Inferential Implications of Over-Parametrization: A Case Study in Incomplete Categorical Data

P>In the context of either Bayesian or classical sensitivity analyses of over-parametrized models for incomplete categorical data, it is well known that prior-dependence on posterior inferences of nonidentifiable parameters or that too parsimonious over-parametrized models may lead to erroneous conclusions. Nevertheless, some authors either pay no attention to which parameters are nonidentifiable or do not appropriately account for possible prior-dependence. We review the literature on this topic and consider simple examples to emphasize that in both inferential frameworks, the subjective components can influence results in nontrivial ways, irrespectively of the sample size. Specifically, we show that prior distributions commonly regarded as slightly informative or noninformative may actually be too informative for nonidentifiable parameters, and that the choice of over-parametrized models may drastically impact the results, suggesting that a careful examination of their effects should be considered before drawing conclusions.Resume Que ce soit dans un cadre Bayesien ou classique, il est bien connu que la surparametrisation, dans les modeles pour donnees categorielles incompletes, peut conduire a des conclusions erronees. Cependant, certains auteurs persistent a negliger les problemes lies a la presence de parametres non identifies. Nous passons en revue la litterature dans ce domaine, et considerons quelques exemples surparametres simples dans lesquels les elements subjectifs influencent de facon non negligeable les resultats, independamment de la taille des echantillons. Plus precisement, nous montrons comment des a priori consideres comme peu ou non-informatifs peuvent se reveler extremement informatifs en ce qui concerne les parametres non identifies, et que le recours a des modeles surparametres peut avoir sur les conclusions finales un impact considerable. Ceci suggere un examen tres attentif de l`impact potentiel des a priori.

Improved maximum-likelihood estimation in a regression model with general parametrization

We analyse the finite-sample behaviour of two second-order bias-corrected alternatives to the maximum-likelihood estimator of the parameters in a multivariate normal regression model with general parametrization proposed by Patriota and Lemonte [A. G. Patriota and A. J. Lemonte, Bias correction in a multivariate regression model with genereal parameterization, Stat. Prob. Lett. 79 (2009), pp. 1655-1662]. The two finite-sample corrections we consider are the conventional second-order bias-corrected estimator and the bootstrap bias correction. We present the numerical results comparing the performance of these estimators. Our results reveal that analytical bias correction outperforms numerical bias corrections obtained from bootstrapping schemes.

Dispersive analysis of KL mu 3 and KLe3 scalar and vector form factors using KTeV data

Using the published KTeV samples of K(L) -> pi(+/-)e(-/+)nu and K(L) -> pi(+/-)mu(-/+)nu decays, we perform a reanalysis of the scalar and vector form factors based on the dispersive parametrization. We obtain phase-space integrals I(K)(e) = 0.15446 +/- 0.00025 and I(K)(mu) = 0.10219 +/- 0.00025. For the scalar form factor parametrization, the only free parameter is the normalized form factor value at the Callan-Treiman point (C); our best-fit results in InC = 0.1915 +/- 0.0122. We also study the sensitivity of C to different parametrizations of the vector form factor. The results for the phase-space integrals and C are then used to make tests of the standard model. Finally, we compare our results with lattice QCD calculations of F(K)/F(pi) and f(+)(0).

Suppression Pattern of Neutral Pions at High Transverse Momentum in Au plus Au Collisions at root S(NN)=200 GeV and Constraints on Medium Transport Coefficients

For Au + Au collisions at 200 GeV, we measure neutral pion production with good statistics for transverse momentum, p(T), up to 20 GeV/c. A fivefold suppression is found, which is essentially constant for 5 < p(T) < 20 GeV/c. Experimental uncertainties are small enough to constrain any model-dependent parametrization for the transport coefficient of the medium, e. g., <(q) over cap > in the parton quenching model. The spectral shape is similar for all collision classes, and the suppression does not saturate in Au + Au collisions.

Kinetic energy sum spectra in nonmesonic weak decay of hypernuclei

We evaluate the coincidence spectra in the nonmesonic weak decay (NMWD) Lambda N -> nN of Lambda hypernuclei (4)(Lambda)He, (5)(Lambda)He, (12)(Lambda)C, (16)(Lambda)O, and (28)(Lambda)Si, as a function of the sum of kinetic energies E(nN)=E(n)+E(N) for N=n,p. The strangeness-changing transition potential is described by the one-meson-exchange model, with commonly used parametrization. Two versions of the independent-particle shell model (IPSM) are employed to account for the nuclear structure of the final residual nuclei. They are as follows: (a) IPSM-a, where no correlation, except for the Pauli principle, is taken into account and (b) IPSM-b, where the highly excited hole states are considered to be quasistationary and are described by Breit-Wigner distributions, whose widths are estimated from the experimental data. All np and nn spectra exhibit a series of peaks in the energy interval 110 MeV < E(nN)< 170 MeV, one for each occupied shell-model state. Within the IPSM-a, and because of the recoil effect, each peak covers an energy interval proportional to A(-1) , going from congruent to 4 MeV for (28)(Lambda)Si to congruent to 40 MeV for (4)(Lambda)He. Such a description could be pretty fair for the light (4)(Lambda)He and (5)(Lambda)He hypernuclei. For the remaining, heavier, hypernuclei it is very important, however, to consider as well the spreading in strength of the deep-hole states and bring into play the IPSM-b approach. Notwithstanding the nuclear model that is employed the results depend only very weakly on the details of the dynamics involved in the decay process proper. We propose that the IPSM is the appropriate lowest-order approximation for the theoretical calculations of the of kinetic energy sum spectra in the NMWD. It is in comparison to this picture that one should appraise the effects of the final-state interactions and of the two-nucleon-induced decay mode.

On the influence of non-thermal pressure on the mass determination of galaxy clusters

Aims. Given that in most cases just thermal pressure is taken into account in the hydrostatic equilibrium equation to estimate galaxy cluster mass, the main purpose of this paper is to consider the contribution of all three non-thermal components to total mass measurements. The non-thermal pressure is composed by cosmic rays, turbulence and magnetic pressures. Methods. To estimate the thermal pressure we used public XMM-Newton archival data of five Abell clusters to derive temperature and density profiles. To describe the magnetic pressure, we assume a radial distribution for the magnetic field, B(r) proportional to rho(alpha)(g). To seek generality we assume alpha within the range of 0.5 to 0.9, as indicated by observations and numerical simulations. Turbulent motions and bulk velocities add a turbulent pressure, which is considered using an estimate from numerical simulations. For this component, we assume an isotropic pressure, P(turb) = 1/3 rho(g)(sigma(2)(r) + sigma(2)(t)). We also consider the contribution of cosmic ray pressure, P(cr) proportional to r(-0.5). Thus, besides the gas (thermal) pressure, we include these three non-thermal components in the magnetohydrostatic equilibrium equation and compare the total mass estimates with the values obtained without them. Results. A consistent description for the non-thermal component could yield a variation in mass estimates that extends from 10% to similar to 30%. We verified that in the inner parts of cool core clusters the cosmic ray component is comparable to the magnetic pressure, while in non-cool core clusters the cosmic ray component is dominant. For cool core clusters the magnetic pressure is the dominant component, contributing more than 50% of the total mass variation due to non-thermal pressure components. However, for non-cool core clusters, the major influence comes from the cosmic ray pressure that accounts for more than 80% of the total mass variation due to non-thermal pressure effects. For our sample, the maximum influence of the turbulent component to the total mass variation can be almost 20%. Although all of the assumptions agree with previous works, it is important to notice that our results rely on the specific parametrization adopted in this work. We show that this analysis can be regarded as a starting point for a more detailed and refined exploration of the influence of non-thermal pressure in the intra-cluster medium (ICM).

Experimental investigation on adaptive robust controller designs applied to a free-floating space manipulator

This paper aims to formulate and investigate the application of various nonlinear H(infinity) control methods to a fiee-floating space manipulator subject to parametric uncertainties and external disturbances. From a tutorial perspective, a model-based approach and adaptive procedures based on linear parametrization, neural networks and fuzzy systems are covered by this work. A comparative study is conducted based on experimental implementations performed with an actual underactuated fixed-base planar manipulator which is, following the DEM concept, dynamically equivalent to a free-floating space manipulator. (C) 2011 Elsevier Ltd. All rights reserved.

EXACT AND QUASI-EXACT MODELS OF STRANGE STARS

We construct and compare in this work a variety of simple models for strange stars, namely, hypothetical self-bound objects made of a cold stable version of the quark-gluon plasma. Exact, quasi-exact and numerical models are examined to find the most economical description for these objects. A simple and successful parametrization of them is given in terms of the central density, and the differences among the models are explicitly shown and discussed. In particular, we present a model starting with a Gaussian ansatz for the density profile that provides a very accurate and almost complete analytical integration of the problem, modulo a small difference for one of the metric potentials.

Revisiting 2D numerical models for the 19th century outbursts of eta Carinae

We present here new results of two-dimensional hydrodynamical simulations of the eruptive events of the 1840s (the great) and the 1890s (the minor) eruptions suffered by the massive star eta Carinae (Car). The two bipolar nebulae commonly known as the Homunculus and the little Homunculus (LH) were formed from the interaction of these eruptive events with the underlying stellar wind. We assume here an interacting, non-spherical multiple-phase wind scenario to explain the shape and the kinematics of both Homunculi, but adopt a more realistic parametrization of the phases of the wind. During the 1890s eruptive event, the outflow speed decreased for a short period of time. This fact suggests that the LH is formed when the eruption ends, from the impact of the post-outburst eta Car wind (that follows the 1890s event) with the eruptive flow (rather than by the collision of the eruptive flow with the pre-outburst wind, as claimed in previous models; Gonzalez et al.). Our simulations reproduce quite well the shape and the observed expansion speed of the large Homunculus. The LH (which is embedded within the large Homunculus) becomes Rayleigh-Taylor unstable and develop filamentary structures that resemble the spatial features observed in the polar caps. In addition, we find that the interior cavity between the two Homunculi is partially filled by material that is expelled during the decades following the great eruption. This result may be connected with the observed double-shell structure in the polar lobes of the eta Car nebula. Finally, as in previous work, we find the formation of tenuous, equatorial, high-speed features that seem to be related to the observed equatorial skirt of eta Car.

The Diffusion Kernel Filter

A particle filter method is presented for the discrete-time filtering problem with nonlinear ItA ` stochastic ordinary differential equations (SODE) with additive noise supposed to be analytically integrable as a function of the underlying vector-Wiener process and time. The Diffusion Kernel Filter is arrived at by a parametrization of small noise-driven state fluctuations within branches of prediction and a local use of this parametrization in the Bootstrap Filter. The method applies for small noise and short prediction steps. With explicit numerical integrators, the operations count in the Diffusion Kernel Filter is shown to be smaller than in the Bootstrap Filter whenever the initial state for the prediction step has sufficiently few moments. The established parametrization is a dual-formula for the analysis of sensitivity to gaussian-initial perturbations and the analysis of sensitivity to noise-perturbations, in deterministic models, showing in particular how the stability of a deterministic dynamics is modeled by noise on short times and how the diffusion matrix of an SODE should be modeled (i.e. defined) for a gaussian-initial deterministic problem to be cast into an SODE problem. From it, a novel definition of prediction may be proposed that coincides with the deterministic path within the branch of prediction whose information entropy at the end of the prediction step is closest to the average information entropy over all branches. Tests are made with the Lorenz-63 equations, showing good results both for the filter and the definition of prediction.

Exclusive processes in electron-ion collisions

The exclusive processes in electron-ion (eA) interactions are an important tool to investigate the QCD dynamics at high energies as they are in general driven by the gluon content of the target which is strongly subject to parton saturation effects. In this Letter we compute the cross sections for the exclusive vector meson production as well as the deeply virtual Compton scattering (DVCS) relying on the color dipole approach and considering the numerical solution of the Balitsky-Kovchegov equation including running coupling corrections (rcBK). The production cross sections obtained with the rcBK solution and bCGC parametrization are very similar, the former being slightly larger. (C) 2011 Elsevier B.V. All rights reserved.

Antihyperon polarization in high-energy inclusive processes

We propose a model for the antihyperon polarization in high-energy proton-nucleus inclusive reactions, based on the final-state interactions between the antihyperons and other produced particles (predominantly pions). To formulate this idea, we use the previously obtained low-energy pion-(anti-)hyperon interaction using effective chiral Lagrangians, and a hydrodynamic parametrization of the background matter, which expands and decouples at a certain freezeout temperature.

A matrix formula for the skewness of maximum likelihood estimators

We give a general matrix formula for computing the second-order skewness of maximum likelihood estimators. The formula was firstly presented in a tensorial version by Bowman and Shenton (1998). Our matrix formulation has numerical advantages, since it requires only simple operations on matrices and vectors. We apply the second-order skewness formula to a normal model with a generalized parametrization and to an ARMA model. (c) 2010 Elsevier B.V. All rights reserved.

Solvatochromic Shift of the pi -> pi* Transition in All-Trans, Cis-13, Cis-11, Cis-9, and Cis-7 Retinal Isomers Induced by Water and Methanol

The solvatochromic shift of the lowest singlet it pi -> pi* electronic transition in the all-trans, cis-13, cis-11, cis-9, and cis-7 retinal isomers were computed under the influence of water, methanol, and benzene solvents. Excitation energies were calculated in gas phase and in solution. The calculations in solution were performed considering the sequential Monte Carlo (MC) /Quantum Mechanical approach. The MC simulations were performed considering the full retinal isomer molecules and 900 water molecules, 900 methanol, or 400 benzene ones. The OPLS/AA parametrization was chosen for retinal, methanol, and benzene molecules and the SPC model was used for water one. From the MC calculations 100 independent configurations were selected, with 100 solvent molecules in thermodynamical equilibrium at T = 298.15 K. Average point-charges were obtained from those independent configurations for water, methanol, and benzene solvent. TDDFT and CASSCF//CASPT2 methodologies were used to compute the vertical excitation energy of the retinal isomers in different environment. (C) 2010 Wiley Periodicals, Inc. Int J Quantum Chem 110: 2076-2087, 2010