Course Overview

According to recent studies, the demand in society for data scientists with broad experience in data analysis is increasing. The initial units will focus on the relation among data science, basic mathematics and statistics, aiming at the application to computational algebraic statistics. In the middle units, we will focus on hypothesis testing for actual data and the theory of decision-making based on the predictions. In the last units, students will learn methods of analysis on the basis of informetric data. In particular, the sample-size dependency of informetric indicators will also be discussed.

Learning Achievement

(1) To understand the mathematical basics for the discussed algorithms, and to develop the ability to solve the problems using mathematical software.
(2) To understand the hypothesis testing methods and to use data analysis results for real-world problems.
(3) To understand the nature of informetric data, and to develop the ability to perform data analysis.

Competence

Knowledge application competence, Quantitative research competence, Media expertise
System expertise, Resource expertise

Course prerequisites

Grading Philosophy

Tasks based on the items indicated in the goals will be assigned multiple times, and three parts (1)-(3), (4)-(7), (8)-(10) will be evaluated as one theme each.
The degree of understanding of the assignment and the degree of completeness of the report, etc. are used as evaluation items, and the results are quantified.
For the entire subject, each theme is totaled with the weight at 3:4:3, and those with a total score of 60 points or more will pass.

Course schedule

(1) Components of data science and statistics (Moritsugu)
(2) Mathematical bases for data analysis: correlation, cause and effect, regression analysis (Moritsugu)
(3) Application to data analysis by computational algebraic statistics (Moritsugu)
(4) Data analysis using statistical tests: basic concepts of test theory (Ito)
(5) Differential equations and mathematical models: ecosystems models, epidemiology models, etc. (Ito)
(6) Causal inference and verification of intervention effects (Ito)
(7) Decision making using prediction: value of information, utilization of decision analysis (Ito)
(8) Open data resources and Lotka type data (Yoshikane)
(9) Sample size dependency and binomial interpolation and extrapolation (Yoshikane)
(10) Analyses using informetric indicators (Yoshikane)

Course type

Lectures

Online Course Requirement

Instructor

Moritsugu Shuichi,ITO Hiroyoshi,Yoshikane Fuyuki

Other information

Classes will be conducted face-to-face.
Manaba is used for instructions on report assignments.

Site for Inquiry

Link to the syllabus provided by the university