US Inflation Expectations and Heterogeneous Loss Functions, 1968–2010

Abstract

The recent literature has suggested that macroeconomic forecasters may have asymmetric loss functions, and that there may be heterogeneity across forecasters in the degree to which they weigh under and over-predictions. Using an individual-level analysis that exploits the SPF respondents' histogram forecasts, we …nd little evidence of asymmetric loss for the in ‡ation forecasters.Journal of Economic Literature classi…cation: C53, E31, E37

Do US Macroeconomic Forecasters Exaggerate their Differences?

“…14 If we let F ;h D ;h Cx ;h , then under some assumptions x ;h D h p V h .y /, where h is a constant which depends on the distribution function of the data and the loss function, and V h .y / is the conditional variance: see Patton and Timmermann (2007, Proposition 2). Clements (2010Clements ( , 2014b investigate whether asymmetric loss accounts for the inconsistencies reported in Table IV, but find little support for the contention.…”

“…If we let F τ , h = μ τ , h + x τ , h , then under some assumptions , where ϕ h is a constant which depends on the distribution function of the data and the loss function, and V τ − h ( y τ ) is the conditional variance: see Patton and Timmermann (, Proposition 2). Clements () investigate whether asymmetric loss accounts for the inconsistencies reported in Table , but find little support for the contention. Our interest here is whether (anti‐)herding explains the inconsistencies, and whether we can use the above testing approach (‘Testing procedure’) to test this hypothesis in the presence of asymmetric loss.…”

Asymmetric Loss and the Rationality of Inflation Forecasts: Evidence from South Korea

“…Clements (), in a recent study that uses the Survey of Professional Forecasters (SPF), tests for and finds little evidence of asymmetric loss for inflation forecasters. Ulu () indicates that the rationality of joint forecasts for inflation and output cannot be rejected under an asymmetric loss function.…”

Asymmetry of Individual and Aggregate Inflation Expectations: A Survey

“…The literature has debated several candidate distributions starting with the normal (Giordani and Söderlind, ), which imposes symmetry, the skew‐normal (García and Manzanares, ) and the generalized beta (see e.g. Engelberg, Manski and Williams, ; Clements, ). Secondly, one needs to estimate parameters of the chosen distribution on a relatively small number of observed bins.…”

“…In the lab, Pfajfar and Žakelj () find significant asymmetry in confidence intervals of expected inflation in different monetary policy environments but treatments that do not allow participants to specify asymmetric intervals perform better. Clements () studies SPF data and reports that allowing for asymmetry in individual distributions has no significant effect on forecast means and variances. In line with the latter paper and using survey data, Bruine de Bruin, Manski, Topa and van der Klaauw () find that the mean of individual distributions is an accurate statistic for expected inflation at the aggregate level.…”