Controlling for seasonal patterns and time varying confounders in time‐series epidemiological models: a simulation study

Abstract

An important topic when estimating the effect of air pollutants on human health is choosing the best method to control for seasonal patterns and time varying confounders, such as temperature and humidity. Semi-parametric Poisson time-series models include smooth functions of calendar time and weather effects to control for potential confounders. Case-crossover (CC) approaches are considered efficient alternatives that control seasonal confounding by design and allow inclusion of smooth functions of weather confounders through their equivalent Poisson representations. We evaluate both methodological designs with respect to seasonal control and compare spline-based approaches, using natural splines and penalized splines, and two time-stratified CC approaches. For the spline-based methods, we consider fixed degrees of freedom, minimization of the partial autocorrelation function, and general cross-validation as smoothing criteria. Issues of model misspecification with respect to weather confounding are investigated under simulation scenarios, which allow quantifying omitted, misspecified, and irrelevant-variable bias. The simulations are based on fully parametric mechanisms designed to replicate two datasets with different mortality and atmospheric patterns. Overall, minimum partial autocorrelation function approaches provide more stable results for high mortality counts and strong seasonal trends, whereas natural splines with fixed degrees of freedom perform better for low mortality counts and weak seasonal trends followed by the time-season-stratified CC model, which performs equally well in terms of bias but yields higher standard errors.

The effects of air pollution on asthma hospital admissions in Adelaide, South Australia, 2003–2013: time‐series and case–crossover analyses

“…Methodologically speaking, the estimated effects from time‐series analysis and CCO analysis were comparable when the seasonality and long‐term trends were adequately controlled for. Previous studies have also showed the equivalence of CCO analyses and time‐series analyses by utilizing health outcome data and simulated data .…”

A Systematic Review of the Time Series Studies Addressing the Endemic Risk of Acute Gastroenteritis According to Drinking Water Operation Conditions in Urban Areas of Developed Countries

“…In all the TSS included in the review, authors basically used Poisson regression most often adapted to over-dispersed counts (e.g., by using quasi-Poisson regression) to model daily counts of AGE cases and implemented the generalized additive model (GAM). When specified, the criterion for fitting the model was the absence of autocorrelation in residuals, which provides optimal risk estimates when health outcomes follow marked seasonal variations [ 44 , 45 ]. Control covariates were mostly similar: trends and seasonal patterns were modelled with a spline or Loess function of time, day of the week, and school vacation periods.…”

Short-Term Associations between Air Pollution Concentrations and Respiratory Health—Comparing Primary Health Care Visits, Hospital Admissions, and Emergency Department Visits in a Multi-Municipality Study

“…This design adjusts for seasonality, time trend, and time non-variant factors by design, if the control days are selected suitably [29]. We used calendar month non-overlapping strata, which helps to prevent overlap bias [30], and control days were matched to the day of the week.…”