Estimated percentage change in quit success (the proportion successful quitters among those who made an attempt in the past 2 months) per 10% change in mass media expenditure from ARIMAX models
| Quit success | Unadjusted | Adjusted for covariates in table |
| Percentage change per 10% change in the exposure (95% CI), p Value | Percentage change per 10% change in the exposure (95% CI), p Value | |
| Smoking cessation | ||
| Mass media expenditure (lag 0) | 0.55 (0.15 to 0.96), 0.007 | 0.51 (0.10 to 0.91), 0.014 |
| Weekly spend tobacco (lag 0) | −16.83 (-37.41 to 3.75), 0.109 | |
| Cessation aid use (lag 4) | 2.11 (-1.51 to 5.73), 0.254 | |
| Tobacco control policies | −0.15 (-2.09 to 1.79), 0.878 | |
| Best fitting model | ARIMAX (0, 1, 1) (0, 0, 0) | ARIMAX (0, 1, 1) (0, 0, 0) |
| Non-seasonal (p)—AR | NA | <0.001 |
| —MA | <0.001 | NA |
| Seasonal (p)—AR | NA | NA |
| —MA | NA | NA |
| R2 | 0.075 | 0.112 |
Additional MA (0, 1, 2) or AR (1, 1, 1) terms were not significant. The assumption of normally distributed errors was met. When all lags were set to zero in the adjusted model, similar results were found for mass media (β=0.50 (0.10 to 0.90), p=0.015). A lag of 1 month for mass media expenditure, although with a considerably worse fit, led to a comparable increase in quit success (β=0.49 (0.10 to 0.87), p=0.013).
AR, autoregressive terms; ARIMAX, Autoregressive integrated moving average modelling with exogenous variables;MA, moving average terms.