The study of temporal environmental change is motivated by the need to know if the state of the environment has deteriorated or, in some cases, if it has improved as a result of the removal or lessening of stress on the system. The data available for study of temporal change are observational and this presents challenges to the analysis as the cause of a detected change is also of interest. Through a series of examples, this article reviews modeling techniques that partition variability into components constructed to adequately describe the structure of the data. Temporal change is important in many areas and examples are taken from studies of water quality, floods, air quality, stratospheric ozone, global surface temperature, and species abundance, landscape patterns, and point patterns in ecology. Model features include deterministic and stochastic trends, seasonality, covariates as fixed and random components, evolutionary terms, short‐, and long‐term memory processes.