Oblique Procrustean Transformations to Fit an Incompletely Specified Target Matrix

1969 ◽  
Author(s):  
Stanley A. Mulaik
Keyword(s):  
Target Matrix ◽  
Procrustean Transformations

scholarly journals Centered Kernel Alignment Enhancing Neural Network Pretraining for MRI-Based Dementia Diagnosis

2016 ◽  
Vol 2016 ◽  
pp. 1-10 ◽  
Author(s):  
David Cárdenas-Peña ◽  
Diego Collazos-Huertas ◽  
German Castellanos-Dominguez
Keyword(s):  
Neural Network ◽  
Characteristic Curve ◽  
Principal Component ◽  
Imaging Data ◽  
Resonance Imaging ◽  
Dementia Diagnosis ◽  
Target Matrix ◽  
Computer Aided ◽  
Artificial Neural Network Ann ◽  
Aided Diagnosis

Dementia is a growing problem that affects elderly people worldwide. More accurate evaluation of dementia diagnosis can help during the medical examination. Several methods for computer-aided dementia diagnosis have been proposed using resonance imaging scans to discriminate between patients with Alzheimer’s disease (AD) or mild cognitive impairment (MCI) and healthy controls (NC). Nonetheless, the computer-aided diagnosis is especially challenging because of the heterogeneous and intermediate nature of MCI. We address the automated dementia diagnosis by introducing a novel supervised pretraining approach that takes advantage of the artificial neural network (ANN) for complex classification tasks. The proposal initializes an ANN based on linear projections to achieve more discriminating spaces. Such projections are estimated by maximizing the centered kernel alignment criterion that assesses the affinity between the resonance imaging data kernel matrix and the label target matrix. As a result, the performed linear embedding allows accounting for features that contribute the most to the MCI class discrimination. We compare the supervised pretraining approach to two unsupervised initialization methods (autoencoders and Principal Component Analysis) and against the best four performing classification methods of the 2014CADDementiachallenge. As a result, our proposal outperforms all the baselines (7% of classification accuracy and area under the receiver-operating-characteristic curve) at the time it reduces the class biasing.

scholarly journals The genetic covariance between life cycle stages separated by metamorphosis

2014 ◽  
Vol 281 (1788) ◽  
pp. 20141091 ◽  
Author(s):  
J. David Aguirre ◽  
Mark W. Blows ◽  
Dustin J. Marshall
Keyword(s):  
Life Cycle ◽  
Life Cycle Stage ◽  
Evolutionary Change ◽  
Phenotypic Evolution ◽  
Genetic Associations ◽  
Embryo Viability ◽  
Genetic Covariance ◽  
Life Cycle Stages ◽  
Target Matrix ◽  
Before And After

Metamorphosis is common in animals, yet the genetic associations between life cycle stages are poorly understood. Given the radical changes that occur at metamorphosis, selection may differ before and after metamorphosis, and the extent that genetic associations between pre- and post-metamorphic traits constrain evolutionary change is a subject of considerable interest. In some instances, metamorphosis may allow the genetic decoupling of life cycle stages, whereas in others, metamorphosis could allow complementary responses to selection across the life cycle. Using a diallel breeding design, we measured viability at four ontogenetic stages (embryo, larval, juvenile and adult viability), in the ascidian Ciona intestinalis and examined the orientation of additive genetic variation with respect to the metamorphic boundary. We found support for one eigenvector of G ( g obs max ), which contrasted larval viability against embryo viability and juvenile viability. Target matrix rotation confirmed that while g obs max shows genetic associations can extend beyond metamorphosis, there is still considerable scope for decoupled phenotypic evolution. Therefore, although genetic associations across metamorphosis could limit that range of phenotypes that are attainable, traits on either side of the metamorphic boundary are capable of some independent evolutionary change in response to the divergent conditions encountered during each life cycle stage.

Procrustean Transformations and Pandoran Hope in the Case of Climategate

2012 ◽  
Vol 2012 (1) ◽  
pp. 16338
Author(s):  
Raghu Garud ◽  
Joel Gehman ◽  
Arvind Karunakaran
Keyword(s):  
Procrustean Transformations

scholarly journals A Coskewness Shrinkage Approach for Estimating the Skewness of Linear Combinations of Random Variables*

2018 ◽  
Vol 18 (1) ◽  
pp. 1-23 ◽  
Author(s):  
Kris Boudt ◽  
Dries Cornilly ◽  
Tim Verdonck
Keyword(s):  
Hedge Funds ◽  
Convex Combination ◽  
Random Variables ◽  
Accurate Estimate ◽  
Small Sample ◽  
Shrinkage Estimators ◽  
Funds Of Hedge Funds ◽  
Target Matrix ◽  
Asymmetric Distributions ◽  
Small Sample Sizes

Abstract Decision-making in finance often requires an accurate estimate of the coskewness matrix to optimize the allocation to random variables with asymmetric distributions. The classical sample estimator of the coskewness matrix performs poorly for small sample sizes. A solution is to use shrinkage estimators, defined as the convex combination between the sample coskewness matrix and a target matrix. We propose unbiased consistent estimators for the MSE loss function and include the possibility of having multiple target matrices. In a portfolio application, we find that the proposed shrinkage coskewness estimators are useful in mean–variance–skewness efficient portfolio allocation of funds of hedge funds.

Target Rotation and Normative Policy Analysis in Urban Ecology

1978 ◽  
Vol 10 (3) ◽  
pp. 275-285 ◽  
Author(s):  
E D Perle
Keyword(s):  
Census Data ◽  
Urban System ◽  
Performance Standards ◽  
Factor Loading ◽  
Policy Implications ◽  
System Description ◽  
Target Matrix ◽  
Target Rotation ◽  
Vector Basis ◽  
Loading Matrix

Factor analytic methodology in geography and planning has been limited to system description. The conventional approach of searching for an underlying vector basis is germane for exploratory type research, but it is not directly applicable for normative purposes. Target rotation provides an analytical matrix-comparison methodology particularly useful in extending the utility of urban system findings from descriptive ecological studies to normative ones. An empirical example of this approach is provided, based upon 1970 census data of the Detroit SMSA. An empirical factor-loading matrix is presented, a target matrix of desirable performance standards is hypothesized, and the observed loadings are rotated upon the target loadings. Observed system performance is then directly compared with desired performance, indicating the direction and magnitude of convergence/divergence. Finally, policy implications of these empirical findings are suggested.

Sign in / Sign up

Export Citation Format

Share Document