Why panel tests of purchasing power parity should allow for heterogeneous mean reversion

Abstract

JEL classification: F31 F33 F47 Keywords: PPP Real exchange rates Panel models Unit root tests Heterogeneity Panel tests a b s t r a c tRecent studies of purchasing power parity (PPP) use panel tests that fail to take into account heterogeneity in the speed of mean reversion across real exchange rates. In contrast to several other severe restrictions of panel models and tests of PPP, the assumption of homogeneous mean reversion is still widely used and its consequences are virtually unexplored. This paper analyzes the properties of homogeneous and heterogeneous panel unit root testing methodologies. Using Monte Carlo simulation, we uncover important adverse properties of the panel approach that relies on homogeneous estimation and testing. More specifically, power functions are low and assume irregular shapes. Furthermore, homogeneous estimates of the mean reversion parameters exhibit potentially large biases. These properties can lead to misleading inferences on the validity of PPP. Our findings highlight the importance of allowing for heterogeneous estimation when testing for a unit root in panels of real exchange rates.

Parity reversion in the Asian real exchange rates: new evidence from the local-persistent model

“…Our study is closely related to the work of Koedijk et al (2011) and Ozdemir and Cakan (2010), who have argued that, when studying the behaviour of RER, it is important to recognize that mean reversion may differ across individual countries. In fact, Ozdemir and Cakan (2010), employing a univariate analysis, show that persistence may vary not only across countries, but also over a sampling period for a sample of six East Asian countries.…”

“…Another restriction, as mentioned in Koedijk et al (2011), is the imposition of a homogeneous rate of mean reversion across all RERs in the panel. A panel approach that relies on homogeneous estimation and testing could lead to misleading inferences on the validity of PPP.…”

Does bad company corrupt good character? A spatial econometric analysis of oil resource management in Africa

“…Moreover, according to Koedijk et al (2011), the few studies that build upon panel data methodology featuring fixed or random effects are plagued by a high degree of homogeneity across the countries under study. Koedijk et al (2011) suggest that homogeneous estimates can exhibit large biases that may provoke wrong inferences and recommend heterogeneous estimation.…”

“…According to Cavalcanti et al (2011), cross-sectional regression methodology does not take into consideration the time dimension of the data and consequently may suffer from endogeneity bias. Moreover, according to Koedijk et al (2011), the few studies that build upon panel data methodology featuring fixed or random effects are plagued by a high degree of homogeneity across the countries under study. Koedijk et al (2011) suggest that homogeneous estimates can exhibit large biases that may provoke wrong inferences and recommend heterogeneous estimation.…”

Does Bad Company Corrupts Good Character? A Spatial Econometric Analysis of Oil Resource Management in Africa

“…According to Cavalcanti et al (2011), cross-sectional regression methodology does not take into consideration the time dimension of the data and consequently may suffer from endogeneity bias. Moreover, according to Koedijk et al (2011), the few studies that build upon panel data methodology featuring fixed or random effects are plagued by a high degree of homogeneity across the countries under study. Koedijk et al (2011) suggest that homogeneous estimates can exhibit large biases that may provoke wrong inferences and recommend heterogeneous estimation.…”