Skip to main content

Table 2 Results of panel unit root tests

From: Is gold a safe haven for the dynamic risk of foreign exchange?

Level LG LE
Method   
Levin, Lin & Chu t* test −3.809***
(0.001)
1.767
(0.961)
Breitung t-stat test 0.662
(0.746)
−0.667
(0.252)
Im, Pesaran and Shin W-stat test −0.180
(0.428)
−0.761
(0.223)
ADF—Fisher Chi-square test 20.52
(0.902)
24.75
(0.736)
PP—Fisher Chi-square test 20.81
(0.893)
22.64
(0.829)
Difference \(\Delta\)LG \(\Delta\)LE
Levin, Lin & Chu t* test −116.7***
(0.000)
−95.93***
(0.000)
Breitung t-stat test −30.90***
(0.000)
−15.57***
(0.000)
Im, Pesaran and Shin W-stat test −84.34***
(0.000)
–86.47***
(0.000)
ADF—Fisher Chi-square test 3950.8***
(0.000)
3950.8***
(0.000)
PP—Fisher Chi-square test 3950.8***
(0.000)
3950.8***
(0.000)
  1. Done on EViews 12
  2. We specified lags at four by minimum AIC Exogenous variables: individual effects, individual linear trends. The notation "***" implies the statistical significance at 1% level. Fisher tests are computed using an asymptotic Chi-square distribution. Values in the parentheses (.) are the p value. All other tests assume asymptotic normality. When carrying out the test as well as the estimation, all variables are formed in natural logarithm