Login required to access the wiki. Please register to create your login credentials We apologize for any inconvenience this may cause, but please note that this step is necessary to protect your privacy and ensure a safer browsing experience. Thank you for your cooperation. Public access: GAMSO , GSBPM , GSIM |
News from the Groups | |||
---|---|---|---|
Blue-skies Thinking | Identifying Topics/Opportunities | CONTINIOUS | Project proposals: Following pitching at BSTN, the following 2022 project proposals where approved at the November HLG workshop (along with the extension of IPP project that was proposed by project team):
Activity proposals: In addition, the following activities were identified: - Digital Twins. Proposal available (BSTN) Community proposal: |
Network Data | IN PROGRESS | Work is ongoing. | |
Covid-19 Hotspot Joint Biosecurity Centre Platform | IN PROGRESS | This is still in the scoping phase, although recent meetings have been held to develop the basis for this work. | |
User Research for Official Statistics | IN PROGRESS | ||
Rapid survey systems | IN PROGRESS | ||
From experimentation to implementation in official statistics | IN PROGRESS | A Project Proposal 'Meta-Academy for the Modernization of Official Statistics' was prepared as a project proposal for 2022, that was approved at the November HLG workshop. The purpose of the meta-academy is to raise the standards of virtual learning on topics necessary for the modernization of statistics but are missing or inconsistent from academic, commercial or in-house offerings. The meta-academy project sets out to create a benchmark to better map existing initiatives and offerings in order to better coordinate efforts, reduce duplication and fill in training gaps. This project will facilitate sharing of skills strategies, as well as catalogues of contents and pedagogical artefacts, and more generally good practices and standards in that space, so that scopes for reuse or co-creation in learning capabilities can be more easily and more systematically spotted and leveraged by all National Statistical Offices (NSOs). | |
Microdata for understanding declining response rates | IN PROGRESS | Currently postponed: Has been identified as an element of the 2022 work programme. | |
Facebook survey covid19 related symptoms and behaviour | IN PROGRESS | On hold | |
Capabilities and Communication | Future of work, future workplace and future skills | COMPLETED | Last call of the Task Team was on 29 November. All three activity proposals for the next year were submitted to the Workshop and accepted. So the team need to find resources for all of them: (1) Reaching youths, (2) Job of the future and (3) Future of work toolkits. The team will consider if two first activities should be merged into one. Task Team will start working with finalizing activity proposal on toolkits, with populating wiki pages with the information. Afterwards the team will look into refining other two proposals and will start working around April 2022 depending on the resources available. Call for the new members for all HLG-MOS Groups will be sent out to the countries in January by the head of the HLG-MOS. Next call of the Task Team will be on 25 January 2022. |
Ethical leadership as part of culture evolution | COMPLETED | Last call of the Task Team was on 24 November. Activity proposal submitted to the Workshop on the Modernisation of Official Statistics was accepted, and group is starting to plan next steps of their work. For the next call it was agreed that it will be prepared first draft of the placemat/picture that links ethical activities to GAMSO and GSBPM and afterwards to add case studies from the countries. UNECE will prepare a list of all groups/teams that work with Ethics. Next call of the Task Team is on 19 January 2022. | |
Role of market research, digital marketing & communication strategies and tools in managing a crisis communication situation and in promoting public engagement in surveys | IN PROGRESS | Last call of the Task Team was on 2 December. Some final changes to the Guidelines are made, to be soon circulated to the Task Team members for their comments. Afterwards Statistics Canada will harmonize document and will add graphics. It was decided that use cases from the countries will only be posted on the wiki, and the reference to the wiki will be in original document. New wiki space was created for this purpose and will be populated with the relevant materials. When work on the guidelines and wiki with use cases is finalized, Task Team will start on scoping their activity proposal and deciding what they will start working on. Next call of the Task Team will be on 20 January 2022. | |
Strategic Communication Framework Publication | COMPLETED | ||
HRMT Workshop 2022 | IN PROGRESS | ||
Topic 6 | placeholder | ||
Other | |||
Supporting Standards | Linking GSBPM and GSIM | IN PROGRESS | The last remaining sub-process descriptions have been prepared and are currently being discussed by the group. The final report is yet to be fully updated, but the main bulk (Chapter 3) and introduction part (Chapter 1) are more or less ready. The implementation level examples have been updated based on what was agreed on the specification level. All the sub-processes are updated here on this information flow diagram https://statswiki.unece.org/display/GSBPM/Information+flow+within+GSBPM+using+GSIM |
Core Ontology for Official Statistics | IN PROGRESS | Work is progressing as scheduled. The expert review is now finished, the group received valuable feedback from the experts. One of the next steps is to check the feedback and update the deliverables/define solutions for the issues. This is included in the "Phase 2" of COOS for next year. You can find the COOS main document at https://linked-statistics.github.io/COOS/coos.html. It includes links to the formal vocabulary, the governance document and the URI policy. Next phase of the work will focus on development of use cases, operationalization & further development of COOS outputs. | |
Updating GSIM | IN PROGRESS | Work is progressing as scheduled. The Task Team has recently closed the issues associated with the Business Group. The task team will start the full revision process of GSIM from next year: the task team will be divided into sub-teams that will work on GSIM Groups in parallel and the new version will be shared for feedback. | |
GSBPM Task | IN PROGRESS | Work is progressing as scheduled. The Task Team has divided its work into 8 smaller groups for the 8 Phases of the GSBPM. The work of the task team will continue in 2022 with a planned closing in June 2022. | |
Application of GSBPM for Geospatial Information | COMPLETED | ||
CSPA | NOT STARTED | No success in finding a potential chair for the group yet. Need support from the Executive Board. | |
ModernStats World Workshop 2022 | IN PROGRESS | Members for the Organising Committee has been nominated from the Supporting Standards Group members and discussions on potential date for the workshop has started. Target period: first half of June - first half of July 2022 (3 days). | |
Other | The group discussed the activity proposals for 2022, in light of the conclusions of the workshop, made some minor changes in scoping and prioritized the proposals. The final planned activity for 2022 are: Continuation:
New activities:
Our group will also collaborate and coordinate work with the Statistical Data Governance Framework project and start an internal discussion on how CSDA is interrelated with other ModernStats models and can be reviewed considering recent developments. The generic revision policy (ModernStats Governance Guide) for the ModernStats models is available here: https://bit.ly/2XOrdhe. The Supporting Standards Group will consider it final by the end of the year and make it publicly available. | ||
Machine Learning 2021 | IN PROGRESS | Coding and classification was the most popular application area in this year’s research of ML applications. New application areas investigated included modelling and route optimization. One study highlighted the benefit that NSOs gain from allowing their ML projects to be replicated by other NSOs. | |
WS2 – From Valid Solution to Production | IN PROGRESS | The workstream explored issues related to how to make the operationalization of ML solutions smooth and efficient such as how to develop a user-friendly interface and how to build a data lake that data scientists can efficiently draw data from. It also produced a paper outlining typical steps and challenges that statistical organizations take from ML experiment to deployment. | |
COMPLETE | The group produced high-level guidance on ethical considerations that arise in ML projects to support analysts, researchers, data scientists, and statisticians. It has been published by the UK Statistics Authority (see link). | ||
WS4 – On The Quality of Training Data | IN PROGRESS | The workstream carried out a simulation study exploring how to identify the circumstances under which an ML model should be retrained in order to maintain the predictive power and quality of the model. It also held a discussion panel at the all-group meeting in October where different NSOs shared their experiences and approaches to the topic. | |
WS5 – On The Quality Framework for Statistical Algorithms | IN PROGRESS | A framework was developed to see how well ML performs compared to other methods. This year the framework was tested using a real NSO use case. It reaffirmed the importance of having a holistic view, with quality dimensions having different priority for different stakeholders at different stages of the production cycle. | |
Other | Update to UNECE HLG MOS EB meeting - November / December 2021 Overview The Group ended a successful year by presenting highlights of its research to the global official statistics community at its annual webinar on 19 November on the sidelines of the UNECE HLG MOS workshop. Over 279 attendees from 48 different countries for presentations of the group’s research highlights and discussion with national data science leads of the way forward for ML in official statistics involving data science leads from Canada, Sweden and the UK. A post-event survey showed a 96% satisfaction rate and that 74% of attendees were now interested in taking part in the ML Group activities next year Research and knowledge sharing. In the workstreams activity leads have been writing up their research results and preparing final reports. These are being published on the new public page for the 2021 activities here. The last all group meeting held at the end of October some interesting presentations including Supervised Text Classification with Leveled Homomorphic Encryption from Saeid Molladavoudi, Statistics Canada, and MLOps in the Australian Taxation Office, from James Beck, Australian Taxation Office. A discussion panel on model retraining saw representatives of different NSOs (US, UK, Norway, Canada) present their perspectives on the challenges and possible approaches to model retraining. Evaluation and strategy. The Coordination Team ran a survey evaluating the activities of the group in 2021 and seeking to understand priorities for next year. Feedback showed high levels of satisfaction with the group’s activities and the benefits of connecting with others to exchanging ideas, information and experience when many NSOs are still in the early stages of their machine learning journey. As one respondent commented “The project has created the opportunity to spread the knowledge of ML among other members of the institution, benefiting the institution as a whole.” The survey flagged interest in more training activities such as the Coffee and Coding sessions, and looking at the challenges of moving ML models into production. It also highlighted some obstacles to the group’s plans to expand next year, notably that many members found it difficult to contribute to activities in a sustained way due to the pressures of their day-to-day work commitments. ML 2022: The Team has developed detailed plans to deliver a bolder, bigger and more collaborative project next year. It will launch the next stage with a series of training sessions, presentations and workshops at the UN CEBD / UAE Big Data conference at Expo 202 in Dubai in January 2022. We will issue a call for proposals for activities next week and would encourage NSOs to promote the call and put forward their ideas for research and knowledge sharing activities they could contribute. |
- HLG-MOS, 29 January 2021, online
- Linking GSBPM and GSIM Sprint, 2-3 February 2021
- Expert Meeting on Statistical Data Collection, 27-30 September, online
- Expert Meeting on Dissemination and Communication of Statistics, 11-14 Oct, online
- HLG-MOS workshop on the Modernisation of Official Statistics, 15-16 November 2021, online
- Synthetic Data Webinar, 17 November 2021, online
- Input Privacy-Preservation Techniques Webinar, 18 November 2021, online
- Machine Learning Webinar, 19 November 2021, online
- Expert Meeting on Statistical Data Confidentiality, 1-3 Dec, Poznan, Poland