We consider the setting where multiple parties with different variables and units seek to combine their data to fit regressions but are not willing or not allowed to share their data values. We present a general strategy to tackle such problems by treating them as missing data problems, and we estimate regression coefficients using secure EM algorithms. We present secure EM algorithms for linea...

Finite mixtures of regression models offer a flexible framework for investigating heterogeneity in data with functional dependencies. These models can be conveniently used for unsupervised learning on data with clear regression relationships. We extend such models by imposing an eigen-decomposition on the multivariate error covariance matrix. By constraining parts of this decomposition, we obta...

Forty-eight randomly selected age-related human biological functions were analyzed in order to establish whether or not their (linear) regressions were modified by age-related standard errors. Possible reasons for this are advanced. Statistically significant multiple regressions were obtained in 25%, and 21% of the functions yielded statistically significant changes in the correlations between ...

Do established predictors of children’s arithmetic performance differentially predict performance on timed versus untimed calculation tests? We investigated phonological awareness (i.e., CTOPP), phonological working memory (i.e., digit span), and visuo-spatial short-term memory (i.e., Corsi blocks) as predictors of timed and untimed calculation, both concurrently in Grade 1 (N= 116) and longitu...