Censored linear model in high dimensions

Censored data are quite common in statistics and have been studied in depth in the last years [for some references, see Powell (J Econom 25(3):303–325, 1984), Murphy et al. (Math Methods Stat 8(3):407–425, 1999), Chay and Powell (J Econ Perspect 15(4):29–42, 2001)]. In this paper, we consider censored high-dimensional data. High-dimensional models are in some way more complex than their low-dimensional versions, therefore some different techniques are required. For the linear case, appropriate estimators based on penalised regression have been developed in the last years [see for example Bickel et al. (Ann Stat 37(4):1705–1732, 2009), Koltchinskii (Bernoulli 15:799–828, 2009)]. In particular, in sparse contexts, the \(l_1\)-penalised regression (also known as LASSO) [see Tibshirani (J R Stat Soc Ser B 58:267–288, 1996), Bühlmann and van de Geer (Statistics for high-dimensional data. Springer, Heidelberg, 2011) and reference therein] performs very well. Only few theoretical work was done to analyse censored linear models in a high-dimensional context. We therefore consider a high-dimensional censored linear model, where the response variable is left censored. We propose a new estimator, which aims to work with high-dimensional linear censored data. Theoretical non-asymptotic oracle inequalities are derived.     

A moment generating function of a combination of linear rank tests and its asymptotic efficiency

When testing hypotheses in two-sample problems, the Lepage test has often been used to jointly test the location and scale parameters, and has been discussed by many authors over the years. The Lepage test was a combination of the Wilcoxon statistic and the Ansari–Bradley statistic. Various Lepage-type tests were proposed with discussions of an asymptotic relative efficiency (Duran et al., Biometrika 63:173–176, 1976; Goria, Stat Neerl 36:3–13, 1982), a robustness and a power comparison (Neuhäuser, Commun Stat Theory Methods 29:67–78, 2000; Büning, J Appl Stat 29:907–924, 2002) and an adaptive test (Büning and Thadewald, J Stat Comput Sim 65:287–310, 2000). We derive an expression for the moment generating function of a linear combination of two linear rank statistics. As a suggested Lepage-type test, we use a combination of the generalized Wilcoxon statistic and the generalized Mood statistic. Deriving the exact critical value of the statistic can be difficult when the sample sizes are increasing. In this situation, an approximation method to the distribution function of the test statistic can be useful with a higher order moment. We use a moment-based approximation with an adjusted gamma polynomial to evaluate the upper tail probability of a Lepage-type test for a finite sample size. We determine the asymptotic efficiencies of the Lepage and Lepage-type tests for various distributions.     

A New Class of Topp–Leone Power Series Distributions with Reliability Application

Okasha et al. (J Failure Anal Prevention, 2017. doi: 10.1007/s11668-017-0263-x) introduced the novel Topp–Leone geometric distribution. Here, we introduce a class of distributions containing [32]’s distribution as a particular case. The class of distributions contains several important distributions, including the Topp–Leone geometric, Topp–Leone Poisson, Topp–Leone logarithmic, Topp–Leone binomial and Topp–Leone negative binomial distributions. We derive comprehensive mathematical properties of the class. We obtain closed form expressions for the density function, cumulative distribution function, survival and hazard rate functions, moments, mean residual lifetime, mean past lifetime, order statistics and moments of order statistics. The class is shown to be more flexible by reanalyzing the real data set in [32].     

Test on the linear combinations of mean vectors in high-dimensional data

In this study, we propose a procedure for simultaneous testing \(l (l\ge 1)\) linear relations on \(k(k\ge 2)\) high-dimensional mean vectors with heterogeneous covariance matrices, which extends the result derived by Nishiyama et al. (J Stat Plan Inference 143(11):1898–1911, 2013) and does not need the normality assumption. The newly proposed test statistic is motivated by Bai and Saranadasa (Statistica Sinica 6(2):311–329, 1996) and Chen and Qin (Ann Stat 38(2):808–835, 2010). As a special case, our result could be applied to multivariate analysis of variance, that is, testing the equality of k high-dimensional mean vectors.     

Comparison of the Argon Triple-Point Temperature in Small Cells of Different Construction

The argon triple point (\(T_{90} = 83.8058\,\hbox {K}\)) is a fixed point of the International Temperature Scale of Preston-Thomas (Metrologia 27:3, 1990). Cells for realization of the fixed point have been manufactured by several European metrology institutes (Pavese in Metrologia 14:93, 1978; Pavese et al. in Temperature, part 1, American Institute of Physics, College Park, 2003; Hermier et al. in Temperature, part 1, American Institute of Physics, College Park, 2003; Pavese and Beciet in Modern gas-based temperature and pressure measurement, Springer, New York, 2013). The Institute of Low Temperature and Structure Research has in its disposal a few argon cells of various constructions used for calibration of capsule-type standard platinum resistance thermometers (CSPRT) that were produced within 40 years. These cells differ in terms of mechanical design and thermal properties, as well as source of gas filling the cell. This paper presents data on differences between temperature values obtained during the realization of the triple point of argon in these cells. For determination of the temperature, a heat-pulse method was applied (Pavese and Beciet in Modern gas-based temperature and pressure measurement, Springer, New York, 2013). The comparisons were performed using three CSPRTs. The temperatures difference was determined in relation to a reference function \(W(T)=R(T_{90})/R(271.16\hbox {K})\) in order to avoid an impact of CSPRT resistance drift between measurements in the argon cells. Melting curves and uncertainty budgets of the measurements are given in the paper. A construction of measuring apparatus is also presented in this paper.     

Solubility Prediction of Active Pharmaceutical Compounds with the UNIFAC Model

The crystallization from solution of an active pharmaceutical ingredient requires the knowledge of the solubility in the entire temperature range investigated during the process. However, during the development of a new active ingredient, these data are missing. Its experimental determination is possible, but tedious. UNIFAC Group contribution method Fredenslund et al. (Vapor–liquid equilibria using UNIFAC: a group contribution method, 1977; AIChE J 21:1086, 1975) can be used to predict this physical property. Several modifications on this model have been proposed since its development in 1977, modified UNIFAC of Dortmund Weidlich et al. (Ind Eng Chem Res 26:1372, 1987), Gmehling et al. (Ind Eng Chem Res 32:178, 1993), Pharma-modified UNIFAC Diedrichs et al. (Evaluation und Erweiterung thermodynamischer Modelle zur Vorhersage von Wirkstofflöslichkeiten, PhD Thesis, 2010), KT-UNIFAC Kang et al. (Ind Eng Chem Res 41:3260, 2002), \(\ldots \) In this study, we used UNIFAC model by considering the linear temperature dependence of interaction parameters as in Pharma-modified UNIFAC and structural groups as defined by KT-UNIFAC first-order model. More than 100 binary datasets were involved in the estimation of interaction parameters. These new parameters were then used to calculate activity coefficient and solubility of some molecules in various solvents at different temperatures. The model gives better results than those from the original UNIFAC and shows good agreement between the experimental solubility and the calculated one.     

On the rates of convergence for moments convergence in regression models

In one-dimensional regression models, we establish a rate for the rth moment convergence \((r \geqslant 1)\) of the ordinary least-squares estimator involving explicitly the regressors, answering to an open question raised lately by Afendras and Markatou (Test 25:775–784, 2016). An extension of the classic Theorem 2.6.1 of Anderson (The statistical analysis of time series, Wiley, New York, 1971) is also presented.     

Precursors of failure and weakening in a biaxial test

We study numerical simulations of large (\({N{\approx}10^4}\)) two-dimensional quasi-static granular assemblies subjected to a slowly increasing deviator stress. We report some peculiarities in the behavior of these packings that have not yet been addressed. The number of sliding contacts is not necessarily related to stability: first the number of sliding contacts rises linearly and smoothly with the applied stress. Then, at approximately half the peak stress, the increase slows down, a plateau develops, and a decrease follows. The spatial organization of sliding contacts also changes: during the first half of the simulation, sliding contacts are uniformly distributed throughout the packing, but in the second half, they become concentrated in certain regions. This suggests that the loss of homogeneity occurs well before the appearance of shear bands. During the second half events appear where the number of sliding contacts drops suddenly, and then rapidly recovers. We show that these events are in fact local instabilities in the packing. These events become more frequent as failure is approached. For these two reasons, we call these events precursors, since they are similar to the precursors recently observed in both numerical (Staron et al. Phys Rev Lett 89:204302, 2002; Nerone et al. Phys Rev E 67:011302, 2003) and experimental (Gibiat et al. J Acoust Soc Am 123:3142, 2009; Scheller et al. Phys Rev E 74:031311, 2006; Zaitsev et al. Eur Phys Lett 83:64003, 2008; Aguirre et al. Phys Rev E 73:041307, 2006) studies of avalanches.     

Sleeping beauties in psychology

A ‘Sleeping beauty’ is a term used to describe a research article that has remained relatively uncited for several years and then suddenly blossoms forward. New technology now allows us to detect such articles more easily than before, and sleeping beauties can be found in numerous disciplines. In this article we describe three sleeping beauties that we have found in psychology—Stroop (J Exp Psychol 18:643–662, 1935), Maslow (Psychol Rev 50(4):370–396, 1943), and Simon (Psychol Rev 63(2):129–138, 1956).     

An Enhanced Facet Determination Scheme in 3D

An enhanced scheme for the determination of equilibrium crystal shapes is introduced. The emphasis of the present study is put on the proper detection of the facets appearing on the crystal surface. The original formulation presented in [1] employs the principle of the virtual work, and the enhanced scheme additionally makes use of a penalty formulation approach. The derivation of the penalty terms is discussed in detail. Finally, the corresponding discrete method is applied to a certain problematic example case presented in [1] resulting now in the correct crystal shape.     

On the asymptotics of minimum disparity estimation

Inference procedures based on the minimization of divergences are popular statistical tools. Beran (Ann stat 5(3):445–463, 1977) proved consistency and asymptotic normality of the minimum Hellinger distance (MHD) estimator. This method was later extended to the large class of disparities in discrete models by Lindsay (Ann stat 22(2):1081–1114, 1994) who proved existence of a sequence of roots of the estimating equation which is consistent and asymptotically normal. However, the current literature does not provide a general asymptotic result about the minimizer of a generic disparity. In this paper, we prove, under very general conditions, an asymptotic representation of the minimum disparity estimator itself (and not just for a root of the estimating equation), thus generalizing the results of Beran (Ann stat 5(3):445–463, 1977) and Lindsay (Ann stat 22(2):1081–1114, 1994). This leads to a general framework for minimum disparity estimation encompassing both discrete and continuous models.     

Eisenstein polynomials over function fields

In this paper we compute the density of monic and non-monic Eisenstein polynomials of fixed degree having entries in an integrally closed subring of a function field over a finite field. This gives a function field analogue of results by Dubickas (Appl Algebra Eng Commun Comput 14(2):127–132, 2003) and by Heyman and Shparlinski (Appl Algebra Eng Commun Comput 24(2):149–156, 2013).     

Excited Rotational States in Doped $${^{}}$$He Clusters: a Diffusion Monte Carlo Analysis

We report an extension of diffusion Monte Carlo (DMC) to the calculation of the molecular rotational energies by means of the generalized, symmetry-adapted, imaginary-time correlation functions (SAITCFs) originally introduced in the reptation quantum Monte Carlo (RQMC) framework (?krbi? in J Phys Chem A 111:12749, 2007). We studied the a-type and b-type rotational lines of the CO(\(^{4}\)He)\(_{N}\) clusters with \(N=\)1–8 that correlate, in the dimer limit, with the end-over-end and free-rotor transitions. We compare the SAITCF–DMC results with accurate DVR (for the dimer case), RQMC and other DMC data, and with reference experimental findings (Surin in Phys Rev Lett 101:233401, 2008). A good agreement is generally found, but a systematic underestimation of the SAITCF–DMC rotational energies of the b-type series is observed. Sources of inaccuracy in our theoretical approach and in the computational protocol are discussed and analyzed in detail.     

New aspects for friction coefficients of finite granular avalanche down a flat narrow reservoir

This work examines the bulk internal friction coefficient, \(\mu \), and effective wall friction coefficient, \(\mu _w\), for finite number of nearly identical dry glass spheres in avalanche down a narrow inclined reservoir of smooth frictional bed using a validated discrete element scheme. Instantaneous deviatoric strain rate tensor \(\dot{\gamma }^d_{ij}\) and stress tensor \(\tau _{ij}\) are computed locally to evaluate a three-dimensional constitutive model developed based on the rheology of steady homogeneous surface flows. On one side, the algebraic \(\mu -I\) relation conforms to conventional relation for glass beads, \(\mu =0.34+0.31/(1+0.15/I)\) (Jop et al. in J. Fluid Mech. 541:167–192, 2005, Midi in Eur. Phys. J. E 14:341–365, 2004, Jop in Comptes Rendus Phys. 16:62–72, 2015), when the inertial number \(I>I_{c}=2\times 10^{-2}\). The assumption of collinear \(\tau _{ij}\) and \(\dot{\gamma }^d_{ij}\), however, does not hold and such misalignment agrees to the findings in non-uniform inhomogeneous flows (Cortet et al. in Europhys. Lett. 88(1):14001, 2009). Below \(I_c\), we observe a decaying \(\mu -I\) as found in slowly deforming rheology tests and a simplified model is developed in view of shear-induced dilatation upon yielding. Non-constant effective wall friction coefficient is measured to grow in time and with I towards the sphere-wall sliding friction coefficient in the contact model while preserving the depth-weakening feature as in confined steady surface flows (Richard et al. in Phys. Rev. Lett. 101:248002, 2008, Brodu et al. in Phys. Rev. E 87:022202, 2013). The fact that rotation at one sphere center can divert surface relative velocity across the contact area to render lower sliding friction is considered to develop a model describing how \(\mu _w\) drops with the ratio between rotation-induced velocity and sliding velocity, \(\varOmega \). The simulation data compares fairly well to the predicted monotonic decay of \(\mu _w\) with \(\varOmega \).     

Long-Term Stability Evaluation of a Sn-Doped Ni–C Eutectic Cell Suitable for Radiation Thermometry

Metal carbon eutectic cells (high-temperature fixed points, HTFPs) (Machin in AIP Conf Proc 1552:305, 2013) are being considered for use as reliable high-temperature references for non-contact thermometry above the copper point (\(1084.62\,^{\circ }\hbox {C}\)). Recent studies have demonstrated the concept of using doped metal carbon eutectic cells as artefacts suitable for temperature scale comparisons (Teixeira et al. in AIP Conf Proc 1552:363, 2013; Teixeira et al. in Int J Thermophys 35:467–474, 2014; Machin et al. in Int J Thermophys 36:327–335, 2015). When using such artefacts, the participating institutes do not know the realization temperature of the doped HTFP cell, because it has been modified by the addition of a selected dopant at a definite concentration. The use of such fixed points can critically evaluate the real measurement capability of the institutes in any comparison. The pyrometry laboratory of Inmetro developed a set of doped Ni–C eutectic cells in 2012 and 2013. This paper describes the long-term stability of a Sn-doped Ni–C cell constructed in 2012, which accumulated more than 220 h above \(1300\,^{\circ }\hbox {C}\) amounting to more than 50 cycles of melts and freezes. The cell remained stable, well within the measurement uncertainty, throughout the evaluation period demonstrating the utility of such cells for scale comparison purposes.     

Performance of Different Light Sources for the Absolute Calibration of Radiation Thermometers

The evolving mise en pratique for the definition of the kelvin (MeP-K) [1, 2] will, in its forthcoming edition, encourage the realization and dissemination of the thermodynamic temperature either directly (primary thermometry) or indirectly (relative primary thermometry) via fixed points with assigned reference thermodynamic temperatures. In the last years, the Centro Español de Metrología (CEM), in collaboration with the Instituto de Óptica of Consejo Superior de Investigaciones Científicas (IO-CSIC), has developed several setups for absolute calibration of standard radiation thermometers using the radiance method to allow CEM the direct dissemination of the thermodynamic temperature and the assignment of the thermodynamic temperatures to several fixed points. Different calibration facilities based on a monochromator and/or a laser and an integrating sphere have been developed to calibrate CEM’s standard radiation thermometers (KE-LP2 and KE-LP4) and filter radiometer (FIRA2). This system is based on the one described in [3] placed in IO-CSIC. Different light sources have been tried and tested for measuring absolute spectral radiance responsivity: a Xe-Hg 500 W lamp, a supercontinuum laser NKT SuperK-EXR20 and a diode laser emitting at 6473 nm with a typical maximum power of 120 mW. Their advantages and disadvantages have been studied such as sensitivity to interferences generated by the laser inside the filter, flux stability generated by the radiant sources and so forth. This paper describes the setups used, the uncertainty budgets and the results obtained for the absolute temperatures of Cu, Co-C, Pt-C and Re-C fixed points, measured with the three thermometers with central wavelengths around 650 nm.     

EM Radiation Sensor: Bulk SQUID Made from Polycrystalline HTSC

The micro-contacts in the granules of the high-temperature superconductor (HTSC) films and other polycrystalline objects after transition to the SC state would then be similar to a bulk superconducting quantum interference device (SQUID), with the point S-N-S state greatly enhancing the sensitivity to electromagnetic radiation and can be used as of the application for much higher resolution than ever before possible (Braginsky, NATO ASI Series, 329, 235 (1996); Bray, J. Supercond. Novel Magn., 21, 335–341 (2008); Cantor, Supercoduct. & Cryoelectronics, 2000). Production of SQUIDs based on thin films is a very complicated technological process, requiring very expensive equipment. Use of the composite (HTSC powder + epoxy matrix), compressed SC powder, and thick films for SQUID fabrication should be very much simpler. The range of frequencies that can by detected with such a device will depend on the circuit parameters and may be extended to the microwave or infrared regimes (Braginsky, NATO ASI Series, 329, 235 (1996); Jurga et al. Acta Phys Pol A, 114, (2007); Jurga et al., Acta Phys Pol A, 114, (2007)). The advantage of the bulk SQUID based on HTSC-YBa₂Cu₃O _x , BiSr₂Ca₂Cu₃O _X , B(Pb)iSr₂Ca₂Cu₃O _X , and NdBaCo _X (powder + epoxy matrix, compressed SC powders, and thick films) is the non-selective nature of the spectral characteristics over a wide frequency range, high sensitivity, and quick response. For suppressing the large noise resulting from the maximal instability of electromagnetic properties at the SC, insulator transition is employed a differentiation procedure of the measurements signal.     

Application of the GUM approach to estimate uncertainty in measurements of sustainability systems

This work incorporates measurement uncertainty estimation into the model framework proposed by dos Santos and Brandi (Clean Technol Environ Policy, doi: 10.1007/s10098-015-0919-8, 2015). It brings the metrology science procedures to sustainability situations by incorporating the use of the GUM framework (GUF) together with the Monte Carlo method (MCM) (BIPM, Evaluation of measurement data—guide to the expression of uncertainty in measurement 2008a; Evaluation of measurement data—Supplement 1 to the “Guide to the expression of uncertainty in measurement”—propagation of distributions using a Monte Carlo method 2008b). The GUF uses the law of propagation of uncertainties and the MCM the propagation probability distributions. This scheme is applied to analyze the Integration and Logistic Infrastructure sustainability dimension of a biofuel supply chain in six countries (Santos et al. 2014). An initial set of specific indicators (input quantities) satisfying well-established criteria is used to aggregate indicators in a methodological manner into a single aggregate indicator. The Canberra and the normalized Euclidean distances are assumed as model functions. As recommended by the GUM approach, Supplement 1 (BIPM, Evaluation of measurement data—Supplement 1 to the “Guide to the expression of uncertainty in measurement”—propagation of distributions using a Monte Carlo method 2008b) is used to compare the GUF and the MCM results, adopting the GUM recommendation to perform the MCM with 10⁶ random trials. This allows the determination of the numerical statistical results with the precision level required for comparing the sustainability level of the six countries. It was shown that the use of the GUF is not validated to treat the adopted model functions. The two fundamental reasons are the limitation of the GUF concerning the truncation of the Taylor’s expansion and the deviation of the probability density function from the normal distribution (BIPM, Evaluation of measurement data—Supplement 1 to the “Guide to the expression of uncertainty in measurement”—propagation of distributions using a Monte Carlo method 2008b; Couto et al., Theory and applications of Monte Carlo simulations 2013). This result was predictable because of the nonlinear dependence on the indicators of the Canberra and the normalized Euclidean distances. The MCM calculations have shown that the uncertainties depend on the choice of the aggregate metrics, consequently affecting the countries sustainability ranking. The results demonstrate that Canberra and the Euclidean metrics separate the developed from the developing countries in clusters. The calculations for the single sustainability indicator and its uncertainty suggest that the Euclidean distance separates the countries better than the Canberra distance and, thus, it may be considered more adequate to represent the sustainability metrics Integration and Logistic Infrastructure sustainability dimension of a biofuel supply chain.     

Large scale additive manufacturing of eco-composites

The evolution of additive manufacturing processes is enabling the production of parts with improved dimensional accuracy, mechanical, physical and chemical properties [1]. New materials also contribute to this trend, and in this scope, eco-composites, materials with environmental and ecological advantages, which include natural polymers, have been acquiring increased relevance [2]. The purpose of this study is to develop composite material parts manufactured from recycled thermoplastics and natural fibres, in this case, wood residues. Additive manufacturing (fused deposition modelling) will be accomplished using a robot combined with extrusion unit. The objective is to access the influence of the main manufacturing parameters, such as temperature, distance between layers or deposition speed, on the final part characteristics, especially dimensional accuracy. Reverse engineering and several material analysis techniques will be employed to achieve this goal.     

On the description of ductile fracture in metals by the strain localization theory

Numerical simulations based on the bifurcation and imperfection versions of the strain localization theory are used in this paper to predict the failure loci of metals and applied to an advanced high strength steel subjected to proportional loading paths. The results are evaluated against the 3D unit cell analyses of Dunand and Mohr (J Mech Phys Solids 66(1):133–153, 2014. doi: 10.1016/j.jmps.2014.01.008) available in the literature. The Gurson porous plasticity model (Gurson in J Eng Mater Technol 99(1):2–15, 1977. doi: 10.1115/1.344340) is used to induce strain softening and drive the localization process. The effects of the void growth, void nucleation and void softening in shear are investigated over a large range of stress triaxialities and Lode parameters. A correlation between the imperfection and bifurcation results is established.