| Abstract: |
Tourism is a major source of service receipts for many countries, including
Taiwan. The two leading tourism countries for Taiwan, comprising a high
proportion of world tourist arrivals to Taiwan, are Japan and USA, which are
sources of short and long haul tourism, respectively. As it is well known that
a strong domestic currency can have adverse effects on international tourist
arrivals, daily data from 1 January 1990 to 31 December 2008 are used to model
the world price and US$ / New Taiwan $ and Yen/ New Taiwan $ exchange rates,
and tourist arrivals from the world, USA and Japan to Taiwan, as well as their
associated volatility. The sample period includes the Asian economic and
financial crises in 1997, and part of the global financial crisis of 2008-09.
Inclusion of the exchange rate allows approximate daily price effects on
world, US and Japanese tourist arrivals to Taiwan to be captured. The
Heterogeneous Autoregressive (HAR) model does not reproduce the theoretical
hyperbolic decay rates associated with fractionally integrated (or long
memory) time series models, but it can nevertheless approximate quite
accurately and parsimoniously the slowly decaying correlations associated with
such models. The HAR model is used to approximate long memory properties in
daily exchange rates and international tourist arrivals, to test whether
alternative short and long run estimates of conditional volatility are
sensitive to the approximate long memory in the conditional mean, to examine
asymmetry and leverage in volatility, and to examine the effects of temporal
and spatial aggregation. The empirical results show that the conditional
volatility estimates are not sensitive to the approximate long memory nature
of the conditional mean specifications. The QMLE for the GARCH(1,1), GJR(1,1)
and EGARCH(1,1) models for world, US and Japanese tourist arrivals to Taiwan,
and the world price and US$ / New Taiwan $ and Yen/ New Taiwan $ exchange
rates, are statistically adequate and have sensible interpretations. Asymmetry
(though not leverage) is found for several alternative HAR models for the
world, US and Japanese tourist arrivals to Taiwan. For policy purposes, these
empirical results suggest that an arbitrary choice of data frequency or
spatial aggregation will not lead to robust findings as they are generally not
independent of the level of aggregation used. |