Machine Learning for Official Statistics: Overview of machine learning techniques and their applications in official statistics, including classification, clustering, and predictive modelling
18 Feb 2025 – 18 Feb 2025
Source: Eurostat (Data extracted on: 01 Dec 2024 )
The 2024 meeting of the UN Committee of Experts on International Statistical Classifications will take place virtually in two sessions in May and October respectively. The second session of the meeting is scheduled virtually for 29, 31 October and 5 November 2024 from 6.00am to 9.00am New York time. The Committee is expected to review the progress of the Committee’s work programme and provide advice for the activities for the rest of the year.
Jointly organized by the United Nations Statistics Division (UNSD), the Economic and Social Commission for Western Asia (ESCWA), and the Arab Institute for Training and Research in Statistics (AITRS), this regional workshop will review international recommendations and standards for Statistical Business Registers. The program will facilitate the implementation of the Maturity Model for Statistical Business Registers and address emerging developments, including the global assessment questionnaire, revised industrial classification systems, geospatial information integration, and the global initiative on unique business identifiers.
Source: Eurostat (Data extracted on: 07 Mar 2024 )
[+] More
Organizer(s): Eurostat Icon-Institut
Description: The course should provide participants with a better understanding of the underlying principles and concepts of European and international economic and social classifications, their content and use.
Target Audience: Any statistician of a National Statistical Institute (including newcomers) dealing with any statistical domain and wishing to understand better the system of classifications used.
Description: The webinar, organized by the United Nations Network of Economic Statisticians and the United Nations Committee of Experts on International Statistical Classifications, will explore the role of technology in making the process of classification more efficient. Practical examples from various NSOs and organizations using international classifications will illustrate this point. Additionally, the webinar will close with a panel of senior executives from organizations around the world who will address some of the biggest challenges faced by organizations when implementing international classifications, such as the frequency of revisions, building and maintaining capacity, modernizing the classification process and more.
Description: The United Nations Network of Economic Statisticians and the United Nations Committee of Experts on International Statistical Classifications jointly organized a sprint webinar series on international statistical classifications, with the objective to raise the awareness of the importance of international classifications among users, provide a forum for discussing and sharing modern ways of updating and implementing classifications, and highlight the value of investing in classification work as a foundation for data integration. This second webinar’s theme was: the mechanisms for rendering the classification process more efficient through collaboration and coordination. It was attended by over 200 online participants from national statistics offices, regional and international organizations, classification users from specific industries, and experts on statistical classifications. The meeting provided an outreach opportunity for the Committee of Experts on International Statistical Classifications to engage directly with classification users on the concept of evergreening and on the importance of a more efficient revision process to develop agile and responsive international classifications. The webinar also provided a platform for sharing knowledge and experience on the review process and revision cycles of national, regional and international classifications. More information on the classifications sprint is available on UNSD website.
Description: The United Nations Statistics Division (UNSD), in collaboration with Statistics Indonesia (BPS), is organizing a workshop on Big Data in Asia-Pacific countries, focusing on an introduction to Remote Sensing and Land cover classification using remote sensing. The overall objective of the week-long workshop is to help participants better understand the use and benefits of Big Data specifically the utilization of Remote Sensing for Land Cover Classification. To that end, the workshop program will present methods, case studies, and processes that can support the Agricultural Statistics to identify the agricultural lands. This workshop is one of the first activities organized under the umbrella of the new Regional Hub for Big Data and Data Science in Official Statistics, which will be launched on 24 November 2023.
Description: The PACIFIC CIVIL REGISTRARS NETWORK (PCRN) will be organizing the third webinar in the Webinar series (Journey Towards ICD-11 in the Pacific) on ICD applications, introduction to WHO-FIC and in-depth ICD-11 transition discussion. When: 15 November 2023 To register: Click here.
Description: Classification of the Functions of Government (COFOG) is a classification defined by the United Nations Statistics Division and adapted to the IMF government finance statistics (GFS) reporting framework. COFOG enables trends in government expenditure by function (e.g., defense or education) or policy purposes to be examined over time. The value of this is that expenditure by functions of government of different countries can be compared. Participants will gain an understanding of how the ten functions of government as described in the GFSM 2014 are classified, how to categorize expenditure data to generate a functional split will be explained and how it should reconcile with the economic classification of expenditure data used in the GFS. Participants should feel comfortable to present and discuss relevant data of their own country. Practical exercises with participants working in random groups will feature throughout the course enabling them to be able to appropriately categorize expenditure data to the correct functional categories.
Description: International Statistical Classifications are an essential component of the statistical infrastructure. They ensure quality and relevance of statistics and their comparability across time and domains, e.g., output, trade, employment, balances, etc. International classifications are also essential to guarantee international comparability and therefore monitor global trend and phenomena in a reliable manner. In an increasingly interconnected world, classifications can play an important role for the integration of statistics across domains as long as the underlying concepts are clearly identified and to the extent possible linked. The revision and maintenance of classifications requires continuous and dedicated efforts to ensure that the classifications reflect the reality and support sound policymaking and informed decisions.
The Sprint is jointly organized by UN Network of Economic Statisticians and the UN Committee of Experts on International Statistical Classifications to raise awareness of the importance of international classifications with both internal and external users; advance outreach by the Committee of Experts on International Statistical Classifications to engage NSOs; provide an additional forum for discussing and sharing modern ways of updating and implementing classifications; and highlight the importance of investing in classification work as a foundation for data integration.
The Sprint consists of three webinars. The first webinar will explore the role of statistical classifications for data integration . It will raise awareness of the importance of international statistical classifications with both internal and external users and highlight the importance of investing in classification work as a foundation for data integration by showcasing real life applications inside and outside NSOs.
Description: The UN Committee of Experts on International Statistical Classifications is the central coordination body for the work on international statistical classifications that are the responsibility of the Statistics Division, and for the coordination and review of other international statistical classifications that are the responsibility of other international organizations and that have been proposed for adoption by the Statistical Commission.
Title in Arabic: التصنيفات المتعلقة بإحصاءات التجارة الدولية وأدلة الربط بينها
Organizer(s): AITRS
Description: تشمل الورشة التدريبية المواضيع أدناه: * لمحة عام عن التصنيفات الاقتصادية. * التغيرات التي طرأت على تصنيف النظام المنسق HS حسب نسخة عام 2022. * التغيرات على نسخة عام 2022 من التصنيف الموحد للتجارة الدولية SITC4. * أبرز التعديلات التي طرأت على تصنيف ISIC. * تمارين عملية حول ربط بيانات التجارة الخارجية باستخدام HS, SITC, ISIC. تهدف الورشة الى: * التعريف بأهمية التصنيفات الاقتصادية لأغراض نشر البيانات الإحصائية والمقارنة على المستويات الدولية. * التعرف على التغيرات التي طرأت على النسخ الجديدة من أدلة التجارة الدولية عام 2022. * اكتساب وتعزيز مهارات الربط بين التصنيفات المختلفة.
Description: In 2015, with the launch of the Sustainable Development Goals, the global community made a commitment to end all forms of violence against children by 2030. Although this draws much needed attention to the importance of preventing and responding to violence against children, the availability of comparable data remains limited, which was also confirmed by the recently adopted Guidance of the European Statisticians for the Improvement of Statistics on Children. In response, UNICEF has developed the international classification of violence against children (ICVAC) with inputs from more than 200 experts from national statistical offices, academia, and international organizations. The ICVAC was endorsed at the 54th session of the UN Statistical Commission as international statistical standard and was recommended for inclusion in the International Family of Classifications.
Description: The Standard International Energy Product Classification (SIEC) is the first international classification for energy products built on a set of internationally harmonised definitions of energy products. It was endorsed by the United Nations Statistical Commission in 2011 as part of the International Recommendations for Energy Statistics. SIEC aims to cover all products necessary to provide a comprehensive picture of the production, transformation and consumption of energy throughout an economy. The United Nations Statistical Commission (UNSC) at its 53rd session (2022) endorsed the proposal from the Committee of Experts on International Statistical Classifications (CEISC) to revise SIEC, aiming to address definitional and content changes that have been identified by users. Given the ongoing revision of the Central Product Classification (CPC), the CEISC proposed a concomitant revision of SIEC to ensure better harmonization between the classifications. For this purpose, a task team on the revision of SIEC (TT-SIEC) has been established, being composed of experts responsible for energy statistics, statistical classifications, the SEEA and other related areas from countries and relevant international and regional organizations. The first meeting served as an introduction among the members, discussed the Terms of Reference of the TT-SIEC, and proposed an initial list of issues to be discussed. The meeting counted 25 participants representing countries and international organizations. Within UNSD, the work is coordinated with the relevant substantive sections, namely the Business Statistics Section, the Energy Statistics Section and the Environmental Accounts Section.
Description: Classification tree algorithms are a convenient method to perform variable selection and obtain interpretable structures relating covariates and an outcome of interest. When fitting classification trees to survey data, it is common to ignore sampling weights as well other design characteristics such as stratification and clustering. However, unless the survey design is uninformative, there is a risk that the inference for the classification tree is incorrect. A particular application in which this is a concern is the construction of nonresponse adjustment cells, a key step in the development of survey weights. We propose an extension of the popular Chi-square Automatic Interaction Detector (CHAID) approach that accounts for the design by applying a Rao-Scott correction in its classification criterion. We discuss the statistical properties of the resulting algorithm under a design-based framework. We compare its performance to existing weighted and unweighted algorithms, and we illustrate the use of the method using data from the U.S. American Community Survey.
Topics:
Original webpage was deleted, archived version from the Internet Archive (not a UN service): Link
Description: For this Joint FAO and Global Network Webinar, FAO and UNSD experts will talk about Caliper - Statistical Classifications as Public Goods: The FAO approach to disseminating statistical classifications as user-friendly and interoperable resources. WHEN | Tuesday, 30 May 2023: 14:30-15:30 Rome time (check your time) To join, register here. Statistical classifications are the vocabularies that provide the "meaning" of statistical data. As such, they inform all activities related to data collection, analysis, comparison, and dissemination and, ultimately, they affect our knowledge, science and policy. In their talk, Caterina Caracciolo and Carola Fabi from FAO, and Ilaria Di Matteo from UNSD, will argue that given such a crucial role, statistical classifications should be treated as public goods - made available to users in a user-friendly manner, and to computer applications in a way that allows for timely and sound exchange of information. The speakers will present Caliper, FAO's dissemination platform for statistical classifications. Caliper aims at being a user-friendly tool for users, who can explore entire classifications, look up definitions and translations, and compare related classifications. Caliper also addresses data interoperability, by making classifications available in formats such that can be effectively reused in information systems. Caliper approach is based on open-source technologies.
Source: Eurostat (Data extracted on: 29 Nov 2022 )
[+] More
Organizer(s): Eurostat Icon-Institut
Description: The course should provide participants with a better understanding of the underlying principles and concepts of European and international economic and social classifications, their content and use.
Target Audience: Any statistician of a National Statistical Institute (including newcomers) dealing with any statistical domain and wishing to understand better the system of classifications used.
Description: UNSD organized a virtual meeting on the revision of the Classification of the Functions of Government (COFOG). The meeting was organized in response the request by the United Nations Statistical Commission at its fifty-third session in 2022 to revise COFOG and make an assessment of whether changes are required in the other classifications of expenditure according to purpose. The objective of the meeting was to develop a draft work programme and terms of reference of a task team on the revision of COFOG which will submitted to the UN Statistical Commission through the UN Committee of Experts on International Statistical Classifications. The meeting gathered some 25 experts on classification, government finance statistics, national accounts and environmental accounts from several countries (namely, Canada, Netherlands, New Zealand, UK, US) and international organizations such as Eurostat, FAO, IMF and OECD. UNSD experts from classification, national accounts and environmental accounts participated in the meeting. The revision of COFOG was very welcomed. Some of the main drivers identified for the revision of COFOG included addressing emerging data needs for policy making such as climate change, environmental expenditures, and digitalization. Participants also welcomed the efforts to bring together experts from different statistical domains in the revision process.
Description: Classification of the Functions of Government (COFOG) is a classification defined by the United Nations Statistics Division and adapted to the IMF government finance statistics (GFS) reporting framework. COFOG enables trends in government expenditure by function (e.g., defense or education) or policy purposes to be examined over time. The value of this is that expenditure by functions of government of different countries can be compared. Participants will gain an understanding of how the ten functions of government as described in the GFSM 2014 are classified, how to categorize expenditure data to generate a functional split will be explained and how it should reconcile with the economic classification of expenditure data used in the GFS. Participants should feel comfortable to present and discuss relevant data of their own country. Practical exercises with participants working in random groups will feature throughout the course enabling them to be able to appropriately categorize expenditure data to the correct functional categories. Focus will be on the function environmental protection and how this can be used in conjunction with other government data on climate change to see how governments are addressing the issue. In addition, applications of COFOG for reporting select UN Sustainable Development Goal (SDG) indicators will be discussed.
Description: The UN Committee of Experts on International Statistical Classifications is the central coordination body for the work on international statistical classifications that are the responsibility of the Statistics Division, and for the coordination and review of other international statistical classifications that are the responsibility of other international organizations and that have been proposed for adoption by the Statistical Commission. The meeting of the UNCEISC will take place at the Labouisse Hall, UNICEF House, New York from 25 to 28 October 2022. Background notes will be made available in advance of the meeting (approximately two weeks before the actual meeting), containing key questions for discussion during the meeting. Participants are asked to read the background notes in advance of the meeting. This will ensure a focused discussion during each session.
Description: As part of WHO ICD-11 webinar series, the Classifications and Terminologies Unit is organising a webinar on the 16th of May 2022 on: ''ICD-11 implementation strategy and country experiences'' Overview of ICD-11 Country experiences in ICD-11 implementation: * in morbidity coding; * in cause of death coding. Do's and Don'ts in implementing ICD-11
Source: Eurostat (Data extracted on: 30 Jan 2022 )
[+] More
Organizer(s): Eurostat Icon-Institut
Description: The course should provide participants with a better understanding of the underlying principles and concepts of European and international economic and social classifications, their content and use.
Target Audience: Any statistician of a National Statistical Institute (including newcomers) dealing with any statistical domain and wishing to understand better the system of classifications used.
Description: The course will introduce participants to the concepts that underpin the identification and correct sector classification of public sector entities, with particular focus on extrabudgetary units and state-owned enterprises. Participants will receive practical advice on how to apply the sector classification guidance in the Government Finance Statistics Manual 2014 (GFSM 2014), using a framework of standardized questions. Group exercises in a workshop environment will deepen understanding and build learner confidence in applying the framework and concepts, with the final section of the course requiring participants to apply the learning to examples in their own country before reconvening to discuss and share the insights gained. In addition to hands-on experience in the application of sector classification principles, participants will explore, at a high-level, the issues that it is important to consider when collecting and compiling data from entities that are outside of direct budgetary controls and reporting. However, the details of how to compile data for newly classified entities is beyond the scope of this course.
Source: Eurostat (Data extracted on: 21 Dec 2020 )
[+] More
Organizer(s): Eurostat Icon-Institut
Description: The course should provide participants with a better understanding of the underlying principles and concepts of European and international economic and social classifications, their content and use.
Target Audience: Any statistician of a National Statistical Institute (including newcomers) dealing with any statistical domain and wishing to understand better the system of classifications used. ESTP Trainings are open to non-ESS members if capacity allows after ESS needs are fulfilled.
Description: A virtual webinar that will give an overview of ICD-11 and the tools for implementation. The classifications and terminologies team will respond to questions in a Q & A session following the presentations.
Title in Arabic: التصنيفات الإحصائية الرسمية: المفاهيم الأساسية والتطبيقات
Organizer(s): AITRS
Description: تعتبر مكاتب الإحصاء الوطنية المنتج الأساسي لأهم البيانات الرسمية وإتاحتها لجميع المستخدمين وذلك طبقا للمناهج والمعايير والتصنيفات الإحصائية المتعارف عليها والمعتمدة من قبل الهيئات الدولية. وفي هذا الإطار تعتبر التصنيفات الإحصائية الرسمية الاقتصادية والاجتماعية إحدى أهم المعايير لجودة المنتج الإحصائي الرسمي وآلية فنية محورية لتنسيق البيانات الإحصائية على المستويين المحلي والدولي.وتلتزم الأجهزة الإحصائية في إطار احترام مواثيق القواعد المثلى لإنتاج الإحصائيات الرسمية باتخاذ الإجراءات اللازمة لضمان تطبيق المفاهيم والتعريفات والتصنيفات الموحدة باستمرار، من قبل الجهاز الإحصائي الوطني والمنتجين الآخرين للإحصائيات الرسمية وتسهر على توافق أنظمة التصنيفات الوطنية مع الأنظمة الدولية على المستوى التفصيلي.
Description: This event will present examples of the work that has been done to create interactive statistical classifications and an SDG taxonomy using innovative cross-referencing and navigation technologies and approaches.
Description: This regionalmeetingwas set to discuss the progress of the activityontheArabic Glossaries and SDG Metadata implemented under the umbrella of DA11 projectonSupporting ESCWA Member States in the Adoption and Implementation ofArabic Standards. The project aims to address the unavailability of unified standards for scientificArabic terms which has left a gap with significant hurdles in the collection, comparability, and usefulness of data across the full spectrum of development issues especially those produced from administrative records.Themeetingaimed to provide an overview of progress madeontheArabic glossaries and the SDG metadata, to discuss the challenges and opportunities in applying standards at the national level and make recommendations for adopting and using them to better plan and implement the second phase of this project. List of participants Presentation
Activity and Product Classifications: description, use and implementation
25 Nov 2020 – 04 Dec 2020
Source: Eurostat (Data extracted on: 17 Nov 2020 )
[+] More
Organizer(s): Eurostat Sogeti
Description: The course should provide participants with a better understanding of the underlying principles and concepts of European and international economic classifications, their differences and methods of harmonisation. The course should also provide participants with sound confidence for a current use of economic classification.
Target Audience: All staff responsible for the development and application of national activity and product classifications as well as for staff applying economic classifications in business registers or dealing with business statistics and National Accounts. ESTP Trainings are open to non-ESS members if capacity allows after ESS needs are fulfilled.
Description: In this session, the speakers will provide insights about the functionalities of Caliper, an experimental platform aimed at improving the availability and interoperability of statistical metadata, especially statistical classifications.
