Comments on Rossow: The alcohol advertising ban in Norway: Effects on recorded alcohol sales.

Rossow conducts an interrupted-auto-regressive integrated moving average (ARIMA) analysis of alcohol advertising bans in Norway for the 47-year period from 1960 through 2006. Norway's comprehensive restrictions on alcohol advertising occurred in 1975 and 1977. Rossow uses annual data on recorded alcohol sales (litres of pure alcohol per capita) to determine an 'immediate and lasting effect' from the July 1975 ban of about -7%. A lasting effect is not apparent from a plot of the sales data. The sales data are adjusted for changes in real wages and real prices, although the exact method of adjustment and empirical results are not reported, for example, do the wage and price variables have the expected signs? As part of the analysis, Rossow offers two critical comments on my own work in this area. Her comments are incorrect. The purpose of this commentary is to provide a correct reporting of my methods and results. Also, as I have conducted an interrupted-ARIMA analysis and engaged in a dynamic time-series analysis of alcohol advertising, I assess the appropriateness of Rossow's ARIMA analysis for Norway's advertising bans.