Stats

This paper deals with a new Bayesian approach to the one-sample test for proportion. More specifically, let $x=(x_1,\dots ,x_n)$ be an independent random sample of size n from a Bernoulli distribution with an unknown parameter $\theta$. For a fixed value ${\theta }_0$, the goal is to test the null hypothesis $H_0:\theta ={\theta }_0$ against all possible alternatives. The proposed approach is based on using the well-known formula of the Kullback–Leibler divergence between two binomial distributions chosen in a certain way. Then, the difference of the distance from a priori to a posteriori is compared through the relative belief ratio (a measure of evidence). Some theoretical properties of the method are developed. Examples and simulation results are included. Full article

Rubin’s variance estimator of the multiple imputation estimator for a domain mean is not asymptotically unbiased. Kim et al. derived the closed-form bias for Rubin’s variance estimator. In addition, they proposed an asymptotically unbiased variance estimator for the multiple imputation estimator when the imputed values can be written as a linear function of the observed values. However, this needs the assumption that the covariance of the imputed values in the same imputed dataset is twice that in the different imputed datasets. In this study, we proposed a bootstrap variance estimator that does not need this assumption. Both theoretical argument and simulation studies show that it was unbiased and asymptotically valid. The new method was applied to the Hox pupil popularity data for illustration. Full article

The aim of the present paper is to demonstrate the viability of using data envelopment analysis (DEA) in a regional context to evaluate entrepreneurial activities. DEA was used to assess regional entrepreneurship in Greece using individual measures of entrepreneurship as inputs and employment rates as outputs. In addition to point estimates, a bootstrap algorithm was used to produce bias-corrected metrics. In the light of the results of the study, the Greek regions perform differently in terms of converting entrepreneurial activity into job creation. Moreover, there is some evidence that unemployment may be a driver of entrepreneurship and thus negatively affects DEA-based inefficiency. The derived indicators can serve as diagnostic tools and can also be used for the design of various interventions at the regional level. Full article

In the theory of special functions, finding correlations between different types of functions is of great interest as unifying results, especially when considering issues such as analytic continuation. In the present paper, the relation between Lambert W-function and generalized hypergeometric functions is discussed. It will be shown that it is possible to link these functions by following two different strategies, namely, by means of the direct and inverse Mellin transform of Lambert W-function and by solving the trinomial equation originally studied by Lambert and Euler. The new results can be used both to numerically evaluate Lambert W-function and to study its analytic structure. Full article

In this paper, we investigate a validation process in order to assess the predictive capabilities of a single degree-of-freedom oscillator. Model validation is understood here as the process of determining the accuracy with which a model can predict observed physical events or important features of the physical system. Therefore, assessment of the model needs to be performed with respect to the conditions under which the model is used in actual simulations of the system and to specific quantities of interest used for decision-making. Model validation also supposes that the model be trained and tested against experimental data. In this work, virtual data are produced from a non-linear single degree-of-freedom oscillator, the so-called oracle model, which is supposed to provide an accurate representation of reality. The mathematical model to be validated is derived from the oracle model by simply neglecting the non-linear term. The model parameters are identified via Bayesian updating. This calibration process also includes a modeling error due to model misspecification and modeled as a normal probability density function with zero mean and standard deviation to be calibrated. Full article

Understanding the factors that influence voter turnout is a fundamentally important question in public policy and political science research. Bayesian logistic regression models are useful for incorporating individual level heterogeneity to answer these and many other questions. When these questions involve incorporating individual level heterogeneity for large data sets that include many demographic and ethnic subgroups, however, standard Markov Chain Monte Carlo (MCMC) sampling methods to estimate such models can be quite slow and impractical to perform in a reasonable amount of time. We present an innovative closed form Empirical Bayesian approach that is significantly faster than MCMC methods, thus enabling the estimation of voter turnout models that had previously been considered computationally infeasible. Our results shed light on factors impacting voter turnout data in the 2000, 2004, and 2008 presidential elections. We conclude with a discussion of these factors and the associated policy implications. We emphasize, however, that although our application is to the social sciences, our approach is fully generalizable to the myriads of other fields involving statistical models with binary dependent variables and high-dimensional parameter spaces as well. Full article

Motivated by the recent popularization of the beta prime distribution, a more flexible generalization is presented to fit symmetrical or asymmetrical and bimodal data, and a non-monotonic failure rate. Thus, the Weibull-beta prime distribution is defined, and some of its structural properties are obtained. The parameters are estimated by maximum likelihood, and a new regression model is proposed. Some simulations reveal that the estimators are consistent, and applications to censored COVID-19 data show the adequacy of the models. Full article

Accurate time series prediction techniques are becoming fundamental to modern decision support systems. As massive data processing develops in its practicality, machine learning (ML) techniques applied to time series can automate and improve prediction models. The radical novelty of this paper is the development of a hybrid model that combines a new approach to the classical Kalman filter with machine learning techniques, i.e., support vector regression (SVR) and nonlinear autoregressive (NAR) neural networks, to improve the performance of existing predictive models. The proposed hybrid model uses, on the one hand, an improved Kalman filter method that eliminates the convergence problems of time series data with large error variance and, on the other hand, an ML algorithm as a correction factor to predict the model error. The results reveal that our hybrid models obtain accurate predictions, substantially reducing the root mean square and absolute mean errors compared to the classical and alternative Kalman filter models and achieving a goodness of fit greater than 0.95. Furthermore, the generalization of this algorithm was confirmed by its validation in two different scenarios. Full article

In the Big Data era, sampling remains a central theme. This paper investigates the characteristics of inverse sampling on two different datasets (real and simulated) to determine when big data become too small for inverse sampling to be used and to examine the impact of the sampling rate of the subsamples. We find that the method, using the appropriate subsample size for both the mean and proportion parameters, performs well with a smaller dataset than big data through the simulation study and real-data application. Different settings related to the selection bias severity are considered during the simulation study and real application. Full article

Due to the wide availability of functional data from multiple disciplines, the studies of functional data analysis have become popular in the recent literature. However, the related development in censored survival data has been relatively sparse. In this work, we consider the problem of analyzing time-to-event data in the presence of functional predictors. We develop a conditional generalized Kaplan–Meier (KM) estimator that incorporates functional predictors using kernel weights and rigorously establishes its asymptotic properties. In addition, we propose to select the optimal bandwidth based on a time-dependent Brier score. We then carry out extensive numerical studies to examine the finite sample performance of the proposed functional KM estimator and bandwidth selector. We also illustrated the practical usage of our proposed method by using a data set from Alzheimer’s Disease Neuroimaging Initiative data. Full article

Matrix/linear algebra continues bestowing benefits on theoretical and applied statistics, a practice it began decades ago (re Fisher used the word matrix in a 1941 publication), through a myriad of contributions, from recognition of a suite of matrix properties relevant to statistical concepts, to matrix specifications of linear and nonlinear techniques. Consequently, focused parts of matrix algebra are topics of several statistics books and journal articles. Contributions mostly have been unidirectional, from matrix/linear algebra to statistics. Nevertheless, statistics offers great potential for making this interface a bidirectional exchange point, the theme of this review paper. Not surprisingly, regression, the workhorse of statistics, provides one tool for such historically based recompence. Another prominent one is the mathematical matrix theory eigenfunction abstraction. A third is special matrix operations, such as Kronecker sums and products. A fourth is multivariable calculus linkages, especially arcane matrix/vector operators as well as the Jacobian term associated with variable transformations. A fifth, and the final idea this paper treats, is random matrices/vectors within the context of simulation, particularly for correlated data. These are the five prospectively reviewed discipline of statistics subjects capable of informing, inspiring, or otherwise furnishing insight to the far more general world of linear algebra. Full article

In this study, the estimation methods of bias-corrected maximum likelihood (BCML), bootstrap BCML (B-BCML) and Bayesian using Jeffrey’s prior distribution were proposed for the inverse Gaussian distribution with small sample cases to obtain the ML and Bayes estimators of the model parameters and the process performance index based on the lower specification process performance index. Moreover, an approximate confidence interval and the highest posterior density interval of the process performance index were established via the delta and Bayesian inference methods, respectively. To overcome the computational difficulty of sampling from the posterior distribution in Bayesian inference, the Markov chain Monte Carlo approach was used to implement the proposed Bayesian inference procedures. Monte Carlo simulations were conducted to evaluate the performance of the proposed BCML, B-BCML and Bayesian estimation methods. An example of the active repair times for an airborne communication transceiver is used for illustration. Full article

We discuss a Bayesian hierarchical copula model for clusters of financial time series. A similar approach has been developed in recent paper. However, the prior distributions proposed there do not always provide a proper posterior. In order to circumvent the problem, we adopt a proper global–local shrinkage prior, which is also able to account for potential dependence structures among different clusters. The performance of the proposed model is presented via simulations and a real data analysis. Full article

Textile and clothing (T&C) products contribute to a substantial proportion of the non-food product recalls in the European Union (EU) due to various levels of associated risks. Out of the listed 34 categories for product recalls in the EU’s Rapid Exchange of Information System (RAPEX), the category ’clothing, textiles, and fashion items’ was among the top 3 categories with the most recall cases during 2013–2019. Previous studies have attempted to highlight the issue of product recalls and their impacts from the perspective of a single company or selected companies, whereas limited attention is paid to understand the problem from a sector-specific perspective. However, considering the nature of product risks and the consistency in a higher number of recall cases, it is important to analyze the issue of product recalls in the T&C sector from a sector-specific perspective. In this context, the paper focuses on investigating the past recalls in the T&C sector reported RAPEX during 2005–2021 to understand the major trends in recall occurrence and associated hazards. Correspondence Analysis (CA) and Latent Dirichlet Allocation (LDA) were applied to analyze the qualitative and quantitative recall data. The results reveal that there is a geographical pattern for the product risk that leads to the recalls. The countries in eastern part of Europe tend to have proportionately high recalls in strangulation and choking-related issues, whereas chemical-related recalls are proportionately high in countries located in western part of Europe. Further, text-mining results indicate that design-related recall issues are more prevalent in children’s clothing. Full article

This paper presents a spatial analysis of the incidence rate of COVID-19 cases in the state of Paraná, Brazil, from June to December 2020, and a study of the incidence rate of COVID-19 cases associated with socioeconomic variables, such as the Gini index, Theil-L index, and municipal human development index (MHDI). The data were provided from the Paraná State Health Department and Paraná Institute for Economic and Social Development. For the study of spatial autocorrelation, the univariate global Moran index (I), local univariate Moran (LISA), global Geary (c), and univariate local Geary ($c_i$) were calculated. For the analysis of the spatial correlation, the global bivariate Moran index $\left(I_{xy}\right)$, the local multivariate Geary indices $\left(C_i^M\right)$, and the bivariate Lee index $\left(L_{xy}\right)$ were calculated. There is significant positive spatial autocorrelation between the incidence rate of COVID-19 cases and correlations between the incidence rate of COVID-19 cases and the Gini index, Theil-L index, and MHDI in the regions under study. The highest risk areas were concentrated in the macro-regions: east and west. Understanding the spatial distribution of COVID-19, combined with economic and social factors, can contribute to greater efficiency in preventive actions and the control of new viral epidemics. Full article

The importance of Lagrangian distributions and their applicability in real-world events have been highlighted in several studies. In light of this, we create a new zero-truncated Lagrangian distribution. It is presented as a generalization of the zero-truncated binomial distribution (ZTBD) and hence named the Lagrangian zero-truncated binomial distribution (LZTBD). The moments, probability generating function, factorial moments, as well as skewness and kurtosis measures of the LZTBD are discussed. We also show that the new model’s finite mixture is identifiable. The unknown parameters of the LZTBD are estimated using the maximum likelihood method. A broad simulation study is executed as an evaluation of the well-established performance of the maximum likelihood estimates. The likelihood ratio test is used to assess the effectiveness of the third parameter in the new model. Six COVID-19 datasets are used to demonstrate the LZTBD’s applicability, and we conclude that the LZTBD is very competitive on the fitting objective. Full article

We use the functional data methodology to examine whether there are significant differences between two waves of contagion by COVID-19 in Colombia between 7 July 2020 and 20 July 2021. A pointwise functional t-test is initially used, then an alternative statistical test proposal for paired samples is presented, which has a theoretical distribution and performs well in small samples. Our statistical test generates a scalar p-value, which provides a global idea about the significance of the positivity curves, complementing the existing punctual tests, as an advantage. Full article

Zipf’s law is well known in linguistics: the frequency of a word is inversely proportional to its rank. This is a special case of a more general power law, a common phenomenon in many kinds of real-world statistical data. Here, it is shown that snooker statistics also follow such a mathematical pattern, but with varying parameter values. Two types of rankings (prize money earned and centuries scored), and three different time frames (all-time, decade, and year) are considered. The results indicate that the power law parameter values depend on the type of ranking used, as well as the time frame considered. Furthermore, in some cases, the resulting parameter values vary significantly over time, for which a plausible explanation is provided. Finally, it is shown how individual rankings can be described somewhat more accurately using a log-normal distribution, but that the overall conclusions derived from the power law analysis remain valid. Full article

Given several different populations, the relative proportions of each in the high (or low) end of the distribution of a given characteristic are often more important than the overall average values or standard deviations. In the case of two different normally-distributed random variables, as is shown here, one of the (right) tail ratios will not only eventually be greater than 1 from some point on, but will even become infinitely large. More generally, in every finite mixture of different normal distributions, there will always be exactly one of those distributions that is not only overrepresented in the right tail of the mixture but even completely overwhelms all other subpopulations in the rightmost tails. This property (and the analogous result for the left tails), although not unique to normal distributions, is not shared by other common continuous centrally symmetric unimodal distributions, such as Laplace, nor even by other bell-shaped distributions, such as Cauchy (Lorentz) distributions. Full article