Abstract Downscaling is a term that has been used to describe the range of methods that are used to infer regional‐scale or local‐scale climate information from coarsely resolved climate models. The use of statistical methods for this purpose is rooted in both operational weather forecasting and synoptic climatology and has become a widely applied method for development of regional climate change scenarios. This article provides an overview of statistical downscaling with a focus on assumptions, common predictors and predictands, and methodological approaches ranging from interpolation and scaling to regression‐based methods, weather pattern‐based techniques, and stochastic weather generators. Suggestions are made for improved assessment of the fundamental downscaling assumptions as well as reduction of uncertainty associated with application of downscaled climate information across models and greenhouse gas emission scenarios.