J. Swait et al., A SEQUENTIAL APPROACH TO EXPLOITING THE COMBINED STRENGTHS OF SP AND RP DATA - APPLICATION TO FREIGHT SHIPPER CHOICE, Transportation, 21(2), 1994, pp. 135-152
The possibility of and procedure for pooling RP and SP data have been
discussed in recent research work. In that literature, the RP data has
been viewed as the yardstick against which the SP data must be compar
ed. In this paper we take a fresh look at the two data types. Based on
the peculiar strengths and weaknesses of each we propose a new, seque
ntial approach to exploiting the strengths and avoiding the weaknesses
of each data source. This approach is based on the premise that SP da
ta, characterized by a well-conditioned design matrix and a less const
rained decision environment than the real world, is able to capture re
spondents' tradeoffs more robustly than is possible in RP data. (This,
in turn, results in more robust estimates of share changes due to cha
nges in independent variables.) The RP data, however, represent the cu
rrent market situation better than the SP data, hence should be used t
o establish the aggregate equilibrium level represented by the final m
odel. The approach fixes the RP parameters for independent variables a
t the estimated SP parameters but uses the RP data to establish altern
ative-specific constants. Simultaneously, the RP data are rescaled to
correct for error-in-variables problems in the RP design matrix vis-a-
vis the SP design matrix. All specifications tested are Multinomial Lo
git (MNL) models. The approach is tested with freight shippers' choice
of carrier in three major North American cities. It is shown that the
proposed sequential approach to using SP and RP data has the same or
better predictive power as the model calibrated solely on the RP data
(which is the best possible model for that data, in terms of goodness-
of-fit figures of merit), when measured in terms of Pearson's Chi-squa
red ratio and the percent correctly predicted statistic. The sequentia
l approach is also shown to produce predictions with lower error than
produced by the more usual method of pooling the RP and SP data.