enEnglish
CROS

Quality of Statistics (Theme)

Summary

Quality may be defined as "the degree to which a set of characteristics fulfils requirements" using the much cited ISO standard 9000 (2005). This is valid also for quality of statistical output. The European Statistical System (Eurostat , 2011, principles 11-15; EU , 2009a) uses nine major quality characteristics of statistical output: relevance, accuracy and reliability, timeliness and punctuality, coherence and comparability, accessibility and clarity.

Accuracy is generally considered to be a key measure of quality. Total survey error is a conceptual framework describing errors that can occur in a sample survey and the error properties. It may be used as a tool in the design of the survey, working with accuracy, other quality characteristics, and costs. Accuracy is often measured by the mean squared error (MSE) of the estimator. Error sources are considered one by one to estimate the uncertainty and also to obtain some indication of the importance of that source. The errors arise from: sampling, frame coverage, measurement, non-response, data processing, and model assumptions.

Even if statistics are accurate, they cannot be considered as of good quality if, for instance, they are outdated or cannot be easily accessed or there is conflict with other statistics. The quality may be viewed as a multi-faceted concept. Although a major objective of the survey design may be to somehow ‘optimise’ the accuracy, additional quality criteria such as relevance, timeliness, comparability and coherence, and accessibility and clarity are critical to a survey's quality. There needs to be a balance in line with, for instance, regulations and user needs.

 

To read the entire document, please access the pdf file (link under "Related Documents" on the right-hand-side of this page).

 

Your feedback is appreciated. Please send your remarks, suggestions for improvement, etc. to memobust@cbs.nl.