Diversity and structure of urban forests of Sahel cities in Niger

Urban Ecosystems - Urbanization in the Sahel is constantly competing with and greatly affecting the woody flora in urban areas. Urbanization can replace the species mix, leading to changes in plant...     

Fabrication of a desired truth: the oblivion of a Naxalite woman in Jhumpa Lahiri’s The Lowland

Jhumpa Lahiri’s The Lowland (2013) explores effects of the 1967 Communist Naxalbari uprising in West Bengal India. Irrespective of the glowing reviews the author earned for her truthful representations, the novel presents the pro-Communist uprising in a particular discursive regime that establishes a particular way of remembering and forgetting. Drawing on Foucault’s notion of ‘subjugated knowledges,’ this essay seeks to examine the epistemic hegemonies and mainstream perspectives of the novel that have confined particular experiences and memories of the movement to the margins and rendered them unworthy of epistemic respect in the battle among power/knowledge frameworks. The novel reconstitutes a gendered history of the movement in which women’s story of engagement is spatiotemporally erased and reformulated. I argue that the genealogy of this particular oversight is rooted in the heteronormative capitalist ideology of the States that exercises discursive power over individuals to fabricate a desired truth.     

Consistency of information criteria for model selection with missing data

ABSTRACT

In this paper, we investigate the consistency of the Expectation Maximization (EM) algorithm-based information criteria for model selection with missing data. The criteria correspond to a penalization of the conditional expectation of the complete data log-likelihood given the observed data and with respect to the missing data conditional density. We present asymptotic properties related to maximum likelihood estimation in the presence of incomplete data and we provide sufficient conditions for the consistency of model selection by minimizing the information criteria. Their finite sample performance is illustrated through simulation and real data studies.     

Local perceptions of socio-ecological drivers and effects of coastal armoring: the case of Moorea,French Polynesia

Population and Environment - This paper presents a transdisciplinary study focusing on the socio-ecological mechanisms at play in the alteration of Moorea’s (French Polynesia) coastline....     

Modelling Socio-Spatial Change: Istanbul,Kadıköy Case

Social Indicators Research - This study aims to understand the relationship between social structure and morphological character based on a case area...     

Compound Poisson frailty model with a gamma process prior for the baseline hazard: accounting for a cured fraction

Cox model and traditional frailty models assume that all individuals will eventually experience the event of interest. This assumption is often overlooked, and situations will arise where it is not realistic. We introduce Compound Poisson frailty model for survival analysis to deal with populations in which some of the individuals will not experience the event of interest. This model assumes that the target population is a mixture of individuals with zero frailty and those with positive frailty. In this paper, we consider a compound Poisson frailty model for right-censored event times from a Bayesian perspective and compute the Bayesian estimator using the Markov Chain Monte Carlo method, where a Gamma process prior is adopted for the baseline hazard function. Furthermore, we evaluate the approach using simulation studies and demonstrate the methodology by analyzing the data from achalasia patient cohort.KEYWORDS: Bayesian approach, survival model, gamma process, frailty, compound Poisson     

On the distribution-free confidence intervals and universal bounds for quantiles based on joint records

In this paper, we consider three distribution-free confidence intervals for quantiles given joint records from two independent sequences of continuous random variables with a common continuous distribution function. The coverage probabilities of these intervals are compared. We then compute the universal bounds of the expected widths of the proposed confidence intervals. These results naturally extend to any number of independent sequences instead of just two. Finally, the proposed confidence intervals are applied for a real data set to illustrate the practical usefulness of the procedures developed here.     

A Poisson-Based Framework for Setting Poverty Thresholds Using Indicator Lists

Poverty is one of the most important concepts in the social sciences, yet commonly-used thresholds for the operationalization of poverty have little or no conceptual basis. This is especially true of the “relative deprivation” poverty concept, where the arbitrary threshold of missing k ≥ 3 items from a list of socially defined necessities is the accepted operationalization. This paper presents a conceptual framework for meaningfully setting k based on the properties of the Poisson distribution. Data from the 2011 Swiss Household Panel are used to illustrate this approach for three poverty concepts: conventional relative deprivation based on non-affordability of items (“afford-deprivation”), simplified relative deprivation based on non-possession of items (“possess-deprivation”), and a novel approach based on the status syndrome concept (“high life burden”). Proof-of-concept analyses suggest thresholds of k ≥ 2 for conventional afford-deprivation, k ≥ 5 for possess-deprivation, and k ≥ 6 for high life burden. In addition to providing a rationale for k, the Poisson-based approach allows for the systematic variation of k in different empirical contexts. It also supports the estimation of “adjusted” poverty rates that account for the chance probability that non-poverty households are accidentally miscategorized as being in poverty.     

Resampling for Order Estimation of Autoregressive Models with Missing Data

In this article, we consider the order estimation of autoregressive models with incomplete data using the expectation–maximization (EM) algorithm-based information criteria. The criteria take the form of a penalization of the conditional expectation of the log-likelihood. The evaluation of the penalization term generally involves numerical differentiation and matrix inversion. We introduce a simplification of the penalization term for autoregressive model selection and we propose a penalty factor based on a resampling procedure in the criteria formula. The simulation results show the improvements yielded by the proposed method when compared with the classical information criteria for model selection with incomplete data.     

Exploring the co-movements between COVID-19 pandemic and international air traffic: A global perspective based on wavelet analysis

The travel and tourism industry was one of the fastest-growing industries before the onset of the COVID-19 pandemic. However, to avoid COVID-19 spread, the government authorities imposed strict lockdown and international border restrictions except for some emergency international flights that badly hit the travel and tourism industry. The study explores the nexus between international air departures and the COVID-19 pandemic in this strain. We use a novel wavelet coherence approach to dissect the lead and lag relationships between international flight departures and COVID-19 deaths from January 2020 to September 2020 (COVID-19 first wave period). The results reveal that international flights cause the spread of COVID-19 spread during May 2020 to June 2020 worldwide. The overall findings suggest asymmetries between daily international flight departures and COVID-19 deaths globally at different time-frequency periods due to uncertainty surrounding the COVID-19 pandemic. The study will be conducive for the policymakers to control the upsurge of COVID-19 spread worldwide.