Search

Aim: To evaluate the psychometric properties of scales measuring adolescents’ proficiency to critically appraise nutrition information, their engagement in dietary behaviour and self-efficacy in the science topic ‘Body and Health’, and test a theoretical model linking these latent traits. Methods: A sample of 1622 tenth graders at 58 randomly sampled schools in Norway voluntary responded to a questionnaire containing the three scales. The scale measuring adolescents’ proficiency to critically appraise nutrition information was validated by applying the partial credit parameterization of the polytomous unidimensional Rasch model. The scale measuring self-efficacy in the science topic ‘Body and Health’ was validated by using the partial credit parameterization of the polytomous unidimensional Rasch model and confirmatory factor analysis. The theoretical model linking the latent traits was tested by using structural equation modelling. Structural equation modelling was preferred to regression models as this method properly handles latent traits measured with standard errors. The data was tested up against the appropriate Rasch model by using the statistical software package RUMM2030. The confirmatory factor model and the “structural equation modelling” model were estimated by using the statistical software package Lisrel 9. Owing to data at the ordinal measurement level, “diagonally weighted least square” estimation was applied. “Goodness of fit” indexes were also estimated by using robust maximum likelihood estimation, as published target values typically rely on this type of estimation. Main results: The data collected sufficiently fit the polytomous unidimensional Rasch model. Confirmatory factor analysis displayed strong standardized factor loadings, which strengthened the idea of one underlying latent factor (unidimensional scale). The scales were slightly less than optimally targeted for the sample, as the distribution of person location estimates were somewhat shifted toward higher values than the distribution of item threshold locations. Overall, the scales were reliable and able to separate between students with different standing on the latent trait. The theoretical model was empirically strengthened, which means that the model implied variance-covariance matrix fairly well reproduced the observed variance-covariance matrix. Conclusions: Valid and reliable scales for measuring adolescents’ critical nutrition literacy were established, and self-efficacy in the health-related science topic explained variation in students’ critical nutrition literacy. Hence, there is a relation between adolescents’ self-perceived nutrition literacy and self-perceived health-related scientific literacy. Hensikt: Å evaluere de psykometriske egenskapene til måleskalaer som måler ungdoms evne til å kritisk vurdere ernæringsinformasjon (CNL-E), deres engasjement i kostholdsendrende atferd (CNLEng) og mestringsforventning i kjerneelementet «Kropp og helse», samt å teste en modell som beskriver sammenhenger mellom disse latente trekkene. Metoder: Måleskalaene ble validert ved bruk av Rasch-modellering og konfirmerende faktoranalyse i et utvalg på 1622 elever på 10. årstrinn ved 58 tilfeldig utvalgte skoler, og den teoretiske modellen ble testet ved bruk av strukturell ligningsmodellering. Hovedresultater: Dataene hadde tilstrekkelig tilpasning til polytom Rasch-modell (PCM). Samlet sett var de tre måleskalaene pålitelige, men de kunne vært bedre tilpasset elevenes dyktighet. De empiriske dataene styrket den teoretiske modellen. Konklusjon: Valide og reliable måleskalaer for måling av ungdommers kritiske ernæringskompetanse ble etablert, og mestringsforventning, som er et helserelatert kjerneelement i naturfag, forklarte variasjon i kritisk ernæringskompetanse.

The problem of the parameters estimation for the polynomial in the input variables regression function is formulated and solved. The input and output variables of the regression function are multidimensional-matrices. The parameters of the regression function are assumed to be random independent multidimensional matrices with Gaussian distribution and known mean value and dispersion matrices. The solution to this problem is a multidimensional-matrix system of the linear algebraic equations in multidimensional-matrix unknowns function regression parameters. We have considered particular case of quadratic regression function, for which we have obtained formulas for parameters calculation. The computer simulation of the quadratic regression functions is performed for the two-dimensional matrix input and output variables.

The question of whether more Socially Responsible (SR) firms outperform or underperform other conventional firms has been debated in the economic literature. In this study, using the Socially Responsible Investment (SRI) indexes and conventional stock indexes in the US, the UK and Japan, first and second moments of firm performance distributions are estimated based on the Markov Switching (MS) model. We find two distinct regimes (bear and bull) in the SRI markets as well as the stock markets for all the three countries. These regimes occur with the same timing in both types of market. No statistical difference in means and volatilities generated from the SRI indexes and conventional indexes in either region was found. Furthermore, we find strong comovements between the two indexes in both the regimes.

Most protein substitution models use a single amino acid replacement matrix summarizing the biochemical properties of amino acids. However, site evolution is highly heterogeneous and depends on many factors that influence the substitution patterns. In this paper, we investigate the use of different substitution matrices for different site evolutionary rates. Indeed, the variability of evolutionary rates corresponds to one of the most apparent heterogeneity factors among sites, and there is no reason to assume that the substitution patterns remain identical regardless of the evolutionary rate. We first introduce LG4M, which is composed of four matrices, each corresponding to one discrete gamma rate category (of four). These matrices differ in their amino acid equilibrium distributions and in their exchangeabilities, contrary to the standard gamma model where only the global rate differs from one category to another. Next, we present LG4X, which also uses four different matrices, but leaves aside the gamma distribution and follows a distribution-free scheme for the site rates. All these matrices are estimated from a very large alignment database, and our two models are tested using a large sample of independent alignments. Detailed analysis of resulting matrices and models shows the complexity of amino acid substitutions and the advantage of flexible models such as LG4M and LG4X. Both significantly outperform single-matrix models, providing gains of dozens to hundreds of log-likelihood units for most data sets. LG4X obtains substantial gains compared with LG4M, thanks to its distribution-free scheme for site rates. Since LG4M and LG4X display such advantages but require the same memory space and have comparable running times to standard models, we believe that LG4M and LG4X are relevant alternatives to single replacement matrices. Our models, data, and software are available from http://www.atgc-montpellier.fr/models/lg4x.

We generalize Richardson-Lucy (RL) deblurring to 4-D light fields by replacing the convolution steps with light field rendering of motion blur. The method deals correctly with blur caused by 6-degree-of-freedom camera motion in complex 3-D scenes, without performing depth estimation. We introduce a novel regularization term that maintains parallax information in the light field while reducing noise and ringing. We demonstrate the method operating effectively on rendered scenes and scenes captured using an off-the-shelf light field camera. An industrial robot arm provides repeatable and known trajectories, allowing us to establish quantitative performance in complex 3-D scenes. Qualitative and quantitative results confirm the effectiveness of the method, including commonly occurring cases for which previously published methods fail. We include mathematical proof that the algorithm converges to the maximum-likelihood estimate of the unblurred scene under Poisson noise. We expect extension to blind methods to be possible following the generalization of 2-D Richardson-Lucy to blind deconvolution., Comment: Paper accepted for oral presentation at LF4CV workshop at CVPR

The assumption of a linear increasing failure rate uniquely determines a life distribution which has mathematically tractable qualities. The pertinent features of this distribution are derived and listed in the paper. Three methods of estimating the two parameters of the linear increasing failure rate are derived. For each procedure a computer program is provided which performs the necessary calculations. Results utilizing simulated failure data are listed for two of the methods of parameter estimation. http://archive.org/details/methodsofestimat1094515089 Captain, United States Army Approved for public release; distribution is unlimited.