1st class. 
(Introduction & Multiple regression analysis 1) Apr. 12th 

Lecture note: Introduction.pdf MRA1.pdf 

Matlab sample file. class1.m



2nd class. 
(Multiple regression analysis 2) Apr. 19th 

Lecture note: MRA2.pdf 

Matlab sample file. class2.m
baseball2016.mat 


3rd class. 
(Multiple regression analysis 3) Apr. 26th 

Lecture note: MRA3.pdf 

Matlab sample file. class3.m 


1st report. 
Multiple regression analysis, Due: May 17th @ the class 

Analyse your own data by using multiple regression analysis. Your ~10page presentation style
report should include 

1.  Title (your name, student ID) 
2.  Background of data (what kind of data? why do you want to analyze
personally?) 
3.  Check colinearity of data. 
4.  Objective and explanatory variables 
5.  Results of analysis (regression coefficients, goodness of fit index,
variable selection) 
6.  Interpretation of the results (is the result reasonable? what did
you find behind the data?) 
Submit a ppt or pdf file by email (shogo.okamoto(at)mae.nagoyau.ac.jp).
See a sample of report.



4th class. 
(Principal component analysis 1) May 10th 

Lecture note: PCA.pdf


Matlab sample file. class4.m 


5th class. 
(Principal component analysis 2) May 17th 

Matlab sample file. class51.m class52.m 


6th class. 
(Principal component analysis 3) May 24th 

Lecture note: PCA.pdf


Matlab sample file. class6.m 


2nd report. 
Principal component analysis, Due: Jun. 14th @ the class 

Analyse your own data by using principal component analysis. Your ~10page presentationstyle
report should include 

1.  Title (your name, student ID) 
2.  Background of data (what kind of data? why do you want to analyze
personally?) 
3.  Scree diagram and contribution ratios of components (how many components
should you use?) 
4.  Table or matrix of PC coefficients before/after rotation 
5.  Interpretation of the results (is the result reasonable? what did you
find behind the data?) 
Submit a ppt or pdf file by email (shogo.okamoto(at)mae.nagoyau.ac.jp).
See a sample of report.



7th class. 
(Structural equation modeling 1) May 31th 

Lecture note: SEM.pdf



No class 
Jun. 7th 
No class 
Jun. 14th (No class because of Univ. festival) 


8th class. 
(Structural equation modeling 2) Jun. 21th 

Lecture note: SEM.pdf


Matlab sample file. 

Link model: link.m mylink.m


Latent factor model: fa.m myfa.m


Sequential model: sequential.m
mysequential.m


Regression model: regress.m
myregress.m


MIMIC model: mimic.m mymimic.m
baseball_data.m



3rd report. 
Structural equation modeling, Due: Jul. 12th by email. 

1.  Title (your name, student ID) 
2.  Background of data (what kind of data? why do you want to analyze
personally?) 
3.  Choose (at least) three variables, and compare at least two models to
which the data may fit.
Describe which models you selected.
Show the observed and estimated correlation coefficients.
Draw the estimated models with effect values, error variances, and GFI.

4.  Table or matrix of PC coefficients before/after rotation 
5.  Interpretation of the results. 
Submit a ppt or pdf file by email (shogo.okamoto(at)mae.nagoyau.ac.jp).
See a sample of report.



9th class. 
(Covariance selection) Jun. 28th 

Lecture note: CovarianceSelection.pdf


Matlab sample file. class10.m


