120 research outputs found
Cause-Effect Pairs in Time Series with a Focus on Econometrics
No full textThis chapter addresses the problem of identifying the causal structure between two time-series processes. We focus on the setting typically encountered in econometrics, namely stationary or difference-stationary multiple autoregressive processes with additive white noise terms. We review different methods and algorithms, distinguishing between methods that filter the series through a vector autoregressive (VAR) model and methods that apply causal search directly to time series data. We also propose an additive noise model search algorithm tailored to the specific task of distinguishing among causal structures on time series pairs, under different assumptions, among which causal sufficiency
Results of the Cause-Effect Pair Challenge
No full textInternational audienceWe organized a challenge in causal discovery from observational data with the aim of devising a “causation coefficient” to score pairs of variables. The participants were provided with a large database of thousands of pairs of variables {X, Y } (80% semi-artificial data and 20% real data) from which samples were drawn independently (i.e. ignoring possible time dependencies). The goal was to discover whether the data supports the hypothesis that Y = f(X, noise), which for the purpose of this challenge was our definition of causality (X causes Y). The participants adopted a machine learning approach, which contrasts with previously published model-based methods. They extracted numerous features of the joint empirical distribution of X and Y and built a classifier to separate pairs belonging to the class “X causes Y” from other cases (“Y causes X”, “X and Y are related” but not in a causal way, a third variable may be causing both X and Y, “X and Y are independent”). The classifier was trained from examples provided by the organizers and tested on independent test data for which the truth values of causal relationships was known only to the organizers. The participants achieved an Area under the ROC Curve (AUC) over 0.8 in the first phase deployed on the Kaggle challenge, which ran from March through September 2013 (round 1). The participants were then invited to improve upon the code efficiency by submitting fast causation coefficients on the Codalab platform (round 2). The causation coefficients developed by the winners have been made available under open source licenses. We have made all data and code publicly available at http://www.causality.inf.ethz.ch/CEdata/
Nashville, Tennessee Approved,
No full textTo my beloved and infinitely supportive wife, Kristina, and to my parents: my mother, Elena Feofilova, and my father, Roman Statnikov ii ACKNOWLEDGEMENTS First of all, I would like to acknowledge my academic advisors, Dr. Constantin F. Aliferis and Dr. Ioannis Tsamardinos, for their contribution to my Master’s project. In addition, I am grateful to Dr. Aliferis for introducing me to the fields of Biomedical Informatics and Machine Learning; training me both a researcher and as a professional scientific programmer; and setting up a framework for my future research and career development. I am also indebted to Dr. Tsamardinos for providing me with excellent technical and scientific ideas that are relevant for my professional and scientific growth. I would also like to thank everybody with whom I had pleasure to work during this project. In particular, I would to express my gratitude to Dr. Douglas P. Hardin and Dr. Shawn Levy who being members of my Master’s committee contributed not only to this project, but also to the journal manuscript based on this work. I would like to acknowledge all Biomedical Informatics faculty and graduate students for their countless contributions to the success of this project. Finally, I am forever indebted to my wife, Kristina Statnikova, for her understanding, endless patience and encouragement. This project would not be possible without her support. iii TABLE OF CONTENTS DEDICATION............................................................................................................................................... i
DBS-PSI: a new paradigm of database search
No full textThe advent of the World Wide Web made search engines the most
essential component of our everyday life. However, the analysis of information
provided by current search engines often presents a significant challenge to the
client. This is to a large extent because the client has to deal with many
alternatives (solutions) described by contradictory criteria, when selecting the
most preferable (optimal) solutions. Furthermore, criteria constraints cannot be
defined a priori and have to be defined interactively in the process of a dialog
of the client with computer. In such situations, construction of the feasible
solution set has a fundamental value. In this paper, we propose a new
methodology for systematically constructing the feasible solution set for
database search. This allows to significantly improving the quality of search
results
Management of constraints in optimization problems
No full textThe article of record as published may be located at http://dx.doi.org/10.1016/j.na.2009.01.170Optimization problems are encountered in all scientific disciplines and in many aspects
of everyday life. Application of established optimization methods assumes that an expert
can state the optimization problem correctly. Unfortunately, this is not the case in reality.
Below we consider how to help an expert state and solve optimization problems. The
proposed technique splits constraints of an optimization problem into ``soft'' (manageable)
and ``rigid'' constraints and modifies the ``soft'' constraints in an interactive mode with the
expert. The technique is illustrated with a numeric example devoted to the optimization of
a real-life nonlinear system
Analysis and computational dissection of molecular signature multiplicity.
No full textMolecular signatures are computational or mathematical models created to diagnose disease and other phenotypes and to predict clinical outcomes and response to treatment. It is widely recognized that molecular signatures constitute one of the most important translational and basic science developments enabled by recent high-throughput molecular assays. A perplexing phenomenon that characterizes high-throughput data analysis is the ubiquitous multiplicity of molecular signatures. Multiplicity is a special form of data analysis instability in which different analysis methods used on the same data, or different samples from the same population lead to different but apparently maximally predictive signatures. This phenomenon has far-reaching implications for biological discovery and development of next generation patient diagnostics and personalized treatments. Currently the causes and interpretation of signature multiplicity are unknown, and several, often contradictory, conjectures have been made to explain it. We present a formal characterization of signature multiplicity and a new efficient algorithm that offers theoretical guarantees for extracting the set of maximally predictive and non-redundant signatures independent of distribution. The new algorithm identifies exactly the set of optimal signatures in controlled experiments and yields signatures with significantly better predictivity and reproducibility than previous algorithms in human microarray gene expression datasets. Our results shed light on the causes of signature multiplicity, provide computational tools for studying it empirically and introduce a framework for in silico bioequivalence of this important new class of diagnostic and personalized medicine modalities
Algorithms for discovery of multiple Markov boundaries: application to the molecular signature multiplicity problem
No full textAutomatic Cancer Diagnostic Decision Support System for Gene Expression Domain
No full textThe success of treatment of patients with cancer depends on establishing an accurate diagnosis. To this end, we have built a system called GEMS (Gene Expression Model Selector) for the automated development and evaluation of high-quality cancer diagnostic models and biomarker discovery from microarray gene expression data. In order to determine and equip the system with the best performing diagnostic methodologies in this domain, we first conducted a comprehensive evaluation of classification algorithms using 11 cancer microarray datasets. After the system was built, we performed a preliminary evaluation of the system with 5 new datasets. The performance of the models produced automatically by GEMS is comparable or better than the results obtained by human analysts. Additionally, we performed a cross-dataset evaluation of the system. This involved using a dataset to build a diagnostic model and to estimate its future performance, then applying this model and evaluating its performance on a different dataset. We found that models produced by GEMS indeed perform well in independent samples and, furthermore, the cross-validation performance estimates output by the system approximate well the error obtained by the independent validation. GEMS is freely available for download for non-commercial use from http://www.gems-system.org
Syndrome analysis of difficulties in comprehending logical grammatical constructions by children
No full textThe article describes the results of the investigation of the mechanisms of logical-grammatical constructions comprehension in students 7-8 y.o. with and without language acquisition disorders. Computer-administered tests were used to assess the ability to comprehend logical-grammatical constructions, as well as the tests of serial organization of speech and movement (traditional and computer-based) and the tests for assessment of the level of visual-spatial perception strategies. Neuropsychological syndrome analysis allowed to conclude that the difficulties of logical-grammatical constructions comprehension are linked to the deficit of visualspatial
perception, which is the common point of view for Russian neuropsychology. Also, the experimental evidences were found, that the understanding of logicalgrammatical construction is closely linked to the serial organization of speech and movements. The character of this connection differs from the character of the connection between the understanding of logical-grammatical constructions and the level of visual-spatial strategies perception, which highlights that these two groups of functions provide different contributions to the process of comprehension of grammatically complex sentences. These findings are interpreted using the theory of systemic dynamic
localization of higher mental functions by Vygotsky-Luria, the model of the three levels of language organization by A.R. Luria and the model of the three levels of syntax by T.V. Akhutina. It is considered that the operations of grammatical re-structuring of complex sentences ontogenetically relate closely to the functions of serial organization of movements and develop on the neighbouring anatomical substrate (posterior parts of frontal cortex). The other aspect of the process of logical-grammatical constructions comprehension, which includes finding of the «reference point», and generation of asymmetrized «quasi-spatial» structure of the sentence, where the thematical roles are
assigned, is linked in the same way to the functions of visual-spatial perception and the anatomical substrate of these functions (temporal-parietal-occipital zone)
- …
