Great Lakes water levels have fluctuated over thousands of years. High water levels were a problem in the 1980s, but a recent sudden drop in Lakes Michigan and Huron has caused particular concern, in part because lower water levels are consistent with many global climate change scenarios. We examined water level data (1860-2006) representing Lakes Michigan and Huron to evaluate changes in both long-term and seasonal patterns over time, and explore relationships with candidate predictor variables. Our tools for this analysis included both Seasonal Trend decomposition using Loess (STL), and dynamic linear models (DLM). In addition to the recent decline, STL results reveal a sustained decline around 1900, a long-term periodicity of ∼30 years, and an unexpected correspondence with sunspot activity. DLM results indicate a relationship with precipitation over a three-year lagged period, which has been essentially unchanging from 1900 to present. Additionally, the DLM highlights an underlying lake level decline beginning in ∼1973 and continuing to the present, which may have been obscured by concurrently increasing precipitation into the 1990s. The current underlying decline might be related to a simultaneous evaporation increase, however, our model could not confirm this relationship, possibly due to the shorter period of record for evaporation data. We cannot be certain that the present observed water level drop is caused by factors related to global climate change, or that it portends a long-term problem. However, because the underlying decline has been ongoing for ∼33 years it may be prudent to include lower lake levels in future management planning.