The impact of some errors associated with a national road traffic survey is examined in this thesis. The current survey aims to evaluate efforts to reduce the speed of traffic on Swedish roads; it covers both state and urban roads, though the thesis considers only urban roads. In the survey, observational sites are selected by a three-stage sampling procedure. A measurement device installed on the road is used to collect data, from which the average speed of traffic on the roads is estimated. This thesis focuses on errors in the frames used in the final sampling stage, and on errors due to missing data. The impact of these errors on the total error of the survey estimators is investigated. Also explored are possibilities for reducing the total error by weighting adjustments for missing data and by reallocating the sample over the three sampling stages. The problems are approached partly theoretically, by use of various error models; partly empirically, by collecting data on the errors. Throughout, the sampling design of the survey is taken properly into account. Our conclusion is that the frame error under consideration probably does not bias the estimator of average speed, and it only implies a minor increase of its variance. It remains unclear whether the estimator needs to be adjusted for missing data: however, a theoretical framework for further investigations is provided. For unchanged total sample size, the precision of the estimator is likely to improve if the sample sizes in the third stage are increased, and the sampling sizes in the first stage are decreased correspondingly. (Author/publisher)
Samenvatting