Time-series data are a key input to a range of studies and applications work across the electric power industry. For example, studies evaluating impacts of increasing solar generation on operating reserves may require corresponding time series of hourly actuals and day-ahead forecasts of both load and solar generation. However, such data may not be available at all or in the quantity and quality required for a given study. One solution is to synthesize the missing time-series data, where the goal is not a one-to-one reproduction of the “real” data but instead the generation of a “synthetic” data set that is realistic in a statistical sense. This report presents a framework for generating and validating synthetic time-series data. The framework is demonstrated through a case study on day-ahead forecast data, with both quantitative and qualitative comparisons between the synthetic and real data.