出版社：Fundação Getulio Vargas, Escola de Pós-Graduação em Economia
摘要：In this paper, we propose a novel approach to econometric forecast-
ing of stationary and ergodic time series within a panel-data frame-
work. Our key element is to employ the (feasible) bias-corrected aver-
age forecast. Using panel-data sequential asymptotics we show that it
is potentially superior to other techniques in several contexts. In partic-
ular, it is asymptotically equivalent to the conditional expectation, i.e.,
has an optimal limiting mean-squared error. We also develop a zero-
mean test for the average bias and discuss the forecast-combination
puzzle in small and large samples. Monte-Carlo simulations are con-
ducted to evaluate the performance of the feasible bias-corrected aver-
age forecast in .nite samples. An empirical exercise, based upon data
from a well known survey is also presented. Overall, these results show
promise for the feasible bias-corrected average forecast.
