386
International Food and Agribusiness Management Review Vol. 2/No. 3/4/2001
Table 5. Segmentation of the Independent Variable According to the
Houck Procedure
Pr,t |
PRt Pr,t 2 Pr,0 |
Pp,t |
DPpt |
PPPt ¥DPp1,t |
NPPt ¥DPp2,t |
13000 |
0 |
6875 |
— |
— |
— |
12890 |
2110 |
6693 |
2182 |
0 |
2182 |
12289 |
2711 |
6636 |
257 |
0 |
2239 |
13159 |
159 |
6604 |
232 |
0 |
2271 |
13047 |
47 |
6524 |
280 |
0 |
2351 |
13054 |
54 |
6551 |
27 |
27 |
2351 |
13060 |
60 |
6748 |
197 |
224 |
2351 |
13066 |
66 |
6751 |
3 |
227 |
2351 |
12588 |
2412 |
6742 |
29 |
227 |
2360 |
12582 |
2418 |
6787 |
45 |
272 |
2360 |
the structural model (3). The results in Table 7 indicate that ^t is not significant
in the equation, that is, we fail to reject the null hypothesis that producer prices
are weakly exogenous with respect to the short-run parameters in (3). Both tests
confirm our choice of estimating (3) with Pr as a dependent variable.
Returning to Table 7, note that the positive error correction term (ECTt12 1)is
significant at the 1% level in the equation, whereas the negative error correction
term (ECTt22 1) is only significant at the 10% level. The difference in the value of
the associated coefficients suggests that increases in producer prices are transmit-
ted more efficiently to retail prices than are producer price decreases. However,
we fail to reject the null hypothesis of symmetry, (b21 5 b22), using an F;test
(1,3638; Pr 5 0,2429). Empirical results support the hypothesis that retail prices
in Ho Chi Minh City react in a symmetric way to changes in producer prices in
the supplying provinces.
Table 6. Estimation of the Model (2) of
Transmission Asymmetry between Pp and Pr in
the North (dependent variable 5 PRt)
Independent variables
Model (2)
constant
NPPt
NPPt21
NPPt22
PPPt
PPPt21
PPPt22
R2
Hz0
F-stat
1054,55**
0,4962
1,0265**
0,5942**
1,9032**
0,0435
0,3029
0,9646
Pr
k
O bm1
m50
k
O bm2
m50
b01 5 b02, b11 5 b12 ...,bm1 5 bm1
25,6726
11,6875
0.0000
0.0000
Note: * 5 significant at 5%, ** 5 significant at 1%.