A new approach to modeling temperature-related mortality: Non-linear autoregressive models with exogenous input

    loading  Checking for direct PDF access through Ovid


Temperature-mortality relationships are nonlinear, time-lagged, and can vary depending on the time of year and geographic location, all of which limits the applicability of simple regression models in describing these associations. This research demonstrates the utility of an alternative method for modeling such complex relationships that has gained recent traction in other environmental fields: nonlinear autoregressive models with exogenous input (NARX models). All-cause mortality data and multiple temperature-based data sets were gathered from 41 different US cities, for the period 1975–2010, and subjected to ensemble NARX modeling. Models generally performed better in larger cities and during the winter season. Across the US, median absolute percentage errors were 10% (ranging from 4% to 15% in various cities), the average improvement in the r-squared over that of a simple persistence model was 17% (6–24%), and the hit rate for modeling spike days in mortality (>80th percentile) was 54% (34–71%). Mortality responded acutely to hot summer days, peaking at 0–2 days of lag before dropping precipitously, and there was an extended mortality response to cold winter days, peaking at 2–4 days of lag and dropping slowly and continuing for multiple weeks. Spring and autumn showed both of the aforementioned temperature-mortality relationships, but generally to a lesser magnitude than what was seen in summer or winter. When compared to distributed lag nonlinear models, NARX model output was nearly identical. These results highlight the applicability of NARX models for use in modeling complex and time-dependent relationships for various applications in epidemiology and environmental sciences.HighlightsNARX models are established in other environmental research, but are unused in temperature-related mortality research.NARX models do not assume any particular shape to the temperature-mortality association.NARX models are cross-validated and are easily modified to take on real-time, multi-step-ahead predictions and hindcasts.Year-round, daily mortality in 41 different US cities was modeled using an ensemble of NARX models in each location.Models show skill everywhere. Results vary spatially and seasonally, improving upon a persistence model by 17% points.When compared with distributed lag non-linear models, the output time series are largely similar

    loading  Loading Related Articles