This paper studies the problem of scaling ordinal categorical data observed over two or more sets of categories measuring a single characteristic. Scaling is obtained by solving a constrained entropy model which finds the most probable values of the scales given the data. A Kullback-Leibler statistic is generated which operationalizes a measure for the strength of consistency among the sets of categories. A variety of data of two and three sets of categories are analyzed using the entropy approach.

When conducting robustness research where the focus of attention is on the impact of non-normality, the marginal skewness and kurtosis are often used to set the degree of non-normality. Monte Carlo methods are commonly applied to conduct this type of research by simulating data from distributions with skewness and kurtosis constrained to pre-specified values. Although several procedures have been proposed to simulate data from distributions with these constraints, no corresponding procedures have been applied for discrete distributions. In this paper, we present two procedures based on the principles of maximum entropy and minimum cross-entropy to estimate the multivariate observed ordinal distributions with constraints on skewness and kurtosis. For these procedures, the correlation matrix of the observed variables is not specified but depends on the relationships between the latent response variables. With the estimated distributions, researchers can study robustness not only focusing on the levels of non-normality but also on the variations in the distribution shapes. A simulation study demonstrates that these procedures yield excellent agreement between specified parameters and those of estimated distributions. A robustness study concerning the effect of distribution shape in the context of confirmatory factor analysis shows that shape can affect the robust ${\chi }^2$\documentclass[12pt]{minimal}\usepackage{amsmath}\usepackage{wasysym}\usepackage{amsfonts}\usepackage{amssymb}\usepackage{amsbsy}\usepackage{mathrsfs}\usepackage{upgreek}\setlength{\oddsidemargin}{-69pt}\begin{document}$$\chi ^2$$\end{document} and robust fit indices, especially when the sample size is small, the data are severely non-normal, and the fitted model is complex.

When a simple random sample of size n is employed to establish a classification rule for prediction of a polytomous variable by an independent variable, the best achievable rate of misclassification is higher than the corresponding best achievable rate if the conditional probability distribution is known for the predicted variable given the independent variable. In typical cases, this increased misclassification rate due to sampling is remarkably small relative to other increases in expected measures of prediction accuracy due to samplings that are typically encountered in statistical analysis.

This issue is particularly striking if a polytomous variable predicts a polytomous variable, for the excess misclassification rate due to estimation approaches 0 at an exponential rate as n increases. Even with a continuous real predictor and with simple nonparametric methods, it is typically not difficult to achieve an excess misclassification rate on the order of n−1. Although reduced excess error is normally desirable, it may reasonably be argued that, in the case of classification, the reduction in bias is related to a more fundamental lack of sensitivity of misclassification error to the quality of the prediction. This lack of sensitivity is not an issue if criteria based on probability prediction such as logarithmic penalty or least squares are employed, but the latter measures typically involve more substantial issues of bias. With polytomous predictors, excess expected errors due to sampling are typically of order n−1. For a continuous real predictor, the increase in expected error is typically of order n−2/3.

An information-theoretic framework is used to analyze the knowledge content in multivariate cross classified data. Several related measures based directly on the information concept are proposed: the knowledge content (S) of a cross classification, its terseness (Zeta), and the separability (GammaX) of one variable, given all others. Exemplary applications are presented which illustrate the solutions obtained where classical analysis is unsatisfactory, such as optimal grouping, the analysis of very skew tables, or the interpretation of well-known paradoxes. Further, the separability suggests a solution for the classic problem of inductive inference which is independent of sample size.

Let $(X,\mathcal {B},\mu ,T)$ be a probability-preserving system with X compact and T a homeomorphism. We show that if every point in $X\times X$ is two-sided recurrent, then $h_{\mu }(T)=0$, resolving a problem of Benjamin Weiss, and that if $h_{\mu }(T)=\infty $, then every full-measure set in X contains mean-asymptotic pairs (that is, the associated process is not tight), resolving a problem of Ornstein and Weiss.

Entropy of measure-preserving or continuous actions of amenable discrete groups allows for various equivalent approaches. Among them are those given by the techniques developed by Ollagnier and Pinchon on the one hand and the Ornstein–Weiss lemma on the other. We extend these two approaches to the context of actions of amenable topological groups. In contrast to the discrete setting, our results reveal a remarkable difference between the two concepts of entropy in the realm of non-discrete groups: while the first quantity collapses to 0 in the non-discrete case, the second yields a well-behaved invariant for amenable unimodular groups. Concerning the latter, we moreover study the corresponding notion of topological pressure, prove a Goodwyn-type theorem, and establish the equivalence with the uniform lattice approach (for locally compact groups admitting a uniform lattice). Our study elaborates on a version of the Ornstein–Weiss lemma due to Gromov.

This study aims to explore the dependencies on the cryptocurrency market using social network tools. We focus on the correlations observed in the cryptocurrency returns. Based on the sample of cryptocurrencies listed between January 2015 and December 2022 we examine which cryptos are central to the overall market and how often major players change. Static network analysis based on the whole sample shows that the network consists of several communities strongly connected and central, as well as a few that are disconnected and peripheral. Such a structure of the network implies high systemic risk. The day-by-day snapshots show that the network evolves rapidly. We construct the ranking of major cryptos based on centrality measures utilizing the TOPSIS method. We find that when single measures are considered, Bitcoin seems to have lost its first-mover advantage in late 2016. However, in the overall ranking, it still appears among the top positions. The collapse of any of the cryptocurrencies from the top of the rankings poses a serious threat to the entire market.

A series of papers by Hickey (1982, 1983, 1984) presents a stochastic ordering based on randomness. This paper extends the results by introducing a novel methodology to derive models that preserve stochastic ordering based on randomness. We achieve this by presenting a new family of pseudometric spaces based on a majorization property. This class of pseudometrics provides a new methodology for deriving the randomness measure of a random variable. Using this, the paper introduces the Gini randomness measure and states its essential properties. We demonstrate that the proposed measure has certain advantages over entropy measures. The measure satisfies the value validity property, provides an adequate extension to continuous random variables, and is often more appropriate (based on sensitivity) than entropy in various scenarios.

For a class of volume-preserving partially hyperbolic diffeomorphisms (or non-uniformly Anosov) $f\colon {\mathbb {T}}^d\rightarrow {\mathbb {T}}^d$ homotopic to linear Anosov automorphism, we show that the sum of the positive (negative) Lyapunov exponents of f is bounded above (respectively below) by the sum of the positive (respectively negative) Lyapunov exponents of its linearization. We show this for some classes of derived from Anosov (DA) and non-uniformly hyperbolic systems with dominated splitting, in particular for examples described by Bonatti and Viana [SRB measures for partially hyperbolic systems whose central direction is mostly contracting. Israel J. Math. 115(1) (2000), 157–193]. The results in this paper address a flexibility program by Bochi, Katok and Rodriguez Hertz [Flexibility of Lyapunov exponents. Ergod. Th. & Dynam. Sys. 42(2) (2022), 554–591].

Political polarization has become an increasingly salient issue worldwide, but a systematic examination of the variation and sources of mass polarization across countries is limited by current measurement methods. This work proposes a nonparametric, entropy-based measure of mass political polarization. It exploits the specific structure of ordinal distributions in public opinion data, makes no prior assumptions about the form and spacing of the data, and can still draw reliable measures of issue-based polarization. We demonstrate the theoretical and practical superiority of the measure with analytical comparisons and simulations. We then apply the proposed measure to questions about mass polarization in the USA, the relationship between radical parties and polarization in Europe, and cross-country trends in affective and ideological polarization.

Cation-exchange equilibrium for Ca-K-montmorillonite was studied at 35°, 50°, and 90°C and at three total normalities of the equilibrium solution (0.1, 0.05, and 0.01 N). Changes of the standard free energy for the exchange from K-montmorillonite to Ca-montmorillonite were determined to be −53, −270, and −393 cal/eq at 35°, 50°, and 90°C, respectively. Changes of the standard enthalpy and entropy were 1.7 kcal/eq and 5.6 cal/eq/degree at 35°C, respectively. The sign of the change of the standard free energy was found to be determined mainly by the entropy change, in particular, by the hydration entropy of the cations.

The calculation of the excess functions indicates that the mixing model of Ca-K-montmorillonite approximates that of a regular solution. Montmorillonite having potassium equivalent ion fraction of 0.1 to 0.7 consists of a random interstratification of Ca-montmorillonite (15.6 Å) and K-montmorillonite (12.6 Å).

Ion-exchange experiments in expanding clay minerals conducted over a wide range of surface ionic compositions and ionic strength produce variable mass-action selectivity coefficients. When the exchanging ions are of unequal charge, tactoid structure appears to influence selectivity, although configurational entropy of adsorbed ions may also generate variable selectivity. The degree of deviation from ideal mass-action exchange is related to the dissimilarity of the ions undergoing exchange. Data involving trivalent ion adsorption on smectites suggest that mass-action is a poor approximation when the adsorbing and desorbing ions have different hydration energies and charge. No form of exchange equation is successful in describing ion exchange for a wide range of experimental conditions, although the fluctuation of the selectivity coefficient follows consistent trends with changing experimental conditions. The strong adsorption of high-charge ions on clays is not exothermic, but must be driven by the increasing disorder of ions and/or water.

This paper investigates the separation property in binary phase-segregation processes modelled by Cahn-Hilliard type equations with constant mobility, singular entropy densities and different particle interactions. Under general assumptions on the entropy potential, we prove the strict separation property in both two and three-space dimensions. Namely, in 2D, we notably extend the minimal assumptions on the potential adopted so far in the literature, by only requiring a mild growth condition of its first derivative near the singular points $\pm 1$, without any pointwise additional assumption on its second derivative. For all cases, we provide a compact proof using De Giorgi’s iterations. In 3D, we also extend the validity of the asymptotic strict separation property to the case of fractional Cahn-Hilliard equation, as well as show the validity of the separation when the initial datum is close to an ‘energy minimizer’. Our framework offers insights into statistical factors like particle interactions, entropy choices and correlations governing separation, with broad applicability.

We define a notion of substitution on colored binary trees that we call substreetution. We show that a point fixed by a substreetution may (or not) be almost periodic, and thus the closure of the orbit under the $\mathbb {F}_{2}^{+}$-action may (or not) be minimal. We study one special example: we show that it belongs to the minimal case and that the number of preimages in the minimal set increases just exponentially fast, whereas it could be expected a super-exponential growth. We also give examples of periodic trees without invariant measures on their orbit. We use our construction to get quasi-periodic colored tilings of the hyperbolic disk.