Table 3
Results from the random parameter logit model
| Variables | (1) | (2) | (3) | (4) | (5) | (6) | |
| North | Central | South | |||||
| Parameter estimates | Mean price coefficient | Parameter estimates | Mean price coefficient | Parameter estimates | Mean price coefficient | ||
| Price | b | −1.226 | −0.486 | −1.373 | −0.441 | −1.230 | −0.565 |
| (0.061) | (0.042) | (0.088) | (0.039) | (0.110) | (0.043) | ||
| s | 1.005 | 1.052 | 1.148 | ||||
| (0.056) | (0.077) | (0.082) | |||||
| ASC | Yes | Yes | Yes | ||||
| Demographics × ASC | Yes | Yes | Yes | ||||
| Log likelihood | −3088 | −3009 | −4136 | ||||
| Number of choice tasks per person | 8 | 8 | 8 | ||||
| Number of participants | 386 | 380 | 385 |
Parameter estimate columns report the mean b and standard deviation s of the log of the random price coefficient. Then the mean β of the random price coefficient is recovered by applying the transformation
and reported in the mean price coefficient columns.Robust SE in parentheses.
ASC, alternative-specific constant.
