Yoshio Takane

Yoshio Takane has a long standing interest in developing statistical techniques to analyze psychological data. His contributions to the field include developments of nonmetric methods of multivariate analysis, maximum likelihood multidimensional scaling, choice models incorporating systematic individual differences, principal component analysis with linear constraints on both rows and columns of a data matrix, analysis of knowledge representation in neural network models among others.

His most recent interests include regularization techniques for various multivariate data analysis methods, acceleration methods for iterative model fitting, development of structural equation models for analysis of brain connectivity, various kinds of singular value decomposition (e.g., sparse SVD, robust SVD), etc.

Interests

• Multivariate analysis
• Matrix methods in psychometrics
• Computational models for cognition
• Analysis of brain signals

Publications

Hwang, H., Jung, K., Takane, Y., and Woodward, T. S. (in press). A unified approach to multiple-set canonical correlation analysis and principal components analysis. British Journal of Mathematical and Statistical Psychology.

Jung, K., Takane, Y., Hwang, H., and Woodward, T. S. (in press). Dynamic GSCA (Generalized Structured Component Analysis) with applications to the analysis of effective connectivity in functional neuroimaging data. Psychometrika.

Takane, Y., and Zhou, L. (2012). On two expressions of the MLE for a special case of the extended growth curve models. Linear Algebra and Its Applications, 436, 2567-2577.

van de Velden, M., and Takane, Y. (2012). Generalized canonical correlation analysis with missing values. Computational Statistics, 27, 551-571.

Hwang, H., Jung, K., Takane, Y., and Woodward, T. S. (2012). Functional multiple-set canonical correlation analysis. Psychometrika, 77, 48-64.

Takane, Y., and Zhou, L. (2011). Exploratory multilevel redundancy analysis. IPS042.04 (pdf)

Takane, Y., and Hunter, M. A. (2011). A new family of constrained principal component analysis (CPCA). Linear Algebra and Its Applications, 434, 2539-2555.

Yanai, H., Takeuchi, K., Takane, Y. (2011). Projection matrices, generalized inverse matrices, and singular value decomposition. New York: Springer.

Loisel, S., and Takane, Y. (2011). Generalized GIPSCAL Re-revisited: A fast convergent algorithm with acceleration by the minimum polynomial extrapolation. Advances in Data Analysis and Classification, 5, 57-75.

Takane, Y., Jung, K., and Hwang, H. (2011). Regularized growth curve models. Computational Statistics and Data Analysis, 55, 1041-1052.