Abstract Rational respondents to economic surveys may report as a point forecast any measure of the central tendency of their predictive distribution, e.g. the mean, median, or mode. We propose tests of forecast rationality when the measure used by the respondent is unknown. We overcome an identification problem that arises when the centrality measures are in a local neighborhood of each other, as is the case for approximately symmetric distributions. We apply our tests to income forecasts from the FRBNY's Survey of Consumer Expectations. We find these forecasts are rationalizable as mode forecasts, but not as mean or median forecasts.