Remi Prual

Quality Expert - Estonia
‍

Remi Prual has been involved in the enhancement of the quality of official statistics for more than 20 years via numerous projects and activities. He was the Quality Manager and Head of General Department in Statistics Estonia (in between 2004-2017). He has been a Board Member of the Estonian Association for Quality for two consecutive periods. Remi belonged to the ESS Quality in Statistics WG, also to ESS Steering Committee on Quality and task forces on metadata standards, quality reporting, fine tuning of QAF, EU CWPS presidency team etc. Currently he is a ESS peer reviewer, management consultant, strategic advisor, trainer and expert with dedicated focus on valuation of data, metadata, statistics, information and knowledge. Remi is certified as an expert for ISO9001, EFQM, CAF, ITIL, LEAN and several other quality management related standards and approaches. He holds Masters in Information Sciences and also in Information Management.

‍

Course Description:

The course provides useful, both practical and theoretical advice on how to successfully manage the quality and implement well-known quality management approaches in public data valuation organisations such as coordinators of the national statistical systems and other national authorities involved in the production of the official statistics.

‍

Participants will be expected to actively engage, and there will be opportunity for interactions both with the facilitators and other participants. For example, group works will be used to ignite lively discussions and energise innovative thinking.

‍

The course will enhance participants' knowledge about quality management in official statistics, related quality concepts, ESS quality criteria, the ESS Common Quality Framework, quality management models and methods used to monitor, assess, communicate and improve quality of official statistics.
‍

Suggested reading:

European Statistics Code of Practice https://ec.europa.eu/eurostat/web/quality ESS Quality Assurance Framework https://ec.europa.eu/eurostat/web/quality

Generic Statistical Business Process Model (GSBPM) https://statswiki.unece.org/display/GSBPM

‍

Main goals:

The objective is to demonstrate and explain how quality management approaches can be used to guarantee the quality and efficiency by rational design of the official statistics production systems and related capabilities. Common Quality Framework of the European Statistical System (ESS), related quality concepts and quality criteria, European Statistics Code of Practice and other commonly accepted and widely used quality methods and tools will be covered during the course.

‍

Target Audience:

The course is addressed to employees of organisations involved in the production of the official statistics.

‍

Knowledge and experiences in quality management and production of statistics would be very useful for active participation in group works and discussions.

‍

To maximise interaction, the number of participants for the training will be limited.

‍

Laptop:

No

‍

Maximum no. of participants:

40

Pedro Campos

Statistics Portugal; FEP-UP
‍

Pedro Campos is currently Director of the Unit of Methodology of the Department of Methodology and Information Systems, at Statistics Portugal.

‍

Pedro has PhD in Business Sciences from the University of Porto (2008) and is Associate Professor at the Faculty of Economics of the University of Porto where he teaches courses in the areas of Data Analysis, Data Mining and Information Systems in various study cycles. Pedro is Deputy-Director of the International Statistical Literacy Project, where he plays international roles in promoting statistical literacy. He is also a member of LIAAD (Laboratory of Artificial Intelligence and Decision Analysis) at INESC TEC).

‍

Miguel Godinho de Matos (Invited speaker)

CATÓLICA-Lisbon

‍

Miguel Godinho de Matos is Full Professor of Information Systems and Management at Católica Lisbon School of Business & Economics. He also has a courtesy visiting research scholar affiliation at the Heinz College from Carnegie Mellon University.

‍

Miguel received both a Ph.D. and an M.Sc. in Engineering and Public Policy from the Carnegie Mellon University, and M.Sc. and a B.Sc. in Computer Engineering from the Technical University of Lisbon.

‍

Miguel’s research interests focus on studying how digitization changes consumer behavior and firms' product distribution strategies. In particular, Miguel has studied the impact of digitization on creative industries’ outcomes and has several research papers on the analysis of social networks and peer influence on consumer behavior. Miguel's work has been published in top journals such as Management Science, Management Information Systems Quarterly, Information Systems Research, Marketing Science, and the Journal of Management Information Systems.

‍

Miguel is an Associate Editor of Management Information Systems Quarterly since January 2020.

In 2019 Miguel won two early career award distinctions from the Informations Systems Society and the Association of Information System, respectively.

‍

Course Description:

The course will explore the convergence of traditional statistical methods with cutting-edge AI techniques and promote a comprehensive understanding of official statistics' fundamental principles, data collection, and processing, and learn how AI is revolutionizing data analysis, prediction, and decision-making. Through case studies, participants will delve into AI-driven applications in official statistics, such as predictive modelling, natural language processing (NLP), and image recognition. We will also explore the ethical dimensions of AI, including privacy preservation and bias mitigation. By the end of the course, participants will be equipped with the knowledge and skills to harness the power of AI to enhance the accuracy, timeliness, and relevance of official statistics, making informed policy and governance decisions in an AI-driven world.

‍

Main goals:

The goal of this short-course is to discover the transformative potential of Artificial Intelligence (AI) in the world of official statistics.

‍

Target Audience:

Experts dealing with the production of official statistics in all fields

‍

Laptop:

Yes (R software installed)

‍

Maximum no. of participants:

35

Thomas Schulz

Swiss Federal Statistical Office; Head of Publishing and Dissemination

‍

Already early in his career dedicated to cartography, visualisation and statistics, Thomas holds a Master in Cartography from the Karlsruhe University of Applied Sciences (D) and later graduated with his doctoral thesis and a PhD about the role, history and function of «Statistical Atlases» from Dresden University of Technology (D). During his studies, he came into contact with the Swiss Federal Statistical Office in Neuchâtel www.statistics.admin.ch, where he completed several internships and finally wrote his Masters’ thesis about innovative statistical mapping solutions. For almost 25 years since then, Thomas Schulz has been working at the office in various positions: coordinating technical projects for the International Service, as scientific staff in the statistical production, as head of the Cartography and Visualisation unit and for the last 7 years as the current head of the Publishing & Dissemination section. He has already published ten atlases and collaborated on others. With his expertise in statistical data visualisations, he has participated with contributions in many conferences and published two popular books with innovative data visualisation, e.g. for the UNWDF in Bern, 2021. In his private time, Thomas is highly active in the International Cartographic Association ICA www.icaci.org, serving as its Secretary-General and Treasurer since 2019.

‍

Course Description:

As we can all see, today, more and more statistical data is offered to a wide range of users in the form of visualisations. They are the medium of the moment in dissemination, effectively generating quickly comprehensible and clear information from large sets of numbers for a normally broad target audience. They can be used and distributed in almost all channels and media - from classic publications to websites and social media. But how to create good and effective visualisations in the context of a flood of data, tools and visualisation options? Where to start and how to best perform? The course aims to answer this question and present a framework that gives producers in public statistics concrete guidelines and processes to visualise complex data in a modern, attractive way for their clients (not for statisticians!).

‍

Starting from a basic knowledge of the nature of data that can be visualised in statistics, different visualisation options, the basic graphical variables and components and the available structuring options, best practices will be shown on the basis of supporting elements such as a chart chooser, process schemas or visualisation guidelines in order to arrive at the right and good visualisation for each case. Also, aspects of barrier reduced visualisations are shown. The focus of the course is thus on imparting profound knowledge in the methods of data visualisation – for all kinds of visualisations, including charts, maps and infographics. It is aimed at specialists who carry out this task in the context of statistical dissemination. Eventhough an overview of applicable technologies is shown in the course, it is not about the concrete application of or introduction into a specific tool.

‍

Main goals:

Providing participants with a better understanding of transforming statistical data into effective, data-based, open, timely, and user-friendly information objects. How to make complex data understandable with a visual object, incl. storytelling.

‍

Know the toolbox that helps to choose the right kind of visualisation, tools and frameworks adapted to produce effective visualisation, and best practices with guidelines and processes. Sensitivity to accessible visualisations and special target groups.

‍

Target Audience:

The course is addressed to employees of organisations involved in the production of the official statistics. Ideally, staff working in the area of dissemination and with basic knowledge and practical experiences in data visualisation.

‍

In order to maximise interaction, the number of participants for the training will be limited.

‍

Sound command of English is taken for granted. Participants should be able to make short interventions and to actively participate in discussions

‍

Laptop:

Yes

‍

Maximum no. of participants:

25

Sofia Rodrigues

Statistics Portugal

‍

Sofia Rodrigues, with a degree in Management, is the Director of the Administrative and Business Data Unit at the Data Collection and Management Department of Statistics Portugal (Instituto Nacional de Estatística - INE). Throughout her professional career at INE, she has worked in various statistical areas, including National Accounts, Planning, Business Registers, and Business Statistics. Since 2019, she has been responsible for managing the team for both collecting and analysing data from companies and institutions through online surveys, and collecting, analysing, and optimizing the use of administrative and other data, particularly in support of official statistics production.

‍

David Leite

Paris School of Economics

‍

David Leite is a researcher and PhD candidate at the Paris School of Economics. He holds a Master in Econometrics from University of Lisbon and a Master in Analysis and Policy in Economics from the Paris School of Economics and the École des Hautes Études en Sciences Sociales (EHESS). His research focus at empirical public economics using statistical methods applied to administrative data. His previous positions include the OECD Economics Department, the cabinet of the Portuguese Finance Minister of the XXI Government and the Portuguese Central Bank.

‍

Jaime Montaña

Católica-Lisbon & Dauphine University

‍

Jaime is a postdoctoral researcher at Católica Lisbon School of Business & Economics. He is currently visiting Dauphine University. He holds a joint Ph.D. in Economics from the Paris School of Economics and Turin University. Prior to his doctoral studies, Jaime earned a M.Sc. from the Paris School of Economics and a Bachelor's degree in Economics from Universidad del Rosario. He has taught statistics and econometrics at the bachelor's and master's levels at various universities such as Sciences Po, Paris School of Economics, Sorbonne, and Católica Lisbon.  Jaime has experience from both academic and professional settings. He previously worked for the Colombian Ministry of Labor and has collaborated with international organizations and government agencies such as the International Organization for Migration, the Inter-American Development Bank, and Bancoldex. Jaime's research focuses on applied economics, particularly labor economics. He leverages large administrative datasets and nontraditional data sources (job postings) to analyze and understand labor market phenomena.

‍

Course Description:

The availability and the use of administrative data is increasing for both research and production of official statistics. This trend brings advantages and poses new challenges.

‍

From an organizational point of view, the challenge is to adapt the organization, and therefore its culture, to strengthen the capacity for data management and analysis of data other than surveys. The creation of a dedicated unit that centrally cleans, evaluates, processes and improves administrative data is therefore crucial, in order to deliver consolidated and improved databases for all different users, internal and external. Additionally, the goal is also to implement the same quality procedures that are already put in place for surveys, namely, the creation of detailed metadata, definition of service level agreements and production of dashboards with major insights.

‍

From a methodological point of view, one of the pressing challenges of the use of administrative data is how to reconcile household surveys with administrative data, namely for the estimation of the income and wealth distributions. As evidenced by studies based on the tax administrative data, household surveys often fail to capture the top tail of income and wealth distributions, while administrative tax data usually fails to capture the bottom. Yet to date there is no consensus on how to best reconcile both sources of information, given the multiple biases at play.

‍

Based on frontier research in this field, namely the work developed at the World Income Lab, we intent to illustrate the methodologies to combine administrative data and survey data with applications to the estimation of the income and wealth distribution in very different settings, so that the course can target an audience with a wide range of needs. In addition, there will be also a practical activity aimed at familiarising the participants with the implementation of the methodologies to reconcile administrative data with surveys taught at the course using statistical software R and Stata.

‍

Main goals:

The main purpose of this course is to present the state-of-art of the methodologies to combine administrative data and survey data with applications to the estimation of the income and wealth distribution.

‍

Target Audience:

Anyone working on administrative or private data or desiring to use that type of data for their work. May include analysts, subject matter experts, researchers or other staff that wants to know more about the subject. The participant needs no prior technical experience.

‍

Laptop:

Yes (R and STATA softwares installed)

‍

Maximum no. of participants:

40