This paper introduces a new non-parametric procedure -- the empirical projection method -- for solving structural models. The method is an alternative to value-function iteration or similar methods, but has the crucial advantage that it requires no distributional assumptions for the random variables in the model. The procedure is complementary to GMM -- GMM provides estimates of structural parameters, while the empirical projection method takes structural parameter estimates, and uses them to produce a time-series of predictions for individual observations. In this way, it shares the advantage of calibration in that it allows models to be evaluated in dimensions other than the ability to test overidentification. I apply this to evaluate the time-series predictive ability of several standard consumption-based asset pricing models, such as the standard CRRA model, the internal habit model of Ferson and Constanides, and the external habit model of Campbell and Cochrane. I choose several parameter estimates from the literature, and see how well they generate the time-series properties of asset prices, such as expected return, and the price-dividend ratio.