Colombia, Costa Rica, Ecuador, Hungary, Indonesia, India, Jamaica, Jordan, Korea,
Malaysia, Mexico, Morocco, Nigeria, Pakistan, Panama, Peru, Philippines, Poland,
South Africa, Turkey, Uruguay and Venezuela.
Our cross sectional and time dimension is ideally suited to a panel approach.
We additionally have a reasonable span of data at least sixteen years, which is more
important according to Shiller and Perron (1985) than the frequency of the data, and
this of course is complemented by the cross sectional dimension of our panel data set.
This is also the approximate size of data set from Mendoza and Ostry (2007) using an
approach that does not consider the stationarity properties of the data.11
< Insert Table 1 here >
4.2 Industrial Countries Results
We first pre-test the industrial countries debt and primary surplus data for
nonstationarity using the Bai and Ng (2004) PANIC approach. As already mentioned,
PANIC uses a factor structure to take account of cross sectional correlation in panels
introduced by common shocks. The time series properties of the data are important in
a study of fiscal sustainability, as noted in Trehan and Walsh (1991) and Bohn (1998).
Table 1 suggests that both primary surplus and debt have nonstationary
components for industrial countries. In particular, industrial countries’ debt (bit) has a
nonstationary factor and idiosyncratic component. For the primary surplus (sit) there is
evidence of nonstationarity of the common factor, but not for the idiosyncratic
component. The former is indicative of pervasive nonstationarity and underscores the
attractiveness of the factor methodology. Given evidence of primary surplus and debt
nonstationarity we can estimate fiscal response functions à la Bohn (1998, 2007),
11 We separate our sample into industrial and emerging market economies following convention and
since the two groups did not share a common factor.
15
More intriguing information
1. Testing Hypotheses in an I(2) Model with Applications to the Persistent Long Swings in the Dmk/$ Rate2. RETAIL SALES: DO THEY MEAN REDUCED EXPENDITURES? GERMAN GROCERY EVIDENCE
3. Fiscal Insurance and Debt Management in OECD Economies
4. The Functions of Postpartum Depression
5. A Classical Probabilistic Computer Model of Consciousness
6. Markets for Influence
7. Public-private sector pay differentials in a devolved Scotland
8. The name is absent
9. Social Balance Theory
10. Chebyshev polynomial approximation to approximate partial differential equations