Demand Potential for Goat Meat in Southern States: Empirical Evidence from a Multi-State Goat Meat Consumer Survey

12

statistic -2 (L₀ -L₁) to test the hypothesis that certain parameters equal zero. Variables in
the initial set would be eliminated if they lack appropriateness or power in explaining
consumer purchasing behavior.

Results and Discussion

We use logistic procedure in the SAS software package to estimate models. The
estimated results of the existing demand, potential demand, and demand related to season
and occasions are reported as follows:

Results of the Existing Demand

The model for the existing demand in Southern states is estimated with effective
observations of 2675. The estimated parameters are presented in Table 2.

Multiple statistics (Likelihood ratio, Wald, and Score) confirm that the variability of
response variable is largely explained by the retained set of variables. The results in
Table 2 demonstrate multiple factors in the determination of goat meat consumption.
First, the consumption of other meat influences goat meat consumption, but not all of
them are significant. No impact from beef consumption is observed, and the expected
substitution effect of Lamb is also not observed. In fact, households are less likely to eat
goat meat if they never consume lamb, suggesting a complimentary relationship. The
impacts of the consumption of chicken and pork are evidenced. Consumers eating
chicken once a week is more likely to eat goat meat than other categories. For pork, the
compliment impact is observed.

Demographic variables including race and age play a significant role. Race is a
critical driving force for goat meat consumption. Compared with the White, the odds

<<   10   11   12   13   14   15   16   >>

More intriguing information