Quality of statistics

							Quality of statistics

The Statistical Office of the Republic of Slovenia (SORS) focuses on providing quality and user -friendly
national statis tics, which means the statis tics are presented and accessible in a user -friendly way.

In the past, the quality of national sta tistics was dealt with mostly in connection with data accuracy in
the narrow sense (mainly as coherence between statistical data and exact values). In the last decade
the statis tical profession has made great progress towards broader understanding of the quality of
statistical data. The mos t developed countries implemented a new approach in national statis tical
institutes: to tal quality management at the level of organization. C onsiderable change in dealing with
quality in the European Statistical System was brought by the European Statistics C ode of Practice,
which was adopted in 2005.

Strategy of Quality in National Statistics
SORS understands the quality policy as a corporate culture with five basic quality pillars (main factors),
mutually linked with modern management tools. These pillars are:


       Independent national statistics. The current arrangement of the natio nal statis tical system in
        Slovenia assures high level of professional independence of national statistics (i.e. the national
        statistical office together with the authorized producers of statistical surveys). This position will
        be further strengthened, since only professionally and politically independent statis tics are
        trustworthy and thus relevant for the users.
       Data users and data providers. Balancing between users’ requests for statistical data and
        information on one hand and demands to provide data presented to the data providers on the
        other is becoming increasingly difficult. It is therefore extremely important to monitor to what
        extent published statis tics meet the expectations and needs of users and to monitor burden
        caused on data providers due to their obligation to report the data for statis tical purposes.
        Reducing the burden of data providers and assuring confidentiality and protection of the
        submitted data (which mus t be used exclusively for statistical purposes) will continue to be
        fundamental tasks of national statis tics.
       Quality of statistical produc ts and related services. In order to provide good quality statistical
        products and services, the office complies with the standard definition of q uality, as well as
        with the principles of the European Statis tics C ode of Practice. The dissemination of quality in
        national statis tics made great progress with the documenta tion of the quality of statistical
        surveys in the form of standard quality reports.
       Process orientation of national statistics. In the process of preparing statistical data and
        information in the framework of individual statis tical surveys sources used, metho dologies,
        procedures and also costs related to the statis tical survey play an important role. With
        transparent statistical process and clearly documented procedures, better quality of the results
        and better cost efficiency can be obtained.
       Human resource development. Training of employees in order to increase the level of quality of
        statistical products and services includes several aspects: methodological knowledge,
        information know-how and the promotion of good practices exchange. It is important tha t th e
        employees in the system of national statistics – at SORS and at the statistical units of
        authorized producers – are aware of the content of the European Statistics C ode of Practice
        and that they work in accordance with it in their everyday professional w ork.

The main pillars (factors) of quality presented above are defined and thoroughly described in the
Medium-term Programme of Statistical Surveys 2008-2012. The strategic directions from the Medium-
term Programme of Statistical Surveys are in detail presented in the Total Quality Management
Strategy 2006-2008.

The European Statistics Code of Practice
With the adoption of the European Statis tics C ode of Practice (in 2005) Eurostat and the statis tical
authorities of the EU Member States have committed themselves to an encompassing appro ach
towards high quality s tatistics. T he C ode builds upon a common definition of quality (which was
developed and accepted within the European Statistical System) and targets all relevant areas:
institutional environment, s tatistical processes and statistical outputs. T he C ode is nowadays a
recommendation which should be followed as much as possible; Member States and Eurostat should
regularly report on implementation to the European C ommission. The first report for 2005 was done in
the form of a self-assessment questionnaire. As the next step towards the implementation of the C ode,
Eurostat organised peer reviews to complement the self-assessments. They are considered a vital
element for the implementation of the C ode in practice given their capacity to encourage the sharing of
best practice and to contribute to better transparency of the whole statistical system. The peer review
of SORS took place in May 2007. The report includes the description of the situa tion at that time of the
implementation of the C ode at SORS and the recommendations for further improvements. The peer
review reports from other countries are available on Eurostat's website.

Data Quality Components
SORS adopted the Eurostat’s common quality definition. Ac cording to this definition the quality of
statistical data is composed of the following six components:


       Relevance. Relevance is the degree to which statis tics meet current and potential user needs.
        It refers to whether all statistics that are needed are pr oduced and the extent to which
        concepts used (definitions, classifications, etc.) reflect user needs.
       Accuracy. In the general statistical sense this concept denotes the closeness of computations
        or estimates to the (unknown) exact or true values. Statis tical data are namely not equal to
        the true values because of variability (values vary due to random effects/errors that appear at
        the implementation of the survey) and bias (values vary due to systematic effects/errors that
        appear at the implementation of the survey).
       Timeliness and punctuality. Timeliness of publica tion reflects the length of time between the
        period when the statis tical phenomenon was observed and the release date of data. Punctuality
        refers to the time lag between the announced date of publication (for example in the release
        calendar) and the actual release date of data.
       Comparability. Used concepts should be harmonized, so that the ob tained data and information
        are comparable over time, between geographical areas and between domains.
       Coherence. C oherence of statistics is their adequacy to be reliably combined in different ways
        and for various uses. The problems with coherence can occur when data originate from
        different sources or from different statistical surveys, where the used conce pts, classifications
        and methodological standards are not harmonized.
       Accessibility and clarity. Accessibility refers to the physical conditions for users to access the
        statistical data: where and how it is possible to order data, delivery time, how much it costs
        (clear pricing policy), access to microdata and metadata, availability in various formats. C larity
        refers to the environment in which the data are presented: are data accompanied by
        appropriate metadata, by graphical presentations, by information on their quality and by
        information about the extent to whic h additional assistance is provided by the national
        statistical ins titute.


Besides the mentioned quality components, SORS also adds a seventh component, costs and burdens.
This component measures the cost efficiency of statistical surveys and the burden of reporting units
(data providers) when they report the demanded data for statistical purposes.

Reporting About the Quality of Statistical Surveys
Standard quality reports for statistical surve ys have been regularly prepared by SORS since 2006 and
they cover a broad scope of quality indicators for statistical surveys (in line with the Eurostat’s standard
for quality reports). Later on also annual quality reports for statistical surveys were introduced; these
are shorter, translated also in English and include only the most impor tant quality indicators about
individual statis tical surveys and are prepared every year. These q uality indicators provide an overview
of various quality components and enable comparability between statistical surveys and between
countries. Individual quality indica tors can be divided into producer and user oriented: the former
measure quality from the point of view of producers and the latter from the point of view of users of
statistical results. More information about the quality definition and quality indicators is available on
Eurostat's Quality homepage.

User Satisfaction Surveys
User satisfaction with s tatistical data and services is regularly monitored with various user satisfaction
surveys. The results of these surveys are an important source of information about the needs of users
and problems they face.