eduzhai > Applied Sciences > Computer Science >

Testing Forecast Rationality for Measures of Central Tendency

  • KanKan
  • (0) Download
  • 20210425
  • Save

... pages left unread,continue reading

Document pages: 65 pages

Abstract: Rational respondents to economic surveys may report as a point forecast anymeasure of the central tendency of their (possibly latent) predictivedistribution, for example the mean, median, mode, or any convex combinationthereof. We propose tests of forecast rationality when the measure of centraltendency used by the respondent is unknown. We overcome an identificationproblem that arises when the measures of central tendency are equal or in alocal neighborhood of each other, as is the case for (exactly or nearly)symmetric distributions. As a building block, we also present novel tests forthe rationality of mode forecasts. We apply our tests to survey forecasts ofindividual income, Greenbook forecasts of U.S. GDP, and random walk forecastsfor exchange rates. We find that the Greenbook and random walk forecasts arebest rationalized as mean, or near-mean forecasts, while the income surveyforecasts are best rationalized as mode forecasts.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...