BIAS project偏差项目.pptVIP

BIAS: Biases in observational studies Promote principled methods for accounting for potential biases in observational data: “non-response” bias: selection bias (participation in a study) missing data (on some variables for one individual) confounding (important variables not available) ecological bias (from aggregate / area-level data) measurement error Na?ve methods not normally appropriate. Alleviating biases Suitable statistical models for the processes underlying the data Express uncertainty about biases as probability distributions. Uncertainty carries through to the results Bayesian graphical models Software, e.g. WinBUGS Using multiple data sources to inform about the potential biases Application areas Small area estimation (with Virgilio Gómez Rubio) Using combination of aggregate (e.g. census) and individual survey data Selection bias in case-control and survey studies (with Sara Geneletti) Using directed acyclic graphs Inference from combining datasets of different designs from different sources (with Chris Jackson, Jassy Molitor) Using Bayesian hierarchical / graphical models Example: low birth weight and air pollution Does exposure to air pollution during pregnancy increase the risk of low birth weight? Example illustrates various biases. Combine datasets with different strengths: Survey data (Millennium Cohort Study) Small, great individual detail. Administrative data (national births register) Large, but little individual detail. Single underlying model assumed to govern both datasets: elaborate as appropriate to handle biases Low birth weight Important determinant of future health ? population health indicator. Established risk factors: Tobacco smoking during pregnancy. Ethnicity (South Asian, issue for UK data) Maternal age, weight, height, number of previous births. Role of environmental risk factors, such as air pollution, less clear. Various studies around the world suggest a link. Exposure to urban air pollution correlated with socioecono