Water quality and its future availability for sustaining both industry and aquatic ecosystems are seen as two of the most pressing environmental issues for the coming decades. Our ability to understand and model the often complex dynamics of these systems relies on sound statistical methods for defensible decision and policy making. Hydrological and water quality data can be challenging to work with and often require novel statistical methods or analyses in order to answer important questions. Some of these challenges arise as a result of spatio-temporal correlations in the data, missing data, censoring of observations that fall below detection limits and the influence of outliers. Examples of recent work in this area include: estimation of pollutant loads and discharge volumes, detection of water quality trends, design of stream sampling programmes and methods for reporting stream health.