Equilibrium information in credence goods

We study credence goods in a general model. A consumer may suffer a loss which is a continuous random variable. Privately observing the loss value, an expert can provide a repair at a price to eliminate the consumer's loss. All perfect-Bayesian equilibria are inefficient, in that some losses are not repaired. In closed form, we derive a pooling equilibrium (where losses are inferred to be in an interval), and a separating equilibrium (where losses are precisely inferred). If the expert can acquire an information structure on losses, the first best is achieved by a binary signal. Results are robust when cost and loss are random and correlated, and when there are multiple experts.