Predicting extreme asthma events in London using quantile regression models


The burden of asthma is a major public health issue, and of a wider interest particularly to public health practitioners, health care providers and policy makers, as well as researchers. The literature on forecasting of adverse respiratory health events like asthma attacks is limited. It is an unclear field; and there is a need for more research on the forecasting of the demand for hospital respiratory services.


This paper describes a framework for creating a time series data set with daily asthma admissions, weather and air quality factors; and then generating suitable lags for predictive multivariate quantile regression models (QRMs). It also demonstrates the use of root mean square error (RMSE) and receiver operating characteristic (ROC) error measures in selecting suitable predictive models.

Primary Topic Areas: 
Original Publication Year: 
Event/Publication Date: 
December, 2010

June 25, 2019

Contact Us

NSSP Community of Practice



This website is supported by Cooperative Agreement # 6NU38OT000297-02-01 Strengthening Public Health Systems and Services through National Partnerships to Improve and Protect the Nation's Health between the Centers for Disease Control and Prevention (CDC) and the Council of State and Territorial Epidemiologists. Its contents are solely the responsibility of the authors and do not necessarily represent the official views of CDC. CDC is not responsible for Section 508 compliance (accessibility) on private websites.

Site created by Fusani Applications