Lecture / 講義

Adv. lecture on System dynamics (2021, Spring semester, Thursday, 16:30-18:00, Online, Dr. Shogo OKAMOTO)

システム・ダイナミクス特論(R3年,前期,木曜日16:30-18:00, オンライン, 岡本 正吾 准教授)

Course purpose

Substantial difficulties of dynamic systems in the real world lie in the involvement of a large number of related factors that deviate statistically. Multivariate analyses and statistics are common tools for understanding and modeling these intricate systems. This course is arranged for those who had few opportunities to study statistics, multivariate analyses, and some basis for these mathematics. We learn intermediate topics of classic multivariate analyses and related statistics. We also practice how to apply each method of multivariate analysis on real data and interpret the results throughout the course.

Online course

On-demand videos will be provided on NUCT. Note that if you were late to register on the course, your ID will also appear late in NUCT. If you want me to manually register your name on NUCT, please, tell me your name and student ID number via e-mail.

What you will learn

Multi-variate analysis techniques and underlining mathematics


Based on 3 reports and one final presentation.


Dr. Shogo OKAMOTO, shogo.okamoto (at) mae.nagoya-u dot jp

Matlab data file

baseball2013.mat   baseball2016.mat

Archive and schedule

15-Apr Introduction & Multiple regression analysis 1
Matlab sample file: class1.m

22-Apr Multiple regression analysis 2
Matlab sample file: class2.m   baseball2016.mat

6-May Outlier analysis
Matlab sample file: WhiskerPlot.m MahalanobisDistance.m

Report 1 Multiple regression analysis, Due: May 20th 18:00
Analyse your own data by using multiple regression analysis. Your presentation style report (less than 11 pages) should include

13-May Principal component analysis 1
Matlab sample file: class4.m

20-May Principal component analysis 2
Matlab sample file: class51.m   class52.m

27-May Factor analysis
Matlab sample file:

Report 2 Principal component analysis or factor analysis, Due: Jun. 14th
Analyse your own data by using principal component analysis. Your ~10-page presentation-style report should include

3-Jun. Discrimination analysis 1
Lecture note:

10-Jun. No class because of Univ. festival

17-Jun. Discrimination analysis 2
Matlab sample file:

24-Jun. Structural equation modeling 1
Lecture note:
Matlab sample file:

1-Jul. Structural equation modeling 2
Matlab sample file:

Report 3 Discrimination analysis or structural equation modeling, Due: Jul. 15th

8-Jul. Covariance selection
Lecture note:
Matlab sample file:

15-Jul. Time-series analysis
Lecture note:
Matlab sample file:

22-Jul. Online video presentation by all students (for 1 week)

29-Jul. Final presentaton by selected students