Abstract
The effect of the saccharin warning label on sales of diet soft drinks was modeled with an autoregressive integrated moving average (A RIMA) process. Retail price trends and attendant publicity were modeled concurrently to separate these effects from those due to the warning. Results indicated that the label produced a small yet statistically significant reduction in sales, with an abrupt onset and, thus far, permanent duration. Reasons for the absence of decay effects, limitations of interpretability, and ideas for improving future evaluations of warning labels are discussed.
Get full access to this article
View all access options for this article.
