Multidimensional analysis

Abstract: This paper offers a new methodology for analyzing individual differences in preference judgments with regard to a set of stimuli prespecified in a multidimensional attribute space. The individual is modelled as possessing an “ideal point” denoting his most preferred stimulus location in this space and a set of weights which reveal the relative saliences of the attributes. He prefers those stimuli which are “closer” to his ideal point (in terms of a weighted Euclidean distance measure). A linear programming model is proposed for “external analysis”i.e., estimation of the coordinates of his ideal point and the weights (involved in the Euclidean distance measure) by analyzing his paired comparison preference judgments on a set of stimuli, prespecified by their coordinate locations in the multidimensional space. A measure of “poorness of fit” is developed and the linear programming model minimizes this measure overall possible solutions. The approach is fully nonmetric, extremely flexible, and uses paired comparison judgments directly. The weights can either be constrained nonnegative or left unconstrained. Generalizations of the model to consider ordinal or interval preference data and to allow an orthogonal transformation of the attribute space are discussed. The methodology is extended to perform “internal analysis,”i.e., to determine the stimuli locations in addition to weights and ideal points by analyzing the preference judgments of all subjects simultaneously. Computational results show that the methodology for external analysis is “unbiased”—i.e., on an average it recovers the “true” ideal point and weights. These studies also indicate that the technique performs satisfactorily even when about 20 percent of the paired comparison judgments are incorrectly specified.

Abstract: Nonnegative matrix factorization (NMF) and its extensions such as Nonnegative Tensor Factorization (NTF) have become prominent techniques for blind sources separation (BSS), analysis of image databases, data mining and other information retrieval and clustering applications. In this paper we propose a family of efficient algorithms for NMF/NTF, as well as sparse nonnegative coding and representation, that has many potential applications in computational neuroscience, multi-sensory processing, compressed sensing and multidimensional data analysis. We have developed a class of optimized local algorithms which are referred to as Hierarchical Alternating Least Squares (HALS) algorithms. For these purposes, we have performed sequential constrained minimization on a set of squared Euclidean distances. We then extend this approach to robust cost functions using the alpha and beta divergences and derive flexible update rules. Our algorithms are locally stable and work well for NMF-based blind source separation (BSS) not only for the over-determined case but also for an under-determined (over-complete) case (i.e., for a system which has less sensors than sources) if data are sufficiently sparse. The NMF learning rules are extended and generalized for N-th order nonnegative tensor factorization (NTF). Moreover, these algorithms can be tuned to different noise statistics by adjusting a single parameter. Extensive experimental results confirm the accuracy and computational performance of the developed algorithms, especially, with usage of multi-layer hierarchical NMF approach [3].

Abstract: At the heart of all OLAP or multidimensional data analysis applications is the ability to simultaneously aggregate across many sets of dimensions. Computing multidimensional aggregates is a performance bottleneck for these applications. This paper presents fast algorithms for computing a collection of group bys. We focus on a special case of the aggregation problem - computation of the CUBE operator. The CUBE operator requires computing group-bys on all possible combinations of a list of attributes, and is equivalent to the union of a number of standard group-by operations. We show how the structure of CUBE computation can be viewed in terms of a hierarchy of group-by operations. Our algorithms extend sort-based and hashbased grouping methods with several .optimizations, like combining common operations across multiple groupbys, caching, and using pre-computed group-by8 for computing other groupbys. Empirical evaluation shows that the resulting algorithms give much better performance compared to straightforward meth

Abstract: Recent trends on measurement of well-being have elevated the scientific standards and rigor associated with approaches for national and international comparisons of well-being One major theme in this has been the shift toward multidimensional approaches over reliance on traditional metrics such as single measures (eg happiness, life satisfaction) or economic proxies (eg GDP) To produce a cohesive, multidimensional measure of well-being useful for providing meaningful insights for policy, we use data from 2006 and 2012 from the European Social Survey (ESS) to analyze well-being for 21 countries, involving approximately 40,000 individuals for each year We refer collectively to the items used in the survey as multidimensional psychological well-being (MPWB) The ten dimensions assessed are used to compute a single value standardized to the population, which supports broad assessment and comparison It also increases the possibility of exploring individual dimensions of well-being useful for targeting interventions Insights demonstrate what may be masked when limiting to single dimensions, which can create a failure to identify levers for policy interventions We conclude that both the composite score and individual dimensions from this approach constitute valuable levels of analyses for exploring appropriate policies to protect and improve well-being