Assessing Statistical Results: Magnitude,Precision, and Model Uncertainty

ABSTRACT

Evaluating the importance and the strength of empirical evidence requires asking three questions: First, what are the practical implications of the findings? Second, how precise are the estimates? Confidence intervals provide an intuitive way to communicate precision. Although nontechnical audiences often misinterpret confidence intervals (CIs), I argue that the result is less dangerous than the misunderstandings that arise from hypothesis tests. Third, is the model correctly specified? The validity of point estimates and CIs depends on the soundness of the underlying model.     

“Me,the street,and a backpack”: employment,income, and physical capital in rural recovery

ABSTRACT

Recovery capital is a framework for understanding individuals’ resources for recovery from substance misuse. In a qualitative analysis of rural individuals in recovery (N = 49), the role of physical capital emerged prominently across ten focus groups. Participants highlighted the effects of employment status, income, and other forms of physical capital directly, as well as indirect effects through changes in human capital. Negative cultural capital components, in the form of stigma and employment discrimination, were described as barriers to physical capital acquisition and successful recovery. Based on these findings, we discuss rural recovery challenges and propose a model of recovery capital interactions.     

THE EXTENT OF THE MARKET AND INTEGRATION THROUGH FACTOR MARKETS: EVIDENCE FROM WHOLESALE ELECTRICITY

We document the influence of factor markets in determining the extent of the market, appealing to the Mundell hypothesis that trade in goods and factor markets are substitutes. We confirm this influence using the U.S. wholesale market for electric power. Although the Eastern, Western, and Texas regions cannot trade electricity, inputs such as natural gas move freely across these regions. Through a set of price transmission ratios, and a supply model for natural gas, we find regional electricity shocks do propagate across regions. We conclude output markets institutionally in autarky achieve modest degrees of economic integration through factor markets. (JEL C32, L94, Q41)     

Indigenous research methodology – weaving a research interface

ABSTRACT

Indigenous research Knowledges and methodologies have existed over millennia, however it is only recently that Indigenous scholars have been able to challenge institutional Western hegemony to reclaim sovereignty in the research space. Despite the high volume of quantitative research describing Aboriginal and Torres Strait Islander health, there has been limited evaluation of the value added through incorporation of Indigenous Knowledges and methodologies. ‘Research at the interface’ has been discussed as an Indigenous research methodology for researchers to contextualise and inform their research practices, between Indigenous and Western systems of knowledge. In this article we address the significance of ‘research at the interface’ for Aboriginal and Torres Strait Islander research, as an exciting opportunity for innovation to ensure strength, self-determination and resilience for Aboriginal and Torres Strait Islander communities engaged in research. We also introduce weaving a methodology for ‘research at the interface’ as a process for conceptualising Indigenous and quantitative research methodologies at the interface.     

Persistent Risk-Related Worry as a Function of Recalled Exposure to the Deepwater Horizon Oil Spill and Prior Trauma

Large oil spills are disasters associated with psychological effects for exposed communities. The amount of worry that individuals experience after a disaster may be influenced by many factors, such as the type and extent of exposure to disaster impacts, prior trauma, and sociodemographic characteristics. This study examined the nature and predictors of worry about ongoing impacts of the 2010 Deepwater Horizon (DH) oil spill reported by Gulf of Mexico coastal residents. A random sample of 2,520 adult residents of Gulf of Mexico coastal counties were administered a telephone survey in 2016, including items about persistent worry and exposure to DH impacts, prior trauma, residence at the time of the spill, and sociodemographic characteristics. Respondents varied in the amount of worry they reported about ongoing health, social, and economic impacts. Controlling for sociodemographic characteristics, higher exposure to the DH oil spill was related to higher levels of worry about ongoing impacts, with past traumatic events related specifically to worry about health impacts. Unexpectedly, those who moved into the region after the spill showed similar levels of worry to residents exposed to the spill, and higher levels than residents who did not recall being exposed to the DH oil spill. This study highlights the impact of the DH oil spill on coastal residents many years after the DH disaster. The findings underscore the need to examine multiple pathways by which individuals experience disasters and for risk researchers to close knowledge gaps about long-term impacts of oil spills within a multi-dimensional framework.     

A Starting Point for Navigating the World of Daily Fantasy Basketball

Fantasy sports, particularly the daily variety in which new lineups are selected each day, are a rapidly growing industry. The two largest companies in the daily fantasy business, DraftKings and Fanduel, have been valued as high as $2 billion. This research focuses on the development of a complete system for daily fantasy basketball, including both the prediction of player performance and the construction of a team. First, a Bayesian random effects model is used to predict an aggregate measure of daily NBA player performance. The predictions are then used to construct teams under the constraints of the game, typically related to a fictional salary cap and player positions. Permutation based and K-nearest neighbors approaches are compared in terms of the identification of “successful” teams—those who would be competitive more often than not based on historical data. We demonstrate the efficacy of our system by comparing our predictions to those from a well-known analytics website, and by simulating daily competitions over the course of the 2015–2016 season. Our results show an expected profit of approximately $9,000 on an initial $500 investment using the K-nearest neighbors approach, a 36% increase relative to using the permutation-based approach alone. Supplementary materials for this article are available online.     

Detecting Directionality in Time Series

Abstract

Directionality can be seen in many stationary time series from various disciplines, but it is overlooked when fitting linear models with Gaussian errors. Moreover, we cannot rely on distinguishing directionality by comparing a plot of a time series in time order with a plot in reverse time order. In general, a statistical measure is required to detect and quantify directionality. There are several quite different qualitative forms of directionality, and we distinguish: rapid rises followed by slow recessions; rapid increases and rapid decreases from the mean followed by slow recovery toward the mean; directionality above or below some threshold; and intermittent directionality. The first objective is to develop a suite of statistical measures that will detect directionality and help classify its nature. The second objective is to demonstrate the potential benefits of detecting directionality. We consider applications from business, environmental science, finance, and medicine. Time series data are collected from many processes, both natural and anthropogenic, by a wide range of organizations, and directionality can easily be monitored as part of routine analysis. We suggest that doing so may provide new insights to the processes.     

Habitat selection by an avian top predator in the tropical megacity of Delhi: human activities and socio-religious practices as prey-facilitating tools

Research in urban ecology is growing rapidly in response to the exponential growth of the urban environment. However, few studies have focused on tropical megacities, and on the interplay between predators’ habitat selection and human socio-economic aspects, which may mediate their resilience and coexistence with humans. We examined mechanisms of breeding habitat selection by a synanthropic raptor, the Black Kite Milvus migrans, in Delhi (India) where kites mainly subsist on: (1) human refuse and its associated prey-fauna, and (2) ritualised feeding of kites, particularly practised by Muslims. We used mixed effects models to test the effect of urban habitat configuration and human practices on habitat selection, site occupancy and breeding success. Kite habitat decisions, territory occupancy and breeding success were tightly enmeshed with human activities: kites preferred areas with high human density, poor waste management and a road configuration that facilitated better access to resources provided by humans, in particular to Muslim colonies that provided ritual subsidies. Furthermore, kites bred at ‘clean’ sites with less human refuse only when close to Muslim colonies, suggesting that the proximity to ritual-feeding sites modulated the suitability of other habitats. Rather than a nuisance to avoid, as previously portrayed, humans were a keenly-targeted foraging resource, which tied a predator’s distribution to human activities, politics, history, socio-economics and urban planning at multiple spatio-temporal scales. Many synurbic species may exploit humans in more subtle and direct ways than was previously assumed, but uncovering them will require greater integration of human socio-cultural estimates in urban ecological research.

     

Dynamic inference for non-Markov transition probabilities under random right censoring

The main contribution of this article is the verification of weak convergence of a general non-Markov (NM) state transition probability estimator by Titman, which has not yet been done for any other general NM estimator. A similar theorem is shown for the bootstrap, yielding resampling-based inference methods for statistical functionals. Formulas of the involved covariance functions are presented in detail. Particular applications include the conditional expected length of stay in a specific state, given occupation of another state in the past, and the construction of time-simultaneous confidence bands for the transition probabilities. The expected lengths of stay in a two-sample liver cirrhosis dataset are compared and confidence intervals for their difference are constructed. With borderline significance and in comparison to the placebo group, the treatment group has an elevated expected length of stay in the healthy state given an earlier disease state occupation. In contrast, the Aalen-Johansen (AJ) estimator-based confidence interval, which relies on a Markov assumption, leads to a drastically different conclusion. Also, graphical illustrations of confidence bands for the transition probabilities demonstrate the biasedness of the AJ estimator in this data example. The reliability of these results is assessed in a simulation study.