On this page there are links to applied statistical research papers that are eminently readable. By this we mean they do not require a deep familiarity with, and understanding of, sophisticated statistical methods. It is our intention that one or more of these papers might ignite your desire to engage in applied statistical research. 

---

Goel, S., Rao, J. M., & Shroff, R. (2016). Precinct or prejudice? Understanding racial disparities in New York City’s stop-and-frisk policy. The Annals of Applied Statistics, 10(1), 365-394. (Google Scholar)

Abstract:

Recent studies have examined racial disparities in stop-and-frisk, a widely employed but controversial policing tactic. The statistical evidence, however, has been limited and contradictory. We investigate by analyzing three million stops in New York City over five years, focusing on cases where officers suspected the stopped individual of criminal possession of a weapon (CPW). For each CPW stop, we estimate the ex ante probability that the detained suspect has a weapon. We find that in more than 40% of cases, the likelihood of finding a weapon (typically a knife) was less than 1%, raising concerns that the legal requirement of “reasonable suspicion” was often not met. We further find that blacks and Hispanics were disproportionately stopped in these low hit rate contexts, a phenomenon that we trace to two factors: (1) lower thresholds for stopping individuals— regardless of race — in high-crime, predominately minority areas, particularly public housing; and (2) lower thresholds for stopping minorities relative to similarly situated whites. Finally, we demonstrate that by conducting only the 6% of stops that are statistically most likely to result in weapons seizure, one can both recover the majority of weapons and mitigate racial disparities in who is stopped. We show that this statistically informed stopping strategy can be approximated by simple, easily implemented heuristics with little loss in efficiency.

---

Billick, I., & Case, T. J. (1994). Higher order interactions in ecological communities: what are they and how can they be detected? Ecology, 75(6), 1529-1543. (Google Scholar)

Abstract:

The detection and significance of higher order interactions (HOIs) between species has been a matter of debate and experimentation in community ecology for several decades. HOIs are considered potentially significant because their presence is assumed to mean that the dynamic behavior of a full community of species is unpredictable based on observations of interactions between subsets of the species within the community. Despite such attention, the causal mechanisms that produce HOIs have been inadequately discussed. We discuss three different usages of the term HOIs and provide insight as to why HOIs might be found within a given community. HOIs may be detected for three reasons: inappropriate assumptions made concerning species interactions that influence statistical tests, unmeasured parameters and variables, and interaction modifications (i.e., a functional change in the interaction of two species caused by a third species). This confusion concerning the defining attributes of HOIs has made their detection problematic. While the statistical tests being used in the ecological experiments to detect HOIs are described in detail in most papers, the dynamic models underlying these tests are often not made explicit. Additionally, we demonstrate the equivalency of three different statistical tests: the Case and Bender (1981) test, analysis of variance, and a multiplicative test (Wootton 1994). However, the choice of a response variable (i.e., population densities, population growth rates, per-capita growth rates, etc.) and different data transformations applied to these response variables alter the underlying dynamics model that is being tested. The result is that the statistical test applied does not always perform the intended comparison but instead tests a different and sometimes unjustified or even inappropriate dynamic model. Finally, we review the relationship between indirect effects and HOIs. Whereas some researchers have lumped HOIs and indirect effects, we argue that the two represent completely unique and separate phenomena. Additionally, indirect effects can complicate detection of HOIs, and we review several methods by which to separate the two processes.

---

Smith, M., Vaughan Sarrazin, M., Wang, X., Nordby, P., Yu, M., DeLonay, A. J., & Jaffery, J. (2022). Risk from delayed or missed care and non‐COVID‐19 outcomes for older patients with chronic conditions during the pandemic. Journal of the American Geriatrics Society. (Google Scholar)

Abstract:

Background: During the COVID-19 pandemic, patients with chronic illnesses avoided regular medical care, raising concerns about long-term complications. Our objective was to identify a population of older patients with chronic conditions who may be at risk from delayed or missed care (DMC) and follow their non-COVID outcomes during the pandemic.
Methods: We used a retrospective matched cohort design using Medicare claims and electronic health records at a large health system with community and academic clinics. Participants included 14,406 patients over 65 years old with two or more chronic conditions who had 1 year of baseline data and up to 9 months of postpandemic follow-up from March 1, 2019 to December 31, 2020; and 14,406 matched comparison patients from 1 year prior. Risk from DMC was defined by 13 indicators, including chronic conditions, frailty, disability affecting the use of telehealth, recent unplanned acute care, prior missed outpatient care, and social determinants of health. Outcomes included mortality, inpatient events, Medicare payments, and primary care and specialty care visits (in-person and telehealth).

Results: A total of 25% of patients had four or more indicators for risk from DMC. Per 1000 patients annually, those with four or more indicators had increased mortality of 19 patients (95% confidence interval, 4 to 32) and decreased utilization, including unplanned events (
496 events,
611 to
381) and primary care visits (
1578 visits,
1793 to
1401).
Conclusions: Older patients who had four or more indicators for risk from DMC had higher mortality and steep declines in inpatient and outpatient utilization during the pandemic.

---

Rai, B., & Meshram, A. (2020). Application of neural network to detect freezing of gait in patients with Parkinson’s disease. In Mangey Ram and Suraj B. Singh  (eds.) Soft Computing, De Gruyter Series on the Applications of Mathematics in Engineering and Information Sciences. Chapter 1, pp. 1-12.

Abstract:

Freezing of gait (FOG) consistently reoccurs in the later phases of a patient suffering from Parkinson’s disease (PD). Although it is treated with pharmacological treatment, the impact of the medication fades with increasing duration of the disease and thus diminishing the mobility of a patient. This chapter aims at developing a neural network–based classification model that helps to detect FOG episodes in a patient at early stages so that lethal mishaps can be avoided. In this application example, we build user-independent FOG recognition system that would work along in conjunction with nonpharmacological medications. The structured system of developing a neural network–based classification model can be organized into three different stages. The process starts with extraction of suitable features from the dataset. In the subsequent stage, patients are additionally grouped into two clusters depending on the FOG episodes. In the final stage, two neural network models are developed using feedforward network on the two clusters that were formed. The accuracy of the model is computed using sensitivity and specificity.

---