Bayesian analysis of outlier problems using divergence measures

A Bayesian approach is presented for detecting influential observations using general divergence measures on the posterior distributions. A sampling-based approach using a Gibbs or Metropolis-within-Gibbs method is used to compute the posterior divergence measures. Four specific measures are proposed, which convey the effects of a single observation or covariate on the posterior. The technique is applied to a generalized linear model with binary response data, an overdispersed model and a nonlinear model. An asymptotic approximation using Laplace method to obtain the posterior divergence is also briefly discussed.     

‘Others’ Within the ‘Others’: An Intersectional Analysis of Gender Violence in India

Gender Issues - In 2018, the rapes of two young girls shook India. The ruling government blatantly supported the perpetrators in both cases. It was also highlighted that if the victims were high...     

Estimation of reliability of multicomponent stress–strength for a Kumaraswamy distribution

This article deals with the Bayesian and non Bayesian estimation of multicomponent stress–strength reliability by assuming the Kumaraswamy distribution. Both stress and strength are assumed to have a Kumaraswamy distribution with common and known shape parameter. The reliability of such a system is obtained by the methods of maximum likelihood and Bayesian approach and the results are compared using Markov Chain Monte Carlo (MCMC) technique for both small and large samples. Finally, two data sets are analyzed for illustrative purposes.     

The Impact of Lean Management Practices and Sustainably‐Oriented Innovation on Sustainability Performance of Small and Medium‐Sized Enterprises: Empirical Evidence from the UK

While lean management practices (LMP) help small and medium‐sized enterprises (SMEs) to be efficient, sustainability‐oriented innovation (SOI) facilitates adopting environmental and social practices. Although prior research looks into the effect of LMP on the economic performance (EP) of SMEs, less is known about the effect of LMP on sustainability (economic, environmental and social) performance. Studies on the effect of SOI on sustainability and economic performance are also scant. Additionally, examining the mediating effect of corporate social responsibility (CSR) practices (environmental and social practices) on both LMP and SOI achieving sustainability performance (SP) is rare. This research bridges these knowledge gaps by answering the question of how LMP, SOI, CSR practices, sustainability and economic performance are correlated. Through hypothesis testing using structural equation modelling, this study reveals the impact of LMP, SOI, CSR (environmental and social) practices on sustainability and economic performance. The study uses data from 119 SMEs within manufacturing industries in the Midlands, UK. The analysis reveals that LMP and SOI facilitate achieving both sustainability and economic performance, and SOI mediates LMP to achieve sustainability performance. Additionally, although CSR practices mediate LMP to achieve sustainability performance, they only borderline mediate SOI to achieve sustainability performance.     

Unified multivariate survival model with a surviving fraction: an application to a Brazilian customer churn data

In this paper we propose a new lifetime model for multivariate survival data in presence of surviving fractions and examine some of its properties. Its genesis is based on situations in which there are m types of unobservable competing causes, where each cause is related to a time of occurrence of an event of interest. Our model is a multivariate extension of the univariate survival cure rate model proposed by Rodrigues et al. [37 J. Rodrigues, V.G. Cancho, M. de Castro, and F. Louzada-Neto, On the unification of long-term survival models, Statist. Probab. Lett. 79 (2009), pp. 753–759. doi: 10.1016/j.spl.2008.10.029[Crossref], [Web of Science ®] , [Google Scholar]]. The inferential approach exploits the maximum likelihood tools. We perform a simulation study in order to verify the asymptotic properties of the maximum likelihood estimators. The simulation study also focus on size and power of the likelihood ratio test. The methodology is illustrated on a real data set on customer churn data.     

Statistical inference based on generalized Lindley record values

This paper addresses the problems of frequentist and Bayesian estimation for the unknown parameters of generalized Lindley distribution based on lower record values. We first derive the exact explicit expressions for the single and product moments of lower record values, and then use these results to compute the means, variances and covariance between two lower record values. We next obtain the maximum likelihood estimators and associated asymptotic confidence intervals. Furthermore, we obtain Bayes estimators under the assumption of gamma priors on both the shape and the scale parameters of the generalized Lindley distribution, and associated the highest posterior density interval estimates. The Bayesian estimation is studied with respect to both symmetric (squared error) and asymmetric (linear-exponential (LINEX)) loss functions. Finally, we compute Bayesian predictive estimates and predictive interval estimates for the future record values. To illustrate the findings, one real data set is analyzed, and Monte Carlo simulations are performed to compare the performances of the proposed methods of estimation and prediction.     

Bayesian robustness for multiparameter problems

Bayesian robustness is studied for ε-contamination classes of prior distributions. Nonparametric classes of contsminations such as the class of all unimodal spherically symmetric densities are considered here. Posterior φ-divergence and its curvature are used to measure the sensitivity of priors on the resulting posterior densities. Examples are provided to illustrate our results.