X hits on this document





4 / 8


European Journal of Economics, Finance And Administrative Sciences - Issue 18 (2010)

3.2. Granger Causality Test

In this section, we employ the Granger Causality test to explore the causal relationship between the two variables. The result of the analysis is presented in Table 1.

Table 1:

Results of the Granger Causality Test

Lag 6

Lag 2

Asia Lag 4

Lag 6

log(E) log(P)

log(P) log(E)

log(RER) log(P) log(YGAP) log(P) Notes:

log(P) log(RER)

log(P) log(YGAP)

Lag 2

Null Hypothesis

Lag 2

All region Lag 4

Lag 6


on Asia Lag 4



Sample period 1991-2005; P=consumer price index; E=nominal exchange rates; RER=real YGAP=((real GDP – potential GDP) /potential GDP) "" indicates that the null hypothesis is rejected, that means the causality is happened.



From the table, it can be seen that there is a bi-directional causality between the nominal exchange rates changes ( log(E)) and inflation ( log(P)). That means, the nominal exchange rate depreciation will affect the inflation and the inflation will result in nominal exchange rate depreciation. The similar results were also found for the relationships between real exchange rates ( log(RER)) and inflation. However, when we separated the analysis into two regions --Asia and Non-Asia-- we found a different results. In Asia region, exchange rates depreciation has a significant impact on the inflation, but not in the opposite direction. In contrast, inflation has significant impact on the exchange rates in Non-Asia region, but not in the opposite direction. These results indicate that Asian countries have a higher vulnerability to exchange rates shocks in compare to European and North American countries. than the exchange of non-Asian.

Concerning the relationships between output gap (log(YGAP)) and inflation, we found that there is one direction relationship from output gap to inflation. That means, output gap significantly influences inflation, but inflation has no significant impact on output gap. This relation seems to be consistent for all over the three regions --Asia, Europe and North America.

3.3. Data Panel Analysis

Furthermore, we also employ the panel data analysis to explore the relationship between inflation, exchange rates and output gap in an integrated system. Preliminary analysis using Hausman-Test shows that the H-statistics (108.750 for all region, 52.449 for Asia and 13.883 for Non-Asia region) are greater than 2 from the table (11.070). The complete results are presented in Appendix 2. Based on these results, we conclude that the fixed effect model is the most appropriate one for our further analysis. The result is presented in Table 2.

In the model presented in Table 2, we include two dummy variables --namely Area dummy DA (DA=1 for Asia and DA=0 for Non-Asia) and Crisis Dummy DC (DC=0 for the period before the Asian crisis and DC=1 for the period after the Crisis) to capture and compare the behavior on inflation between two regions and two periods.

Document info
Document views14
Page views14
Page last viewedSat Oct 22 05:36:04 UTC 2016