Survey context and question wording affects self reported annoyance due to road traffic noise: a comparison between two cross-sectional studies

Background: Surveys are a common way to measure annoyance due to road traffic noise, but the method has some draw-backs. Survey context, question wording and answer alternatives could affect participation and answers and could have implications when comparing studies and/or performing pooled analyses. The aim of this study was to investigate the difference in annoyance reporting due to road traffic noise in two types of surveys of which one was introduced broadly and the other with the clearly stated aim of investigating noise and health. Methods: Data was collected from two surveys carried out in the municipality of Malmo, southern Sweden in 2007 and 2008 (n = 2612 and n = 3810). The first survey stated an aim of investigating residential environmental exposure, especially noise and health. The second survey was a broad public health survey stating a broader aim. The two surveys had comparable questions regarding noise annoyance, although one used a 5-point scale and the other a 4-point scale. We used geographic information systems (GIS) to assess the average road and railway noise (L-Aeq,L- 24h) at the participants' residential address. Logistic regression was used to calculate odds ratios for annoyance in relation to noise exposure. Results: Annoyance at least once a week due to road traffic noise was significantly more prevalent in the survey investigating environment and health compared to the public health survey at levels >45 dB(A), but not at lower exposure levels. However no differences in annoyance were found when comparing the extreme alternatives "never" and "every day". In the study investigating environment and health, "Noise sensitive" persons were more likely to readily respond to the survey and were more annoyed by road traffic noise compared to the other participants in that survey. Conclusions: The differences in annoyance reporting between the two surveys were mainly due to different scales, suggesting that extreme alternatives are to prefer before dichotomization when comparing results between the two. Although some findings suggested that noise-sensitive individuals were more likely to respond to the survey investigating noise and health, we could not find convincing evidence that contextual differences affected either answers or participation.