Abstract:
The paper focuses on the US cigarette industry and uses a gradual switching regression model to estimate changes in the US demand for cigarettes over time. This technique is found to be superior to the use of dummy variables in capturing the health scare. The results show that cigarette demand gradually decreased over a ten-year period coinciding with the release of key health information. Price and advertising elasticities have gradually diminished, which is consistent with a change in the mix of US consumers before and after the switch. Copyright 1999 by Blackwell Publishing Ltd and the Board of Trustees of the Bulletin of Economic Research