Principle 3. - Accountability

To facilitate a correct interpretation of the data, the statistical agencies are to present information according to scientific standards on the sources, methods and procedures of the statistics.

From the design stage through to the dissemination stage of a statistical collection or compilation there are many ways in which errors can be introduced into the results. Some errors, particularly those resulting from the use of sampling, are random and their magnitude measurable. Other errors, mainly from non-sampling sources or from the choice of model and assumptions behind the measurement process, can introduce bias into the results and are difficult to measure. Whether errors can be measured or not, information on their source and extent should be made openly available to users so that they can judge the fitness of use of the data. This information on known sources of error and the

concepts, sources and methods behind the statistics should be readily found, by either including it along with the results or by being readily available as accompanying documentation.