Skip to main content

Table 10 Vector error correction model results for Juba and Addis Ababa market pairs

From: The impact of production shocks on maize markets in Ethiopia: implications for regional trade and food security

CoefficientsCointegrating vector and adjustment coefficient
\( {P}_{t-1}^{ETH} \)1.139**
ECTt-1− 0.236*
Half-life2.57
Short-run parameters
\( {\Delta P}_{t-1}^{JUBA} \)− 0.209
\( {\Delta P}_{t-2}^{JUBA} \)0.073
\( {\Delta P}_{t-1}^{ETH} \)− 0.618
\( {\Delta P}_{t-2}^{ETH} \)− 1.007
 Shift130.076*
Model specification tests
 LM (3) test0.71
 Adj. portmanteau test0.39
 Normality test438***
MARCH-LM test54.77**
ARCH LM test0.36
  1. Half-life is computed as h = [ln(0.5)/( ln(1 + α)], where α is the error correction term (ECTt-1) and interpreted in months; adj. portmanteau test denotes adjusted portmanteau test which has more powerful small sample properties than the standard portmanteau test (see Lütkepohl and Krätzig 2004, 127); MARCH-LM test denotes multivariate ARCH test; ***, ** reject the null hypothesis at 1 and 5% significance levels, respectively