A Bayesian semiparametric approach with change points for spatial ordinal data

A spatially varying change points model for monitoring glaucoma progression using visual field data

Glaucoma disease progression, as measured by visual field (VF) data, is often defined by periods of relative stability followed by an abrupt decrease in visual ability at some point in time. Determining the transition point of the disease trajectory to a more severe state is important clinically for disease management and for avoiding irreversible vision loss. Based on this, we present a unified statistical modeling framework that permits prediction of the timing and spatial location of future vision loss and informs clinical decisions regarding disease progression. The developed method incorporates anatomical information to create a biologically plausible data-generating model. We accomplish this by introducing a spatially varying coefficients model that includes spatially varying change points to detect structural shifts in both the mean and variance process of VF data across both space and time. The VF location-specific change point represents the underlying, and potentially censored, timing of true change in disease trajectory while a multivariate spatial boundary detection structure is introduced that accounts for the complex spatial connectivity of the VF and optic disc. We show that our method improves estimation and prediction of multiple aspects of disease management in comparison to existing methods through simulation and real data application. The R package spCP implements the new methodology.

Spatial Variability in the Persistence of Pneumococcal Conjugate Vaccine-targeted Pneumococcal Serotypes Among Adults

Invasive pneumococcal disease is a leading cause of morbidity worldwide. Pneumococcal conjugate vaccine effectively reduces the number of cases caused by vaccine-targeted serotypes among children who receive the vaccine and adults who are not directly vaccinated. Recently, there has been a debate as to whether adults should receive the same conjugate vaccine as children. In settings where vaccine uptake in children is high, the vaccine serotypes cause a small fraction of disease cases, and direct vaccination might have a small effect. However, direct vaccination might be warranted if geographic regions or subpopulations exist where the targeted serotypes persist at higher levels than expected. To detect such geographic variability, new methodology is required. We introduce an innovative, spatially varying change points model, combined with spatially varying intercepts and slopes, to jointly determine whether the beginning date of the vaccine-associated decline, the initial baseline proportion of invasive pneumococcal disease cases caused by vaccine-targeted serotypes, and/or the rate of decline of vaccine-targeted serotypes vary in the adult population across Connecticut, 1998-2009. Results indicate that there is substantial spatial variability in the pattern with which vaccine-targeted serotypes decline, suggesting that the fraction of invasive pneumococcal disease cases that could have been preventable by direct vaccination of adults in Connecticut during the study period differed over time and space. The newly developed model is shown to outperform a number of competitors in terms of explanatory and predictive ability.

Timing and effect of a safe routes to school program on child pedestrian injury risk during school travel hours: Bayesian changepoint and difference-in-differences analysis

BACKGROUND

In 2005, the US Congress allocated $612 million for a national Safe Routes to School (SRTS) program to encourage walking and bicycling to schools. We evaluated the effectiveness of a SRTS in controlling pedestrian injuries among school-age children.

METHODS

Bayesian changepoint analysis was applied to model the quarterly counts of pedestrian injuries among 5- to 19-year old children in New York City between 2001 and 2010 during school-travel hours in census tracts with and without SRTS. Overdispersed Poisson model was used to estimate difference-in-differences in injury risk between census tracts with and without SRTS following the changepoint.

RESULTS

In SRTS-intervention census tracts, a change point in the quarterly counts of injuries was identified in the second quarter of 2008, which was consistent with the timing of the implementation of SRTS interventions. In census tracts with SRTS interventions, the estimated quarterly rates of pedestrian injury per 10,000 population among school-age children during school-travel hours were 3.47 (95% Credible Interval [CrI] 2.67, 4.39) prior to the changepoint, and 0.74 (95% CrI 0.30, 1.50) after the changepoint. There was no change in the average number of quarterly injuries in non-SRTS census tracts. Overdispersed Poisson modeling revealed that SRTS implementation was associated with a 44% reduction (95% Confidence Interval [CI] 87% decrease to 130% increase) in school-age pedestrian injury risk during school-travel hours.

CONCLUSIONS

Bayesian changepoint analysis of quarterly counts of school-age pedestrian injuries successfully identified the timing of SRTS intervention in New York City. Implementation of the SRTS program in New York City appears to be effective in reducing school-age pedestrian injuries during school-travel hours.