BAYESIAN STATISTICS A

Once you log in, you can use the following functions (Keio ID required).
Affiliation information (faculty, department/major, year level, etc.) is set in the search criteria (available to new students after enrollment).
Favorite (Bookmark)
View syllabus details

Subtitle	（参考）Basics of Bayesian Statistics
Lecturer(s)	HOSHINO, TAKAHIRO
Credit(s)	2
Academic Year/Semester	2022 Spring
Day/Period	Tue.2
Campus	Mita
Class Format	Face-to-face classes (conducted mainly in-person)
Registration Number	45507
Faculty/Graduate School	ECONOMICS
Department/Major	ECONOMICS Type A, B
Year Level	3, 4
Field	MAJOR SUBJECTS ELECTIVE
K-Number	FEC-EC-35113-211-07

Course Administrator	Faculty/Graduate School	FEC	ECONOMICS
Course Administrator	Department/Major	EC	ECONOMICS
Main Course Number	Level	3	Third-year level coursework
	Major Classification	5	Major Subjects Course- Advanced Course
	Minor Classification	11	Lecture - Econometrics and Statistics
	Subject Type	3	Elective subject
Supplemental Course Information	Class Classification	2	Lecture
	Class Format	1	Face-to-face classes (conducted mainly in-person)
	Language of Instruction	1	Japanese
Academic Discipline		07	Economics, business administration, and related fields

Course Description/Objectives/Teaching Method/Intended Learning Outcome

（参考）Bayesian statistics is a paradigm in the field of statistics that makes probabilistic inferences from data and prior knowledge. It overcomes various problems inherent in non-Bayesian statistics (statistics that are based on frequency), has a high affinity with decision making theory, functions as a numerical analysis method that can easily arrive at solutions for complex problems via recently developed Markov chain Monte Carlo methods, and is now being used not only in economics and finance but also in fields such as management studies, medicine, psychology and artificial intelligence. In these lectures, we will discuss differences between Bayesian statistics and non-Bayesian statistics. We will explain how prior probability is updated to posterior probability using Bayes' theorem, on which Bayesian statistics is based; Bayesian decision methods as statistical decision-making; the application of Bayesian inference to normal distribution models or recurrent distribution models; and the various uses of prior distribution.

Course Plan

This item will appear when you log in (Keio ID required).

Method of Evaluation

This item will appear when you log in (Keio ID required).

Reference Books

（参考）Terui, Nobuhiko. R ni yoru beizu tōkei bunseki. Asakura Shoten, 2010. Shigemasu, Kazuo. Beizu tōkei nyūmon. University of Tokyo Press, 1985. Nakatsuma, Teruo. Nyūmon beizu tōkei-gaku. Asakura Shoten, 2007. Nakatsuma, Teruo. Jissen beizu tōkei-gaku. Asakura Shoten, 2013. Matsubara, Nozomu. Beizu tōkei-gaku gaisetsu. Baifūkan, 2010.

Lecturer's Comments to Students

This item will appear when you log in (Keio ID required).

Question/Comments

This item will appear when you log in (Keio ID required).