Richard Smith works in extreme value theory, spatial statistics and time series analysis, and the application of these techniques in different areas of applied research, particularly environmental statistics including climate change and the health effects of air pollution. In extreme value theory, he has worked on probability techniques such as rates of convergence and extreme values in dependent sequences, and also in statistical inference for extremes, starting with univariate extreme value problems and then moving into more modern techniques for multivariate and spatial extremes. He has worked on hierarchical Bayesian methods for climate change and for detection and attribution of the human influence on climate, including for climate extremes. In air pollution research, he has worked on the spatial and temporal properties of air pollution fields, particularly particulate matter and ozone, and on epidemiological questions about the influence of air pollution on human mortality. He is currently an investigator on an NIH project looking at the influence of air pollution on various indicators of dementia, including Alzheimer's disease.