28.02.2015 Views

Exchange Rate Economics: Theories and Evidence

Exchange Rate Economics: Theories and Evidence

Exchange Rate Economics: Theories and Evidence

SHOW MORE
SHOW LESS

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

Purchasing power parity <strong>and</strong> the PPP puzzle 49<br />

from Frenkel (1981) for the dollar–franc rate over the period June 1973–July 1979:<br />

s t = 1.521 + 0.184(p<br />

t − pt ∗ ),SER = 0.029,DW = 2.30. (2.20)<br />

(0.027) (0.37)<br />

This kind of result led Frenkel (1981) to refer to ‘the collapse of purchasing<br />

power parities during the 1970s’. Krugman (1978) also presents estimates of (2.17)<br />

<strong>and</strong> (2.18) for both the inter-war <strong>and</strong> recent floating periods <strong>and</strong> his results are<br />

unfavourable to PPP in both periods. He concludes,‘There is some evidence then<br />

that there is more to exchange rates than PPP. This evidence is that the deviations<br />

from PPP are large,fairly persistent <strong>and</strong> seen to be larger in countries with unstable<br />

monetary policy.’<br />

However,two early studies estimated (2.17) <strong>and</strong> (2.18) using panel methods,<br />

that is,pooled time series – cross-section estimators,<strong>and</strong> report results which are<br />

favourable to PPP even for the 1970s period. Panel estimates of PPP rely on the<br />

following framework:<br />

s it = α i + β ′ (p it − p ∗ it ) + { ∑<br />

i<br />

} { ∑<br />

γ i D i +<br />

t<br />

δ t D t<br />

}<br />

+ u it ,(2.21)<br />

where the i subscript indicates that the data has a cross-sectional dimension (running<br />

from 1 to N ), D i <strong>and</strong> D t denote,respectively,country-specific <strong>and</strong> time-specific<br />

fixed effect dummy variables (although not noted here it is straightforward to<br />

incorporate r<strong>and</strong>om effects into (2.21)). In a st<strong>and</strong>ard panel setting a number of<br />

modelling strategies are available for the disturbance term,ranging from a purely<br />

r<strong>and</strong>om term to autoregressive processes (with either common autoregressive terms<br />

across individual panel members or different autoregressive terms across members),<br />

or it may be spatially correlated,or some combination of these assumptions may<br />

be used.<br />

One clear advantage to using panel methods to estimate PPP has been noted<br />

by Frankel <strong>and</strong> Rose (1995). Their argument is as follows. Since PPP is unlikely to<br />

hold continuously,deviations from PPP – that is,the error term in equation (2.17) –<br />

will be correlated with relative prices,that is,Cov (φ, p− p ∗ ) ̸= 0. If this covariance<br />

is non-zero it will introduce a st<strong>and</strong>ard errors-in-variable bias producing<br />

biased <strong>and</strong> inconsistent estimates of the αs. However,this bias will vanish in circumstances<br />

where u becomes sufficiently small relative to the total variation in<br />

the data (see also Davutyan <strong>and</strong> Pippenger 1985). In the context of a PPP study,<br />

Frankel <strong>and</strong> Rose (1995) demonstrate that for panel data sets defined for the recent<br />

floating period the cross-sectional variability dominates the time series variability.<br />

Therefore Cov (φ, p − p ∗ ) is likely to go to zero in a panel framework.<br />

The earliest application of panel methods to testing PPP was that of Hakkio<br />

(1986),who used a monthly data set for the period March 1973–April 1982 to<br />

estimate equation (2.16) for the UK pound,French franc,Canadian dollar <strong>and</strong><br />

Japanese yen (all against the US dollar). A systems estimator was used which<br />

incorporated the correlation of the error term across countries <strong>and</strong> Hakkio found

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!