Premium
How Fat‐Tailed is US Output Growth?
Author(s) -
Franke Reiner
Publication year - 2015
Publication title -
metroeconomica
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.256
H-Index - 29
eISSN - 1467-999X
pISSN - 0026-1386
DOI - 10.1111/meca.12067
Subject(s) - economics , volatility (finance) , econometrics , distribution (mathematics) , monetary economics , mathematics , mathematical analysis
Abstract Several studies have recently rejected the common hypothesis that aggregate output is normally distributed. The present paper reconsiders this issue for US output growth. To this end, it focusses on the shape parameter b of the exponential power distribution ( EPD ), the two polar values of which constitute the normal distribution and the L aplace distribution with its fatter tails, respectively. The paper first warns against premature conclusions that neglect a structural break in output volatility. On the basis of a battery of M onte C arlo experiments, it is then found out that the results strongly depend on which subperiod is considered, the G reat I nflation ( GI ) or the G reat M oderation ( GM ) period, and which data are referred to, the growth rates of GDP , firm sector output, and quarterly or monthly industrial production ( IP ). Here, only quarterly IP can be said to exhibit fat tails in GI as well as GM ; other evidence is mixed.