Showing 1 - 10 of 968
observation. Practical issues related to the specification of initial values, model-based clustering and discriminant procedure …
Persistent link: https://www.econbiz.de/10010665708
This paper describes a way of constructing an ECM algorithm such that it converges at the rate of the EM algorithm. The approach is motivated by the well known conjugate directions algorithm, and a special case of it is when the parameters corresponding to different CM steps are orthogonal....
Persistent link: https://www.econbiz.de/10004980575
functional objects and also find an optimal subspace for clustering, simultaneously. The method is based on the k-means criterion … for functional data and seeks the subspace that is maximally informative about the clustering structure in the data. An …
Persistent link: https://www.econbiz.de/10010846119
matrices, which in turn provides a clear guideline as to when one can use mixture analysis for clustering high dimensional data. …
Persistent link: https://www.econbiz.de/10010572294
clustering approach into the usual panel data model specification. A case study in the field of R&D variables illustrates the …
Persistent link: https://www.econbiz.de/10005008511
Persistent link: https://www.econbiz.de/10005602931
Formulas for estimating sample sizes are presented to provide specified levels of power for tests of significance from a longitudinal design allowing for subject attrition. These formulas are derived for a comparison of two groups in terms of single degree-of-freedom contrasts of population...
Persistent link: https://www.econbiz.de/10010776007
the Self-Organizing Map (SOM). Through the use of SOM clustering and data visualization can be conducted simultaneously …
Persistent link: https://www.econbiz.de/10011143052
Quasi-Monte Carlo (QMC) methods are important numerical tools in the pricing and hedging of complex financial instruments. The effectiveness of QMC methods crucially depends on the discontinuity and the dimension of the problem. This paper shows how the two fundamental limitations can be...
Persistent link: https://www.econbiz.de/10010990531
We introduce a dimension reduction method for model-based clustering obtained from a finite mixture of <InlineEquation … can be projected onto the subspace and the resulting set of variables captures most of the clustering structure available …
Persistent link: https://www.econbiz.de/10010995284