Wharton Faculty Research
Wharton's faculty members generate the intellectual innovations that fuel business growth around the world. Actively engaged with the leading global companies, governments, and non-profit organizations, they represent the world's most comprehensive source of business knowledge.
For more information, see the Research, Directory & Publications site.
Search results
Publication Medical Students in the Emergency Department and Patient Length of Stay(2015-12-08) Ionnides, Kimon; Mamtani, Mira; Shofer, Frances S; Small, Dylan S; Hennessey, Sean; Abella, Benjamin; Scott, KevinQuantitative assessments of how trainees affect patient care have been limited, especially in the emergency department (ED). A US study by Pitts et al found that supervised resident visits were associated with greater resource use, including longer length of stay (LOS) in the ED. As EDs host more core clerkship courses, less experienced students have become involved in bedside care. This study examined the association between the presence of medical students in the ED and patient LOS, an established patient-centered outcome and marker of ED performance.Publication Constructed Second Control Groups and Attenuation of Unmeasured Biases(2016-10-01) Pimentel, Samuel D; Small, Dylan S; Rosenbaum, Paul RThe informal folklore of observational studies claims that if an irrelevant observed covariate is left uncontrolled, say unmatched, then it will influence treatment assignment in haphazard ways, thereby diminishing the biases from unmeasured covariates. We prove a result along these lines: it is true, in a certain sense, to a limited degree, under certain conditions. Alas, the conditions are neither inconsequential nor easy to check in empirical work; indeed, they are often dubious, more often implausible. We suggest the result is most useful in the computerized construction of a second control group, where the investigator can see more in available data without necessarily believing the required conditions. One of the two control groups controls for the possibly irrelevant observed covariate, the other control group either leaves it uncontrolled or forces separation; therefore, the investigator views one situation from two angles under different assumptions. A pair of sensitivity analyses for the two control groups is coordinated by a weighted Holm or recycling procedure built around the possibility of slight attenuation of bias in one control group. Issues are illustrated using an observational study of the possible effects of cigarette smoking as a cause of increased homocysteine levels, a risk factor for cardiovascular disease. Supplementary materials for this article are available online.Publication Bayesian Hierarchical Regression on Clearance Rates in the Presence of "Lag" and "Tail" Phases with an Application to Malaria Parasites(2015-09-01) Fogarty, Colin B; Fay, Michael P; Flegg, Jennifer A; Stepniewska, Kasia; Fairhurst, Rick M; Small, Dylan SWe present a principled technique for estimating the effect of covariates on malaria parasite clearance rates in the presence of “lag” and “tail” phases through the use of a Bayesian hierarchical linear model. The hierarchical approach enables us to appropriately incorporate the uncertainty in both estimating clearance rates in patients and assessing the potential impact of covariates on these rates into the posterior intervals generated for the parameters associated with each covariate. Furthermore, it permits us to incorporate information about individuals for whom there exists only one observation time before censoring, which alleviates a systematic bias affecting inference when these individuals are excluded. We use a changepoint model to account for both lag and tail phases, and hence base our estimation of the parasite clearance rate only on observations within the decay phase. The Bayesian approach allows us to treat the delineation between lag, decay, and tail phases within an individual's clearance profile as themselves being random variables, thus taking into account the additional uncertainty of boundaries between phases. We compare our method to existing methodology used in the antimalarial research community through a simulation study and show that it possesses desirable frequentist properties for conducting inference. We use our methodology to measure the impact of several covariates on Plasmodium falciparum clearance rate data collected in 2009 and 2010. Though our method was developed with this application in mind, it can be easily applied to any biological system exhibiting these hindrances to estimation.Publication Patterns of Adherence to Oral Hypoglycemic Agents and Glucose Control among Primary Care Patients with Type 2 Diabetes(2016-01-01) de Vries McClintock, Heather F; Morales, Knashawn H; Small, Dylan S; Bogner, Hillary RResearchers sought to examine whether there are patterns of oral hypoglycemic-agent adherence among primary-care patients with type 2 diabetes that are related to patient characteristics and clinical outcomes. Longitudinal analysis via growth curve mixture modeling was carried out to classify 180 patients who participated in an adherence intervention according to patterns of adherence to oral hypoglycemic agents across 12 weeks. Three patterns of change in adherence were identified: adherent, increasing adherence, and nonadherent. Global cognition and intervention condition were associated with pattern of change in adherence (p < .05). Patients with an increasing adherence pattern were more likely to have an Hemoglobin A1c) < 7%; adjusted odds ratio = 14.52, 95% CI (2.54, 82.99) at 12 weeks, in comparison with patients with the nonadherent pattern. Identification of patients with type 2 diabetes at risk of nonadherence is important for clinical prognosis and the development and delivery of interventions.Publication Strong Control of the Familywise Error Rate in Observational Studies that Discover Effect Modification by Exploratory Methods(2015-12-01) Hsu, Jesse Y; Zubizarreta, José R; Small, Dylan S; Rosenbaum, Paul RAn effect modifier is a pretreatment covariate that affects the magnitude of the treatment effect or its stability. When there is effect modification, an overall test that ignores an effect modifier may be more sensitive to unmeasured bias than a test that combines results from subgroups defined by the effect modifier. If there is effect modification, one would like to identify specific subgroups for which there is evidence of effect that is insensitive to small or moderate biases. In this paper, we propose an exploratory method for discovering effect modification, and combine it with a confirmatory method of simultaneous inference that strongly controls the familywise error rate in a sensitivity analysis, despite the fact that the groups being compared are defined empirically. A new form of matching, strength-k matching, permits a search through more than k covariates for effect modifiers, in such a way that no pairs are lost, provided that at most k covariates are selected to group the pairs. In a strength-k match, each set of k covariates is exactly balanced, although a set of more than k covariates may exhibit imbalance. We apply the proposed method to study the effects of the earthquake that struck Chile in 2010.Publication Surrogate Markers for Time-Varying Treatments and Outcomes(2015-08-01) Hsu, Jesse Y; Kennedy, Edward H; Roy, Jason A; Stephens-Shields, Alisa J; Small, Dylan S; Joffe, Marshall MBACKGROUND: A surrogate marker is a variable commonly used in clinical trials to guide treatment decisions when the outcome of ultimate interest is not available. A good surrogate marker is one where the treatment effect on the surrogate is a strong predictor of the effect of treatment on the outcome. We review the situation when there is one treatment delivered at baseline, one surrogate measured at one later time point, and one ultimate outcome of interest and discuss new issues arising when variables are time-varying. METHODS: Most of the literature on surrogate markers has only considered simple settings with one treatment, one surrogate, and one outcome of interest at a fixed time point. However, more complicated time-varying settings are common in practice. In this article, we describe the unique challenges in two settings, time-varying treatments and time-varying surrogates, while relating the ideas back to the causal-effects and causal-association paradigms. CONCLUSION: In addition to discussing and extending popular notions of surrogacy to time-varying settings, we give examples illustrating that one can be misled by not taking into account time-varying information about the surrogate or treatment. We hope this article has provided some motivation for future work on estimation and inference in such settings.Publication Mapping the Spatial Distribution of a Disease-Transmitting Insect in the Presence of Surveillance Error and Missing Data(2014-09-11) Hong, Andrew E; Barbu, Corentin M; Small, Dylan S; Levy, Michael ZMaps of the distribution of epidemiological data often ignore surveillance error or possible correlations between missing information and outcomes. We analyse presence–absence data at the household level (12050 points) of a disease‐carrying insect in Mariano Melgar, Peru, collected as part of the Arequipan Ministry of Health's efforts to control Chagas disease. We construct a Bayesian hierarchical model to locate regions that are vulnerable to under‐reporting due to surveillance error, accounting for variability in participation due to infestation status. The spatial correlation in the data allows us to identify relative inspector sensitivity and to elucidate the relationship between participation and infestation. We show that naive estimates of prevalence would be biased by surveillance error and missingness at random assumptions. We validate our results through simulations and observe how randomized inspector assignments may improve prevalence estimates. Our results suggests that bias due to imperfect observations and missingness at random can be assessed and corrected in prevalence estimates of spatially auto-correlated binary variables.Publication Bias in Estimating the Causal Hazard Ratio When Using Two-Stage Instrumental Variable Methods(2015-03-20) Wan, Fei; Small, Dylan S; Bekelman, Justin E; Mitra, NanditaTwo-stage instrumental variable methods are commonly used to estimate the causal effects of treatments on survival in the presence of measured and unmeasured confounding. Two-stage residual inclusion (2SRI) has been the method of choice over two-stage predictor substitution (2SPS) in clinical studies. We directly compare the bias in the causal hazard ratio estimated by these two methods. Under a principal stratification framework, we derive a closed-form solution for asymptotic bias of the causal hazard ratio among compliers for both the 2SPS and 2SRI methods when survival time follows the Weibull distribution with random censoring. When there is no unmeasured confounding and no always takers, our analytic results show that 2SRI is generally asymptotically unbiased, but 2SPS is not. However, when there is substantial unmeasured confounding, 2SPS performs better than 2SRI with respect to bias under certain scenarios. We use extensive simulation studies to confirm the analytic results from our closed-form solutions. We apply these two methods to prostate cancer treatment data from Surveillance, Epidemiology and End Results-Medicare and compare these 2SRI and 2SPS estimates with results from two published randomized trials.Publication Neighborhood Social Environment and Patterns of Adherence to Oral Hypoglycemic Agents among Patients with Type 2 Diabetes Mellitus(2015-04-01) de Vries McClintock, Heather F; Wiebe, Douglas J; OʼDonnell, Alison J; Morales, Knashawn H; Small, Dylan S; Bogner, Hillary RThis study examined whether neighborhood social environment was related to patterns of adherence to oral hypoglycemic agents among primary care patients with type 2 diabetes mellitus. Residents in neighborhoods with high social affluence, high residential stability, and high neighborhood advantage, compared to residents in neighborhoods with one or no high features present, were significantly more likely to have an adherent pattern compared to a nonadherent pattern. Neighborhood social environment may influence patterns of adherence. Reliance on a multilevel contextual framework, extending beyond the individual, to promote diabetic self-management activities may be essential for notable public health improvements.Publication Hospital-Based Acute Care Use in Survivors of Septic Shock(2015-04-01) Ortego, Alexandra; Gaieski, David F; Fuchs, Barry D; Jones, Tiffanie; Halpern, Scott D; Small, Dylan S; Sante, S. Cham; Drumheller, Byron; Christie, Jason D; Mikkelsen, Mark EOBJECTIVES: Septic shock is associated with increased long-term morbidity and mortality. However, little is known about the use of hospital-based acute care in survivors after hospital discharge. The objectives of the study were to examine the frequency, timing, causes, and risk factors associated with emergency department visits and hospital readmissions within 30 days of discharge. DESIGN: Retrospective cohort study. SETTING: Tertiary, academic hospital in the United States. PATIENTS: Patients admitted with septic shock (serum lactate ≥ 4 mmol/L or refractory hypotension) and discharged alive to a nonhospice setting between 2007 and 2010. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: The coprimary outcomes were all-cause hospital readmission and emergency department visits (treat-and-release encounters) within 30 days to any of the three health system hospitals. Of 269 at-risk survivors, 63 (23.4%; 95% CI, 18.2-28.5) were readmitted within 30 days of discharge and another 12 (4.5%; 95% CI, 2.3-7.7) returned to the emergency department for a treat-and-release visit. Readmissions occurred within 15 days of discharge in 75% of cases and were more likely in oncology patients (p=0.001) and patients with a longer hospital length of stay (p=0.04). Readmissions were frequently due to another life-threatening condition and resulted in death or discharge to hospice in 16% of cases. The reasons for readmission were deemed potentially related to the index septic shock hospitalization in 78% (49 of 63) of cases. The most common cause was infection related, accounting for 46% of all 30-day readmissions, followed by cardiovascular or thromboembolic events (18%). CONCLUSIONS: The use of hospital-based acute care appeared to be common in septic shock survivors. Encounters often led to readmission within 15 days of discharge, were frequently due to another acute condition, and appeared to result in substantial morbidity and mortality. Given the potential public health implications of these findings, validation studies are needed.