A stochastic differential equation approach to the analysis of the 2017 and 2019 UK general election polls

Human dynamics and sociophysics build on statistical models that can shed light on and add to our understanding of social phenomena. We propose a generative model based on a stochastic differential equation that enables us to model the opinion polls leading up to the 2017 and 2019 UK general elections and to make predictions relating to the actual results of the elections. After a brief analysis of the time series of the poll results, we provide empirical evidence that the gamma distribution, which is often used in financial modelling, fits the marginal distribution of this time series. We demonstrate that the proposed poll-based forecasting model may improve upon predictions based solely on polls. The method uses the Euler–Maruyama method to simulate the time series, measuring the prediction error with the mean absolute error and the root mean square error, and as such could be used as part of a toolkit for forecasting elections.     

A new approach to estimating a profit frontier using the censored stochastic frontier model

The translog profit functional form is widely used to study technical efficiency for banks. Although this functional form is known as being flexible, it is not applicable to those banks incurring economic losses. The recently developed approach, i.e., the censored stochastic frontier model (CSFM), by Tsay et al. (2013) appears to be superior to existing approaches, since CSFM does not need to transform negative profit into positive profit before taking the natural logarithm. The transformation with respect to the profit variable tends to bias the parameter estimates of the profit frontier and the subsequent profit efficiency measure. We show that the parameter estimates of CSFM have the desirable statistical properties. Moreover, empirical results reveal that the mean profit efficiency of CSFM is more robust than those models using transformed profits across the sub-periods 1991–1998 and 1999–2009.     

An optimization approach to strategic sourcing: A case study of the United States Air Force

The DoD annually procures billions of dollars worth of systems, supplies, and services in support of the national military strategy. Faced with budget cuts and other resource constraints, the DoD must transform its procurement process to ensure cost-effective sourcing of critical supplies and services. One aspect of current transformation in the DoD is the use of a strategic sourcing approach for the procurement of services at military installations. Using the Air Force's strategic sourcing process as our context, we developed an optimization model for selecting a set of proposals from among multiple offerors for services to be performed at multiple installations. The selection achieves the most favorable objective by balancing the confidence level in an offeror's past performance with the cost of services to the Air Force. The research findings, which are based on a realistic scenario, demonstrate improvements over the current sourcing process in both overall performance and cost.