Monotonic Transformations Research Articles

Bayesian Inference in Nonparanormal Graphical Models

Gaussian graphical models have been used to study intrinsic dependence among several variables, but the Gaussianity assumption may be restrictive in many applications. A nonparanormal graphical model is a semiparametric generalization for continuous variables where it is assumed that the variables follow a Gaussian graphical model only after some unknown smooth monotone transformations on each of them. We consider a Bayesian approach in the nonparanormal graphical model by putting priors on the unknown transformations through a random series based on B-splines where the coefficients are ordered to induce monotonicity. A truncated normal prior leads to partial conjugacy in the model and is useful for posterior simulation using Gibbs sampling. On the underlying precision matrix of the transformed variables, we consider a spike-and-slab prior and use an efficient posterior Gibbs sampling scheme. We use the Bayesian Information Criterion to choose the hyperparameters for the spike-and-slab prior. We present a posterior consistency result on the underlying transformation and the precision matrix. We study the numerical performance of the proposed method through an extensive simulation study and finally apply the proposed method on a real data set.

On generalized conditional cumulative residual inaccuracy measure

Recently, the notion of cumulative residual Rényi’s entropy has been proposed in the literature as a measure of information that parallels Rényi’s entropy. Motivated by this, here we introduce a generalized measure of it, namely cumulative residual inaccuracy of order α. We study the proposed measure for conditionally specified models of two components having possibly different ages called generalized conditional cumulative residual inaccuracy measure. Several properties of generalized conditional cumulative residual inaccuracy measure including the effect of monotone transformation are investigated. Further, we provide some bounds on using the usual stochastic order and characterize some bivariate distributions using the concept of conditional proportional hazard rate model.

On shift-dependent generalized entropies for doubly truncated random variable

Recently, Das (2017) studied the importance of weighted generalized entropy for one sided truncation problems. There are some situations in survival study, where data are usually truncated from both sides. In such cases, individuals whose event-time lies within a certain time interval are only observed. The concept of first kind as well as second kind weighted doubly truncated generalized entropy measures is studied in this paper. It is showed that they characterize the distribution function uniquely. Further, the effect of monotone transformations on these measures is discussed. Uncertainty orders and its relation with the usual stochastic order are presented. Nonparametric class of lifetime distributions is introduced and some inequalities are obtained. Various examples are provided for illustration purpose.

Some Improvements on Markov's Theorem with Extensions

ABSTRACTMarkov's theorem for an upper bound of the probability related to a nonnegative random variable has been improved using additional information in almost the nontrivial entire range of the variable. In the improvement, Cantelli's inequality is applied to the square root of the original variable, whose expectation is finite when that of the original variable is finite. The improvement has been extended to lower bounds and monotonic transformations of the original variable. The improvements are used in Chebyshev's inequality and its multivariate version.

When is the Wilcoxon-Mann-Whitney procedure a test of location? Implications for effect-size measures.

The Wilcoxon-Mann-Whitney procedure is invariant under monotone transformations but its use as a test of location or shift is said not to be so. It tests location only under the shift model, the assumption of parallel cumulative distribution functions (cdfs). We show that infinitely many monotone transformations of the measured variable produce parallel cdfs, so long as the original cdfs intersect nowhere or everywhere. Thus there are infinitely many effect sizes measured as shifts of medians, invalidating the notion that there is one true shift parameter and thereby rendering any single estimate dubious. Measuring effect size using the probability of superiority alleviates this difficulty.

Composite Coefficient of Determination and Its Application in Ultrahigh Dimensional Variable Screening

ABSTRACT In this article, we propose to measure the dependence between two random variables through a composite coefficient of determination (CCD) of a set of nonparametric regressions. These regressions take consecutive binarizations of one variable as the response and the other variable as the predictor. The resulting measure is invariant to monotonic marginal variable transformation, rendering it robust against heavy-tailed distributions and outliers, and convenient for independent testing. Estimation of CCD could be done through kernel smoothing, with a consistency rate of root-n. CCD is a natural measure of the importance of variables in regression and its sure screening property, when used for variable screening, is also established. Comprehensive simulation studies and real data analysis show that the newly proposed measure quite often turns out to be the most preferred compared to other existing methods both in independence testing and in variable screening. Supplementary materials for this article are available online.

QUANTILE-BASED STUDY OF (DYNAMIC) INACCURACY MEASURES

AbstractIn the present communication, we introduce quantile-based (dynamic) inaccuracy measures and study their properties. Such measures provide an alternative approach to evaluate inaccuracy contained in the assumed statistical models. There are several models for which quantile functions are available in tractable form, though their distribution functions are not available in explicit form. In such cases, the traditional distribution function approach fails to compute inaccuracy between two random variables. Various examples are provided for illustration purpose. Some bounds are obtained. Effect of monotone transformations and characterizations are provided.

Deconstructing Odorant Identity via Primacy in Dual Networks.

In the olfactory system, odor percepts retain their identity despite substantial variations in concentration, timing, and background. We study a novel strategy for encoding intensity-invariant stimulus identity that is based on representing relative rather than absolute values of stimulus features. For example, in what is known as the primacy coding model, odorant identities are represented by the conditions that some odorant receptors are activated more strongly than others. Because, in this scheme, odorant identity depends only on the relative amplitudes of olfactory receptor responses, identity is invariant to changes in both intensity and monotonic nonlinear transformations of its neuronal responses. Here we show that sparse vectors representing odorant mixtures can be recovered in a compressed sensing framework via elastic net loss minimization. In the primacy model, this minimization is performed under the constraint that some receptors respond to a given odorant more strongly than others. Using duality transformation, we show that this constrained optimization problem can be solved by a neural network whose Lyapunov function represents the dual Lagrangian and whose neural responses represent the Lagrange coefficients of primacy and other constraints. The connectivity in such a dual network resembles known features of connectivity in olfactory circuits. We thus propose that networks in the piriform cortex implement dual computations to compute odorant identity with the sparse activities of individual neurons representing Lagrange coefficients. More generally, we propose that sparse neuronal firing rates may represent Lagrange multipliers, which we call the dual brain hypothesis. We show such a formulation is well suited to solve problems with multiple interacting relative constraints.

Morphological comparison of signals and its application for estimating signal lag time

Mathematical methods are proposed for comparing the shape of signals with amplitudes distorted by unknown monotonic transformations. These methods are based on the solution of the problems of the best approximation of the signal under analysis to signals of a specified class, and used in estimating the lag time of one fragment of signal with respect to another. Such problems arise, for example, in determining the direction of propagation of a sound wave in the atmosphere. The solution to this problem is based on the assumption that the conditions of the signal detection are different at different spatial points; as a result, the measured signals differ, not only in their lag time but also in nonlinear distortions, such that only the general sape of the signal is preserved: if the amplitude of one signal is the result of a strictly monotonic transformation of the amplitude of another signal, then their shapes are equivalent. In addition, the measurements are accompanied by an additive noise with an unknown dispersion.

Controlling for ability using test scores

SummaryThis paper proposes a semiparametric method to control for ability using standardized test scores, or other item response assessments, in a regression model. The proposed method is based on a model in which the parameter of interest is invariant to monotonic transformations of ability. I show that the estimator is consistent as both the number of observations and the number of items on the test grow to infinity. I also derive conditions under which this estimator is root‐n consistent and asymptotically normal. The proposed method is easy to implement, does not impose a parametric item response model, and does not require item‐level data. I demonstrate the finite‐sample performance in a Monte Carlo study and implement the procedure for a wage regression using data from the NLSY1979.

Two-phase equilibrium microstructures against optimal composite microstructures

We relate two problems which arise from different branches of mechanics of materials: construction of limiting phase transformation surfaces in strain space and stress–strain diagrams for stress-induced phase transitions and optimal design of two-phase 3D composites in the sense of minimizing its energy. In Antimonov et al. (Int J Eng Sci 98:153–182, 2015) for the case of isotropic phases, it was shown that given a new phase volume fraction and depending on average strain, the strain energy of a two-phase linear-elastic composite is minimized by either direct or inclined simple laminates, direct or skew second-rank laminates or third-rank laminates. Then these results were applied for the construction of direct and reverse transformations limiting surfaces in strain space for elastic solids undergoing phase transformations by additional minimization with respect to the new phase volume fraction and finding the strains at which minimizing volume fraction equals zero or one. In the present paper we construct stress–strain diagrams on various straining paths at which a material undergoes the phase transformation. We demonstrate that an additional degree of freedom—new phase volume fraction—may crucially result in instability of two-phase microstructures even if the microstructures are energy minimizers for composites with given volume fractions of phases. This in turn may lead to incompleteness of monotonic phase transformations and broken stress–strain diagrams. We study how such a behavior depends on a loading path and chemical energies of the phases.

单调保k变换半群OR<sub>n</sub>(K)的Green关系

单调保k变换半群OR<sub>n</sub>(K)的Green关系

A Simulation Study on Comparing General Class of Semiparametric Transformation Models for Survival Outcome with Time-Varying Coefficients and Covariates

The consideration of the time-varying covariate and time-varying coefficient effect in survival models are plausible and robust techniques. Such kind of analysis can be carried out with a general class of semiparametric transformation models. The aim of this article is to develop modified estimating equations under semiparametric transformation models of survival time with time-varying coefficient effect and time-varying continuous covariates. For this, it is important to organize the data in a counting process style and transform the time with standard transformation classes which shall be applied in this article. In the situation when the effect of coefficient and covariates change over time, the widely used maximum likelihood estimation method becomes more complex and burdensome in estimating consistent estimates. To overcome this problem, alternatively, the modified estimating equations were applied to estimate the unknown parameters and unspecified monotone transformation functions. The estimating equations were modified to incorporate the time-varying effect in both coefficient and covariates. The performance of the proposed methods is tested through a simulation study. To sum up the study, the effect of possibly time-varying covariates and time-varying coefficients was evaluated in some special cases of semiparametric transformation models. Finally, the results have shown that the role of the time-varying covariate in the semiparametric transformation models was plausible and credible.

A Possible Explanation of Vanishing Halo Velocity Bias

Recently Chen et al. (2018, ApJ, 861, 58) accurately determined the volume weighted halo velocity bias in simulations, and found that the deviation of velocity bias from unity is much weaker than the peak model prediction. Here we present a possible explanation of this vanishing velocity bias. The starting point is that, halos are peaks in the low redshift {\it non-Gaussian} density field with smoothing scale $R_{\Delta}$ (virial radius), instead of peaks in the high redshift initial {\it Gaussian} density field with a factor of $\mathcal{O}(\Delta^{1/3})$ larger smoothing scale. Based on the approximation that the density field can be Gaussianized by a local and monotonic transformation, we extend the peak model to the non-Gaussian density field and derive the analytical expression of velocity dispersion and velocity power spectrum of these halos. The predicted deviation of velocity bias from unity is indeed much weaker than the previous prediction, and the agreement with the simulation results is significantly improved.

Comparing Signal Waveforms and Their Use in Estimating Signal Lag Time

Mathematical methods are proposed for comparing the waveforms of signals with amplitudes distorted by unknown monotonic transformations and random noise. These methods are based on solving the problems of the best approximation of the signal under analysis to signals of a specified class and used in estimating the lag time of one fragment of signal with respect to another. Such problems arise, for example, in determining the direction of propagation of a sound wave in the atmosphere. The solution to this problem is based on the assumption that the conditions of the signal detection are different at different spatial points; as a result, the measured signals differ not only in their lag time, but also in nonlinear distortions, such that only the general waveform of the signal is preserved: if the amplitude of one signal is the result of a strictly monotonic transformation of the amplitude of another signal, then their waveforms are equivalent. In addition, the measurements are accompanied by an additive noise with an unknown dispersion.

Measuring and testing for interval quantile dependence

In this article, we introduce the notion of interval quantile independence which generalizes the notions of statistical independence and quantile independence. We suggest an index to measure and test departure from interval quantile independence. The proposed index is invariant to monotone transformations, nonnegative and equals zero if and only if the interval quantile independence holds true. We suggest a moment estimate to implement the test. The resultant estimator is root-$n$-consistent if the index is positive and $n$-consistent otherwise, leading to a consistent test of interval quantile independence. The asymptotic distribution of the moment estimator is free of parent distribution, which facilitates to decide the critical values for tests of interval quantile independence. When our proposed index is used to perform feature screening for ultrahigh dimensional data, it has the desirable sure screening property.

Metric Transformations and the Filtered Monotonic Polynomial Item Response Model.

The [Formula: see text] metric in item response theory is often not the most useful metric for score reporting or interpretation. In this paper, I demonstrate that the filtered monotonic polynomial (FMP) item response model, a recently proposed nonparametric item response model (Liang & Browne in J Educ Behav Stat 40:5-34, 2015), can be used to specify item response models on metrics other than the [Formula: see text] metric. Specifically, I demonstrate that any item response function (IRF) defined within the FMP framework can be re-expressed as another FMP IRF by taking monotonic transformations of the latent trait. I derive the item parameter transformations that correspond to both linear and nonlinear transformations of the latent trait metric. These item parameter transformations can be used to define an item response model based on any monotonic transformation of the [Formula: see text] metric, so long as the metric transformation is approximated by a monotonic polynomial. I demonstrate this result by defining an item response model directly on the approximate true score metric and discuss the implications of metric transformations for applied testing situations.

Note on sample quantiles for ordinal data

The arithmetic mean computed over ordinal data has to be interpreted with care. Instead it is often recommended to compute the sample median, or more generally sample quantiles. The virtue of raw quantiles is that they are not affected by an arbitrary rescaling of the data. Unfortunately, they are not very informative when an ordinal variable falls into only few categories. The informational content is larger for so-called grouped quantiles interpolating around one possible value. In this note we show, however, that they turn out to be not invariant with respect to strictly monotonous transformations as long as the possible outcomes are not equidistant. This motivates to suggest the new centered interpolated quantiles. They are designed to be invariant with respect to transformations that preserve the ranking of the possible values.

Sample Quantiles for Ordinal Data

Computing the arithmetic mean over ordinal data is not a meaningful procedure. Instead it is often recommended to compute the sample median, or more generally sample quantiles. The virtue of raw quantiles is that they are not affected by an arbitrary rescaling of the data. Unfortunately, they are not very informative when an ordinal variable falls into only few categories. The informational content is larger for so-called grouped quantiles interpolating around one possible value. In this note we show, however, that they turn out to be not invariant with respect to strictly monotonous transformations as long as the possible outcomes are not equidistant. This motivates to suggest the new centered interpolated quantiles. They are designed to be invariant with respect to transformations that preserve the ranking of the possible values.

Signed difference analysis: Testing for structure under monotonicity

Signed difference analysis (SDA), introduced by Dunn and James (2003), is used to derive testable consequences from a psychological model in which each dependent variable is presumed to be a monotonically increasing function of a linear or nonlinear combination of latent variables. SDA is based on geometric properties of the combination of latent variables that are preserved under arbitrary monotonic transformation and requires estimation neither of these variables nor of the monotonic functions. The aim of the present paper is to connect SDA to the mathematical theory of oriented matroids. This serves to situate SDA within an existing formalism, to clarify its conceptual foundation, and to solve outstanding conjectures. We describe the theory of oriented matroids as it applies to SDA and derive tests for both linear and nonlinear models. In addition, we show that state-trace analysis is a special case of SDA which we extend to models such as additive conjoint measurement where each dependent variable is the same unspecified monotonic function of a linear combination of latent variables. Lastly, we show how measurement error can be accommodated based on the model-fitting approach developed by Kalish et al. (2016).