The increasing demand for ecologists to describe and understand the unprecedented global changes transpiring in our study systems has highlighted the limits of our current experimental and analytical approaches. Often the scale at which these events are occurring are beyond the scope of field and lab experiments, and it is difficult to parse the relative importance of one driver over another using widely applied statistical approaches. With rapidly advancing remotely sensed data and increasingly available long-term ecological data, new opportunities are emerging for ecologist to measure local and landscape-scale drivers of global change. Harnessing these data and developing rigorous analyses that enable a greater causal understanding of ecological change, however, remains and outstanding challenge. In this session, we will highlight cutting-edge approaches that leverage observational, timeseries data to infer casual links between outcomes and drivers of global change. Specifically, we will present six studies spanning multiple systems, including forests, grasslands, wildfire, and infectious disease; these studies also span a variety of spatial scales—from field experiments to global observational studies. Each presentation will highlight specific methods that can help overcome bias, which often precludes causal inference in ecological analysis. These methods include difference-in-difference, within-estimator panel data models, instrumental variables, and propensity score matching. Ultimately, we aim to provide accessible examples of causal inference approaches from other disciplines, like economics and public health, that can be applied to a diversity of ecological systems and hypothesis testing. These approaches greatly enhance our abilities as ecologists to harness the data revolution.