Purchasing power parity in ASEAN+3: an application of panel unit root tests

Abstract

The paper assesses the existence of purchasing power parity (PPP) in ASEAN+3 economies taking into account EUR and USD as reference currencies. The research refers to the period from January 2000 to June 2017 and there are three points of view: we tested the period as a whole and then the pre-crisis period and the postcrisis period regarding the structural break due to the economic crisis. The evaluated economies include Brunei, Cambodia, China, Indonesia, Japan, Korea, Laos, Malaysia, Myanmar, the Philippines, Singapore, Thailand and Vietnam. A range of panel unit root tests are applied, covering the Levin, Lin and Chu test, the Breitung test, the Im, Pesaran and Shin test, the ADF-Fisher test and the PP-Fisher test. In cases where the unit root is rejected, the validity of PPP is confirmed. However, our results are ambiguous and depend on the selection of the base currency, the time period observed and on the choice of the methodology.

Are the Mediterranean Countries With Tourism Price Indices in the Purchasing Power Parity Zone?

“…Levin et al (2002) and Breitung (2000) approaches deal with common unit root processes, where there are common autoregressive coefficients across cross-sections (ρ i =ρ) for all i. According to Boršič and Bekő (2018) the preceding subsections summarize the main specific attributes of individual panel unit tests used in this study. Im et al (2003) estimate individual ADF regression for each cross-section taking into account individual unit root processes:…”

Testing the Purchasing Power Parity Hypothesis: Case of ASEAN Economies

“…In search for evidence in favour of PPP, this paper applies panel unit root tests. As described in Boršič and Bekő (2018), the model takes into account the following autoregressive [AR(1)] process for panel data:…”

“…On the other hand, Im, Pesaran, and Shin (2003), Fisher ADF and Fisher PP (Maddala & Wu, 1999;Choi, 2001) procedures deal with individual unit root processes, where ρ i varies across cross-sections. According to Boršič and Bekő (2018), the precending subchapters denote the specific characteristics of panel unit tests applied in this study.…”