Risks for the long run: Estimation with time aggregation

The discrepancy between the decision and data-sampling intervals, known as time aggregation, confounds the identification of long-, short-run growth, and volatility risks in asset prices. This paper develops a method to simultaneously estimate the model parameters and the decision interval of the agent by exploiting identifying restrictions of the Long Run Risk (LRR) model that account for time aggregation. The LRR model finds considerable empirical support in the data; the estimated decision interval of the agents is 33 days. Our estimation results establish that long-run growth and volatility risks are important for asset prices.