Dynamic Financial Constraints: Distinguishing Mechanism Design from Exogenously Incomplete Regimes∗ **under major revisions**

We formulate and solve a range of dynamic models of constrained credit/insurance that allow for moral hazard, limited commitment and unobservable investment. We compare them to full insurance and exogenously incomplete financial regimes (autarky, saving only, and borrowing and lending in a risk-free asset). We develop computational methods based on mechanism design, linear programming, and maximum likelihood to estimate, compare, and statistically test these alternative dynamic models of financial constraints. Our methods work with both cross-sectional and panel data and allow for measurement error and unobserved heterogeneity. We estimate the models using data on Thai households running small businesses. We find that, overall, the borrowing and saving only regimes provide the best fit using joint data on consumption, investment, and income. However, there is evidence that family networks are helpful in consumption smoothing as in a moral hazard constrained regime. The full insurance, autarky and limited commitment regimes are rejected in virtually all estimation runs.