Statistical properties and survey design of visitor spending using segmentation

Estimating visitor spending through the segmentation approach has several advantages in terms of policy evaluation, user management and sampling design. This approach generally relies on visitor surveys to estimate two parameters, average spending per segment and segment share, so that total visitation can be apportioned to each subgroup. Equivalently, this approach is to estimate the weighted average spending by taking into consideration the relative shares of each user segment. This paper first provides a statistical formula to compute the variance of weighted average spending by taking into account the stochastic nature of spending and segment shares. Second, simulation analysis is adopted to compare the accuracy and precision of the spending estimator based on different study designs. The results show that conducting additional short surveys to obtain information on user segments provides two advantages. First, it helps to reduce non-response bias since certain visitor groups have higher ratios of unreturned questionnaires, incomplete data or non-participation. Second, it helps to decrease the variance of the estimator so that the upper and lower bound of the confidence interval can be narrowed. The level of variance reduction will depend on the relative segment shares, the average spending, cases that are obtained, spending variation and the probability of giving full spending information across segments. The implications for survey design are offered in light of the results.