Time series regression studies are widely used in environmental epidemiology to investigate short-term associations between environmental exposures, such as air pollution, weather variables, and pollen, and health outcomes like mortality, myocardial infarction, or hospital admissions. These studies typically use data collected at regular intervals (e.g., daily pollution levels and daily mortality counts) to explore short-term relationships. The article outlines the general features of time series data, the analysis process, and key issues in time series regression, including modeling short-term fluctuations in the presence of seasonal and long-term patterns, dealing with time-varying confounding factors, and modeling delayed associations between exposure and outcome. It also covers model checking, sensitivity analysis, and common extensions to the basic model. The article introduces the methodological features and analytical issues involved in time series regression studies, emphasizing the importance of controlling for long-term and seasonal patterns, as well as potential confounding factors. It discusses various methods for controlling these patterns, including time-stratified models, periodic functions (Fourier terms), and flexible spline functions. The article also addresses the issue of delayed (lagged) associations between exposure and outcome, and the potential for confounding by other time-varying factors. It highlights the importance of model checking and sensitivity analysis to ensure the validity of results. The article provides an example using a dataset from London, where daily ozone levels and mortality data are analyzed. It discusses the challenges of analyzing time series data, including overdispersion, autocorrelation, and the need for appropriate statistical methods. The article also touches on the importance of considering non-linear associations and effect modifiers, as well as the analysis of data from multiple locations. Finally, it summarizes the key steps and complexities involved in conducting a basic time series regression analysis, emphasizing the importance of understanding the unique features of time series data and the need for careful modeling and interpretation.Time series regression studies are widely used in environmental epidemiology to investigate short-term associations between environmental exposures, such as air pollution, weather variables, and pollen, and health outcomes like mortality, myocardial infarction, or hospital admissions. These studies typically use data collected at regular intervals (e.g., daily pollution levels and daily mortality counts) to explore short-term relationships. The article outlines the general features of time series data, the analysis process, and key issues in time series regression, including modeling short-term fluctuations in the presence of seasonal and long-term patterns, dealing with time-varying confounding factors, and modeling delayed associations between exposure and outcome. It also covers model checking, sensitivity analysis, and common extensions to the basic model. The article introduces the methodological features and analytical issues involved in time series regression studies, emphasizing the importance of controlling for long-term and seasonal patterns, as well as potential confounding factors. It discusses various methods for controlling these patterns, including time-stratified models, periodic functions (Fourier terms), and flexible spline functions. The article also addresses the issue of delayed (lagged) associations between exposure and outcome, and the potential for confounding by other time-varying factors. It highlights the importance of model checking and sensitivity analysis to ensure the validity of results. The article provides an example using a dataset from London, where daily ozone levels and mortality data are analyzed. It discusses the challenges of analyzing time series data, including overdispersion, autocorrelation, and the need for appropriate statistical methods. The article also touches on the importance of considering non-linear associations and effect modifiers, as well as the analysis of data from multiple locations. Finally, it summarizes the key steps and complexities involved in conducting a basic time series regression analysis, emphasizing the importance of understanding the unique features of time series data and the need for careful modeling and interpretation.