<abstract xmlns="http://www.w3.org/1999/xhtml"><p>For policymakers and other users of official statistics, it is crucial to distinguish real differences underlying statistical outcomes from noise caused by various error sources in the statistical process. This has become more difficult as official statistics are increasingly based upon a mix of sources that typically do not involve probability sampling. In this article, we apply a resampling method to assess the sensitivity of mixed-source statistics to sourcespecific classification errors. Classification errors can be seen as coverage errors within a stratum. The method can be used to compare relative accuracies between strata and releases, it can assist in deciding how to optimally allocate resources in the statistical process, and it can be applied in evaluating potential estimators. A case study on short-term business statistics shows that bias occurs especially for those strata that deviate strongly from the mean value in other strata. It also suggests that shifting classification resources from small and mediumsized enterprises to large enterprises has virtually no net effect on accuracy, because the gain in precision is offset by the creation of bias. The resampling method can be extended to include other types of nonsampling error.</p></abstract>

For policymakers and other users of official statistics, it is crucial to distinguish real differences underlying statistical outcomes from noise caused by various error sources in the statistical process. This has become more difficult as official statistics are increasingly based upon a mix of sources that typically do not involve probability sampling. In this article, we apply a resampling method to assess the sensitivity of mixed-source statistics to sourcespecific classification errors. Classification errors can be seen as coverage errors within a stratum. The method can be used to compare relative accuracies between strata and releases, it can assist in deciding how to optimally allocate resources in the statistical process, and it can be applied in evaluating potential estimators. A case study on short-term business statistics shows that bias occurs especially for those strata that deviate strongly from the mean value in other strata. It also suggests that shifting classification resources from small and mediumsized enterprises to large enterprises has virtually no net effect on accuracy, because the gain in precision is offset by the creation of bias. The resampling method can be extended to include other types of nonsampling error.

Sensitivity of Mixed-Source Statistics to Classification Errors

Statistics Netherlands, Department of Process Development and Methodology, CBS-weg 11, P.O. Box 4481, 6401 CZ Heerlen, The Netherlands

Statistics Netherlands, Department of Process Development and Methodology, Henri Faasdreef 312, P.O. Box 24500, 2490 HA The Hague, The Netherlands

Journal of Official Statistics

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

{"article-title":"Sensitivity of Mixed-Source Statistics to Classification Errors"}

For policymakers and other users of official statistics, it is crucial to distinguish real differences underlying statistical outcomes from noise caused by...

Sensitivity of Mixed-Source Statistics to Classification Errors

Publié en ligne: 01 sept. 2015

Pages: 489 - 506

DOI: https://doi.org/10.1515/jos-2015-0029

Mots clés
Accuracy, coverage error, administrative data, short-term business statistics, bootstrap, resampling

© by Joep Burger

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Sensitivity of Mixed-Source Statistics to Classification Errors

Publié en ligne: 01 sept. 2015

Pages: 489 - 506

DOI: https://doi.org/10.1515/jos-2015-0029

Mots clésAccuracy, coverage error, administrative data, short-term business statistics, bootstrap, resampling

© by Joep Burger

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Mots clés
Accuracy, coverage error, administrative data, short-term business statistics, bootstrap, resampling