Analysis of agreement between measurements of continuous variables: general principles and lessons from studies of imaging of carotid stenosis

Clinical research often involves measurement of continuous variables. Howev er, clinical measurements are seldom precise. It is frequently necessary, t herefore, either for the reproducibility of measurements to be assessed (ob server agreement studies), or for measurements made by different techniques to be compared (method comparison studies). There are numerous ways in whi ch data can be analysed and reported in such studies, and several pitfalls. In order to determine which methods are commonly used in the medical liter ature, a systematic review of studies involving measurement of carotid sten osis was performed. A random sample of 40 studies were selected for detaile d assessment. The methods of analysis of reproducibility of measurement of stenosis and/or comparison of two alternative techniques of measurement wer e recorded. Ten different methods were identified. The advantages and disad vantages of each of the methods are discussed in a non-technical and non-ma thematical manner, and illustrated using data from a study of measurement o f carotid stenosis by two observers on 1001 carotid angiograms.