Artificial Intelligence and Predicting Illegal Immigration to the USA

The number of Mexican immigrants in the USA tripled between 1990 and 2015. In 2015, about 12 million undocumented immigrants lived in the USA, including 6.6 million undocumented Mexican immigrants. More than half of the undocumented immigrants in the USA enter the USA legally and overstay their visas. Therefore, it is essential to predict whether visa applicants overstay their visas or not. We use a set of pre-immigration variables for more than 6,281 individuals from Mexico to predict their legal status in the USA. By using eight machine learning techniques, we conclude that we can predict correctly the legal status of 80 per cent of Mexicans who migrate to the USA.     

Voluntary disclosure of sustainability reports by Canadian universities

In contrast to corporate firms, voluntary sustainability reporting by universities is still in its infancy. Against this background, we have investigated which Canadian universities report their sustainability performance and what specifically is reported. Our study applies content analyses as a methodological approach to determine the relative importance of disclosure topics by using a university-specific catalogue of indicators. This unique study completely covers all sustainability reports published between 2011 and 2015 by Canadian universities and as such provides evidence and analyses of voluntary sustainability reporting by universities, which has been the subject of very little research to date. The findings show that sustainability reporting by Canadian universities diverges considerably and the range of aspects included is relatively narrow. Overall, the results show a clear focus on the environmental dimension and very weak coverage of the social dimension. The environmental orientation of many Canadian universities seems to be a result of their participation in the STARS program.     

Joint modeling of linear degradation and failure time data with masked causes of failure under simple step-stress test

In this paper, we propose a method to model the relationship between degradation and failure time for a simple step-stress test where the underlying degradation path is linear and different causes of failure are possible. It is assumed that the intensity function depends only on the degradation value. No assumptions are made about the distribution of the failure times. A simple step-stress test is used to induce failure experimentally and a tampered failure rate model is proposed to describe the effect of the changing stress on the intensities. We assume that some of the products that fail during the test have a cause of failure that is only known to belong to a certain subset of all possible failures. This case is known as masking. In the presence of masking, the maximum likelihood estimates of the model parameters are obtained through the expectation–maximization algorithm by treating the causes of failure as missing values. The effect of incomplete information on the estimation of parameters is studied through a Monte-Carlo simulation. Finally, a real-world example is analysed to illustrate the application of the proposed methods.     

A Dynamic Model for the Cross‐sectional Distribution of Unemployment Rates

This paper proposes a model to describe the continuous time‐evolution of density of the cross‐sectional distribution of unemployment rates. The model is founded on the theory of analytical diffusion processes. The steady‐state distribution as well as the dynamic behaviour of the model are analytically derived. Parameters in the resulting analytical expressions are then fitted to US regional data. The empirical portion of the paper illustrates the usefulness of modeling the temporal evolution of the cross‐sectional distribution of unemployment rate, rather than simply attending to equilibrium implications of the process.     

On adaptive progressively Type-II censored competing risks data

In this article, a competing risks model based on exponential distributions is considered under the adaptive Type-II progressively censoring scheme introduced by Ng et al. [2009, Naval Research Logistics 56:687-698], for life testing or reliability experiment. Moreover, we assumed that some causes of failures are unknown. The maximum likelihood estimators (MLEs) of unknown parameters are established. The exact conditional and the asymptotic distributions of the obtained estimators are derived to construct the confidence intervals as well as the two different bootstraps of different unknown parameters. Under suitable priors on the unknown parameters, Bayes estimates and the corresponding two sides of Bayesian probability intervals are obtained. Also, for the purpose of evaluating the average bias and mean square error of the MLEs, and comparing the confidence intervals based on all mentioned methods, a simulation study was carried out. Finally, we present one real dataset to conduct the proposed methods.     

A new three-parameter ageing distribution

We propose a new three-parameter ageing distribution called the Weibull-Poisson (WP) distribution, which generalizes the exponential-Poisson (EP) distribution introduced by Kus (2007). This new distribution has a more general form of failure rate (hazard rate) function. With appropriate choice of parameter values, it is able to model three ageing classes of life distributions including decreasing failure rate (DFR), increasing failure rate (IFR), and modified upside-down-bathtub (MUBT)-shaped failure rate. It thus provides an alternative to many existing life distributions. Various properties of this distribution are discussed and the estimation of the parameters is considered by the expectation maximization (EM) algorithm. Also, the asymptotic variance-covariance matrices of these estimates are obtained. Furthermore, some expressions for the Rènyi and Shannon entropies are given. Simulation studies are performed and experimental results are illustrated based on a real data set.     

Statistical Analysis of the Log-Normal Distribution under Type-II Progressive Hybrid Censoring Schemes

In this article, we obtain the maximum likelihood estimators (MLEs) and approximate maximum likelihood estimators (AMLEs) of the parameters, from a two-parameter log-normal distribution based on the adaptive Type-II progressive hybrid censoring scheme, which was introduced by Ng et al. (2009 Ng , H. K. T. , Kundu , D. , Chan , P. S. ( 2009 ). Statistical analysis of exponential lifetimes under an adaptive Type-II progressively censoring scheme . Naval Research Logistics 56 : 687 – 698 .[Crossref], [Web of Science ®] , [Google Scholar]) for life testing or reliability experiment. In order to compare the results, we calculate corresponding estimators of the Type-II progressive hybrid censoring scheme. In particular, we provide computational formulas of the expected total test time and the expected number of failures for each scheme. We also compute the observed Fisher information matrix and use them to obtain the asymptotic confidence intervals. A simulation study carries out to evaluate the bias and mean square error of the MLEs and AMLEs from the two above-mentioned schemes. Finally, we present a numerical example to illustrate the methods of inference discussed here.