The study is better than the title. It examined U.S. mail order sales from a 1979 catalogue for 44 women’s blouses priced from $5 to $20. Predictions were made by a buyer, the normal procedure used in making initial orders. Consumer intentions were then obtained from 600 women shoppers in shopping malls. The intentions were obtained with a 5-point rating scale in response to a set of photographs. Four different methods were considered for summarizing the ratings for each blouse (median, Thurston, mean and “fraction in top two categories”). So here are the questions:
(a) Which provides the best predictions, the expert (buyer) or the intentions survey?
(b) Does it matter how the rating scale is summarized in the intentions survey?
The answer to (a) was that each provided useful information for prediction, and the predictive ability of the expert was about equal to that of the intentions survey. For (b) the method used to summarize the rating scale did not seem to have much effect on the accuracy of predictions.
Sewell (personal communication) suggests that the combined use of expert and intentions information will improve predictions. He said that it allowed for a 15 percent reduction in inventory ordering errors in this case.