We use spline interpolation to approximate the subjective cumulative distribution function of an economic agent over the future realization of a continuous (possibly censored) random variable. The method proposed exploits information collected using a small number of probability questions on expectations and requires a weak prior knowledge of the shape of the underlying distribution. We find that eliciting 4 or 5 points on the cumulative distribution function of an agent is sufficient to accurately approximate a wide variety of underlying distributions. We show that estimated moments of general functions of the random variable can be computed analytically and/or using standard simulation techniques. We illustrate the usefulness of the method by estimating a simple model to asses the impact of expectations on investment decisions in a commonly used trust game.