The Experts below are selected from a list of 11061 Experts worldwide ranked by ideXlab platform
Benjamin Granger - One of the best experts on this subject based on the ideXlab platform.
-
Response to: 'On using machine learning algorithms to define clinically meaningful patient subgroups' by Pinal-Fernandez and Mammen.
Annals of the rheumatic diseases, 2019Co-Authors: Olivier Benveniste, Yves Allenbach, Benjamin GrangerAbstract:We have read with interest the comment from Pinal-Fernandez and Mammen in which they question the statistical clustering methods based on unsupervised learning analyses to define clinically meaningful patient subgroups.1 Pinal-Fernandez and Mammen base their arguments on the production of an analysis according to this methodology made on a random simulated data set that would highlight the formation of three clusters, in fact arbitrary. It is important to point out that the example which forms the basis of their argument is ill-chosen because it shows a misguided use of this type of technique. Indeed, before applying a clustering method …
Alaric Kohler - One of the best experts on this subject based on the ideXlab platform.
-
A Relational Ontology for Psychology: Life as an Asymmetric Subjet-Object Choosing Relation
Integrative Psychological and Behavioral Science, 2019Co-Authors: Alaric KohlerAbstract:This review of Mammen’s new book (2017), provides a brief summary of the first part, stressing the main points of the author’s constructive critique of the unfortunate issues psychology inherited from the atomistic mechanism of classical physics. Driving the discussion on the ontological level, Mammen briefly shows how nowadays natural sciences provide the main components psychology needs to overcome the everlasting crisis of psychology since its constitution as a science: discontinuity, contextuality, etc. Making of the relation between subject and object the foundation of any science, Mammen contributes to a new ontology specific to human study with elements of last century mathematics, notably the axiom of choice , bridging the rift between natural and human sciences with a continuum from inert matter to more or less advanced life forms. Mammen’s constructive proposal opens the building site of a new foundation for life sciences, avoiding both simplistic mechanism and nihilist post-modernism.
-
A Relational Ontology for Psychology: Life as an Asymmetric Subjet-Object Choosing Relation : Review of A New Logical Foundation for Psychology, J. Mammen, Springer, 2017.
Integrative psychological & behavioral science, 2018Co-Authors: Alaric KohlerAbstract:This review of Mammen’s new book (2017), provides a brief summary of the first part, stressing the main points of the author’s constructive critique of the unfortunate issues psychology inherited from the atomistic mechanism of classical physics. Driving the discussion on the ontological level, Mammen briefly shows how nowadays natural sciences provide the main components psychology needs to overcome the everlasting crisis of psychology since its constitution as a science: discontinuity, contextuality, etc. Making of the relation between subject and object the foundation of any science, Mammen contributes to a new ontology specific to human study with elements of last century mathematics, notably the axiom of choice, bridging the rift between natural and human sciences with a continuum from inert matter to more or less advanced life forms. Mammen’s constructive proposal opens the building site of a new foundation for life sciences, avoiding both simplistic mechanism and nihilist post-modernism.
Stefan Sperlich - One of the best experts on this subject based on the ideXlab platform.
-
Discussion: Nonparametric estimation of noisy integral equations of the second kind
Journal of The Korean Statistical Society, 2009Co-Authors: Stefan SperlichAbstract:Abstract This is a discussion of the paper “Nonparametric estimation of noisy integral equations of the second kind” by Enno Mammen and Kyusang Yu.
-
Feasible estimation in generalized structured models
Statistics and Computing, 2009Co-Authors: Javier Roca-pardiñas, Stefan SperlichAbstract:This article introduces a feasible estimation method for a large class of semi and nonparametric models. We present the family of generalized structured models which we wish to estimate. After highlighting the main idea of the theoretical smooth backfitting estimators, we introduce a general estimation procedure. We consider modifications and practical issues, and discuss inference, cross validation, and asymptotic theory applying the theoretical framework of Mammen and Nielsen (Biometrika 90: 551---566, 2003). An extensive simulation study shows excellent performance of our method. Furthermore, real data applications from environmetrics and biometrics demonstrate its usefulness.
-
Estimating Generalized Structured Models- A Computational Note
2009Co-Authors: Javier Roca Pardinas, Stefan Sperlich, Georg-august Universität GöttingenAbstract:This work is to highlight details on computational issues and in particular fast of the weighted smooth backfitting estimator for generalized structured models. Roca Pardiñas and Sperlich (2007) introduced an estimation method for a rather large set of models which is referred as ”generalized structured models”, see Mammen and Nielsen (2003). This estimator has turned out to be not only rather effective in estimating all kind of models but also to be quite efficient in the statistical sense. However, implementation is by far not trivial. Therefore, this note is aimed to make the procedure understandable and usable for a large audience. The procedures will be made available in R.
-
Efficient Estimation of Generalized Structured Models
SSRN Electronic Journal, 2007Co-Authors: Javier Roca Pardinas, Stefan SperlichAbstract:This article picks up the discussion on semi- and nonparametric generalized structured models by Mammen & Nielsen (2003). We introduce a general feasible estimator based on weighted smooth backfitting that can be used not only for most of the therein presented models. Moreover, we give further examples of statistical models of broad interest which can be handled by our procedure. The procedure is derived on the base of the results of Nielsen & Sperlich (2005) whereas asymptotic theory can be deduced from Mammen & Nielsen (2003). We discuss practical issues like implementation and computation, provide simulation studies and demonstrate the practical use along real data examples.
Olivier Benveniste - One of the best experts on this subject based on the ideXlab platform.
-
Response to: 'On using machine learning algorithms to define clinically meaningful patient subgroups' by Pinal-Fernandez and Mammen.
Annals of the rheumatic diseases, 2019Co-Authors: Olivier Benveniste, Yves Allenbach, Benjamin GrangerAbstract:We have read with interest the comment from Pinal-Fernandez and Mammen in which they question the statistical clustering methods based on unsupervised learning analyses to define clinically meaningful patient subgroups.1 Pinal-Fernandez and Mammen base their arguments on the production of an analysis according to this methodology made on a random simulated data set that would highlight the formation of three clusters, in fact arbitrary. It is important to point out that the example which forms the basis of their argument is ill-chosen because it shows a misguided use of this type of technique. Indeed, before applying a clustering method …
Olga Kubassova - One of the best experts on this subject based on the ideXlab platform.
-
Augmented versus artificial intelligence for stratification of patients with myositis.
Annals of the rheumatic diseases, 2019Co-Authors: Michael Mahler, Brenden Rossin, Olga KubassovaAbstract:With interest we read the recent article by Pinal-Fernandez and Mammen,1 which comments on the paper by Spielmann et al 2 and to a lesser extent on the contribution by Mariampillai et al 3 4 and raises concerns about the artificial intelligence (AI)-driven approach used to define subgroups of patients with idiopathic inflammatory myopathy (IIM). To illustrate this, Pinal-Fernandez and Mammen constructed a library of 1000 observations and selected the four variables using a multivariate normal distribution, thus finding a similar clustering as in the original paper by Spielmann et al .2 We share some of the concerns about unsupervised learning techniques raised by Pinal-Fernandez …