): Data Visualization and Interpretation (20%) - Create at least 5 different visualizations (including charts) of the dataset - Write a short description of each visualization, explaining what information it conveys and how it relates to the research question. Milestone 3 (Due after Module 3): Statistical Modeling or Text Analysis (20%) - Choose and implement a specific statistical model or text analysis technique that is appropriate for the research question and the type of data. For example, if your research question involves comparing groups, you might use a t-test. If it involves relationships between variables, you might use regression. If it involves text data, you might use sentiment analysis or topic modeling. - Justify your choice of model or technique, explaining why it is suitable for addressing the research question. - Present the results of your analysis, including relevant statistics and visualizations. - Discuss the limitations of your chosen method. Group Presentation: 40% Students will communicate findings via final slide presentation. Presentation Rubric: Clarity of research question and methodology (10%) Effectiveness of data visualization (10%) Appropriateness and rigor of statistical modeling or text analysis (10%) Clarity and organization of presentation (10%)

N/A

No knowledge of any of the methods in these textbooks are required. Beginners should not be discouraged if they do not understand the following resources. These are simply recommendations for those interested: Data Science & Statistics •Chen, J.C., Rubin, E.A., & Cornwall, G.J. (2021). Data science for public policy. Springer. •Hansen, B.E. (2022). Econometrics. University of Wisconsin-Madison. •Hansen, B.E. (2022). Probability and Statistics for Economists. University of Wisconsin-Madison. •Hastie, T., Tibshirani, R., & Friedman, J. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer. •James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An Introduction to Statistical Learning, with applications in R. Springer. •James, G., Witten, D., Hastie, T., Tibshirani, R., & Taylor, J. (2023). An introduction to statistical learning: With applications in Python. Springer Nature. •Pawitan, Y. (2013). In All Likelihood: Statistical Modelling and Inference Using Likelihood. Oxford University Press. •Rogers, S., & Girolami, M. (2017). A First Course in Machine Learning (2nd ed). Chapman & Hall. Python Programming & Data Science •Downey, A. (2015). Think Python: How to Think Like a Computer Scientist (2nd ed.). O'Reilly Media. •Downey, A. (2015). Think Stats: Exploratory Data Analysis in Python (2nd ed.). O'Reilly Media. •Downey, A. (2016). Think Bayes: Bayesian Statistics in Python. O'Reilly Media. •Downey, A. (2014). Think DSP: Digital Signal Processing in Python. O'Reilly Media. •Lutz, M. (2013). Learning Python (5th ed.). O'Reilly Media. •McKinney, W. (2022). Python for Data Analysis: Data Wrangling with pandas, NumPy, and Jupyter, 3rd Edition. O'Reilly Media. •Ramalho, L. (2022). Fluent Python: Clear, Concise, and Effective Programming (2nd ed.). O'Reilly Media. Economics & Forecasting •Ash, E., & Hansen, S. (2023). Text algorithms in economics. Annual Review of Economics, 15(1), 659-688. •Diebold, F.X. (2017). Forecasting in Economics, Business, Finance and Beyond. University of Pennsylvania. •Elliott, G., & Timmermann, A. (2006). Economic Forecasting. Princeton University Press. •Fuleky, P. (Ed.). (2020). Macroeconomic Forecasting in the Era of Big Data: Theory and Practice. Springer. •Ghysels, E., & Marcellino, M. (2018). Applied Economic Forecasting using time series methods. Oxford University Press. •Hamilton, J.D. (1994). Time Series Analysis. Princeton University Press. YouTube Tutorials •3Blue1Brown: YouTube Channel •Khan Academy: Khan Academy Computing •Codecademy: Codecademy YouTube Channel •Data Science & Statistics oStatistics for Data Analytics/ Data Science | Complete Statistics Tutorial by Tech Classes Statistics for Data Analytics/ Data Science | Complete Statistics Tutorial oStatistics Course for Data Science | Statistics Course for Data Analytics | MarinStatsLectures by MarinStatsLectures-R Programming & Statistics Statistics Course for Data Science | Statistics Course for Data Analytics | MarinStatsLectures •Python Programming & Data Science oPython Tutorial: Learn Python For Data Science by DataCamp Python Tutorial: Learn Python For Data Science oData Science Full Course For Beginners | Python Data Science Tutorial | Data Science With Python by codebasics Data Science Full Course For Beginners | Python Data Science Tutorial | Data Science With Python •Barba, L., & Wang, T. (2019). Land on Vector Spaces: Practical Linear Algebra with Python | SciPy 2019 Tutorial.

This course welcomes students of all backgrounds, from beginners to those with deep coding and statistical modeling experience. The instructor has extensive experience teaching programming to diverse backgrounds, including many students who have never written a line of code or studied matrix algebra. Through hands-on exercises, and personalized support, students from all backgrounds will develop the technical skills needed to apply data science to policy problems.