Analysis of asymmetric relationships data (description)
Recent Research Report
Report on common methods for comparison of Means (e.g., two-groups t-procedure, ANOVA): Comparing the Student's t and the ANOVA contrast procedure with five alternatives.
pdf version full paper
Master thesis by Wobbe Zijlstra, University of Groningen.
(Abstract: pdf version of abstract)
Teaching
Research Master specialization in Psychometrics and Statistics
(Research Master)
Program for SIMPLIMAX Oblique simple structure rotation
This program can be downloaded here: file: Simplimax.exe (use right mouse click, and 'save target as' command).
A description of the program can be found here: Simplimax.doc.
The program is a PASCAL based executable program (written for MS-DOS)
Main reference: Kiers, H.A.L. (1994). SIMPLIMAX: Oblique rotation to an optimal target with simple structure.
Psychometrika, 59, 567-579.
Matlab program files for several applications
Three-mode component analysis (Tucker3): Threeway m-files.zip (use right mouse click, and 'save target as' command)
Use: unzip zipped file; run "tucker3.m"
Main reference: Kiers, H.A.L., & van Mechelen, I. (2001).Three-way component analysis: Principles and illustrative application.
Psychological Methods, 6 , 84-110.
INDCLUS (Individual Differences Cluster Analysis: indclus.zip (use right mouse click, and 'save target as' command)
Use: unzip zipped file; run "indclus.m"; documention in Word file indclus.doc
Main reference: Kiers, H.A.L. (1997). A modification of the SINDCLUS algorithm for fitting the
ADCLUS and INDCLUS models. Journal of Classification, 14, 297-310.
Multi Trait Multi Method Componenent Analysis : mtmm-ca.zip (use right mouse click, and 'save target as' command)
Use: unzip zipped file; run "mtmm.m"; program is interactive; description of method can be found in article, also in zip-file
Main reference: Kiers, H.A.L., Takane, Y., & Ten Berge, J.M.F. (1996)
The analysis of Multitrait-Multimethod matrices via constrained components analysis. Psychometrika, 61, 601-628.
Orthogonal Congruence Rotation: Orthog Congr Rotation.zip (use right mouse click, and 'save target as' command)
Use: unzip zipped file; run "OrthCongRot.m"; program is interactive; description of method can be found in article, also in zip-file
Main reference: Kiers, H.A.L., & Groenen, P. (1996) A monotonically convergent algorithm for orthogonal congruence rotation.Psychometrika, 61, 375-389.
Zero correlated constrained Parafac: Zero Correlated Parafac.zip (use right mouse click, and 'save target as' command)
Use: unzip zipped file; you will get three matlab script files containing parafac routines; cpfunc.m gives the ordinary Parafac algorithm, and has the zero correlations constraint as an option.
To see how to use this function, first type (in Matlab) "help cpfunc".
The m-files Parafac "UncorrColumns Alg 1'.m" and "Parafac UncorrColumns Alg 2'.m" use the two fast algorithms described in the article referred to below.
In addition you will find some auxiliary files needed to run these script files.
Main reference: Kiers,H.A.L. & Harshman, R.A. (resubmitted). An Efficient Algorithm for Parafac with Uncorrelated Mode-A Components Applied to Large IxJxK Data Sets with I>>JK.
Discussion Forum on Practical Data Analysis
What kind of techniques are really needed in practice?
Can we actually analyse the current types of data (huge, complexly structured) with
the classical statistical techniques?
If researchers don't understand statistical techniques very well, shouldn't we conclude that
the methods we offer are useless?
In teaching statistics, do we pay enough attention to the analysis of current types of data?
How do we avoid that researchers use statistics as a ritual? How to learn them statistical thinking instead?
I think we (i.e., scientists involved in data analysis / statistics) should try to find answers to such questions before long. It is
planned to start a formal web discussion on these topics under the auspices of the IFCS (International Federation of Classification Societies).
In the mean time, suggestions or comments are welcome at my email address.
A similar intitative can be expected in the Foodmetrics network. This is an
interdisciplinary network of researchers interested in application of data analysis techniques.
Downloadable Book: Kiers, H.A.L. (1989) Three-way methods for the analysis of qualitative and quantitative
two-way data, Leiden: DSWO Press.
Kiers, H.A.L., & van Mechelen, I. (2001).Three-way component analysis: Principles and illustrative application.
Psychological Methods, 6 , 84-110.
Kiers, H.A.L. (2001) Leven in onzekerheid en eenvoud. De Psycholoog, 36, 226-233.
(inaugural address (in Dutch))
Kiers, H.A.L. (2002) Setting up Alternating Least Squares and Iterative Majorization Algorithms for Solving Various Matrix Optimization Problems,
Computational Statistics and Data Analysis,41,157-170.
Kiers, H.A.L. (2004) Bootstrap Confidence Intervals for Three-way Methods.Journal of Chemometrics,18,22-36.
(view powerpoint slides)
Sigrist, M., Keller.C., & Kiers, H.A.L. (2005) A new look at the psychometric paradigm of perception of hazards. Risk Analysis, 25, 211-222.
Kiers, H.A.L., Vicari, D., & Vichi, M. (2005) Simultaneous Classification and Multidimensional Scaling with External Information. Psychometrika, 70, 433-460.
Kiers, H.A.L. (2006) Properties of and algorithms for fitting three-way component models with offset terms, Psychometrika, 71, 231-257. (download Addendum to this article)
Kiers, H.A.L., & Smilde, A.K. (2007) A comparison of various methods for Multivariate Regression with highly collinear variables. Statistical Methods and Applications, 16, 193-228.
