112
Table 6. Haugh-Pierce (H-P) Causality Tests on Quarterly Ex-vessel,
Wholesale, and Retail Prices for the 31-40 Size Class Using
ARIMA Filtered Data.
Series 1 =
Series 2
Series 3 *
Prewhitened Ex-vessel Prices
Prewhitened Wholesale Prices
Prewhitened Retail Prices
TEST
I
TEST
II
(N 49)a
(N =
49)a
Lag (k) in
A
Cross Correlations (r..(k)}
A
Cross Correlations {r..(k)
Causal
A
A
A
A
Series j
(a) r2>1(k)
(b) r1>2(k)
(a) r3j2(k)
(b) r2>3(k
0
.912*
.912*
.618*
.618*
1
.059
-.058
.248
-.033
2
-.075
-.030
-.097
.050
3
.022
-.082
.119
-.107
4
-.158
-.163
-.052
-.123
5
-.211
-.148
-.319*
-.207
6
-.001
.049
-.128
.029
TEST Is
(a) Null Hypothesis: ex-vessel does not cause wholesale price,
H-P X6 3.87**
(b) Null Hypothesis: wholesale does not cause ex-vessel price,
H-P x| = 3.40**
TEST II:
(a) Null Hypothesis: wholesale does not cause retail price,
H-P 10.09**
(b) Null Hypothesis: retail does not cause wholesale price,
H-P X6 3.63**
aN is the effective number of observations for cross correlation.
Greater than two standard errors (s), where s = N-*^.
**Fail to reject null hypothesis at .10 level.