Regression Model Fitting With Quadratic Term Leads to Different Conclusion in Economic Analysis of Washington State Smoking Ban
2011

Different Conclusions from Smoking Ban Economic Analysis

publication Evidence: moderate

Author Information

Author(s): Ma Marshal, McClintock Scott

Primary Institution: Pennsylvania Department of Health

Hypothesis

Does the inclusion of a quadratic term in regression models affect the conclusions drawn about the economic impact of the Washington State smoking ban?

Conclusion

The inclusion of a quadratic term in the regression model suggests that the smoking ban did not significantly affect taxable retail sales, contrary to previous findings.

Supporting Evidence

  • The quadratic model provided a better fit for the data than the linear model.
  • The model with the quadratic term showed a $42.3 million decrease in taxable retail sales after the smoking ban.
  • Previous findings suggested a $105 million increase in sales, which was contradicted by the quadratic model.

Takeaway

When looking at how a smoking ban affects bar sales, using a more complex math model shows that the ban might not have helped sales as much as previously thought.

Methodology

The authors fitted taxable retail sales data to both linear and quadratic regression models to analyze the impact of the smoking ban.

Limitations

The model did not include unemployment, population, and income variables, which could affect the results.

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication