Summer School on Survey Statistics 2021 Speakers

Last modified by Maria Valaste on 2024/04/16 14:49

Home | Registration | Important DatesScientific Programme | Speakers | Instructions for Speakers | Sponsors | Committees | Contacts

Speakers

Keynote speakers

Speaker

Title

Abstract

Photo_ShuYang2.jpgPh.D., Associate professor of statistics,  Shu Yang (North Carolina State University, USA)Shu Yang is an associate professor of Statistics at NC State University. She received her Ph.D. in Applied Mathematics and Statistics from Iowa State University and postdoctoral training at Harvard T.H. Chan School of Public Health. Her primary research interest is causal inference and data integration, particularly with applications to comparative effectiveness research in health studies. She also works extensively on methods for missing data, spatial statistics, and sampling statistics. She has been Principal Investigator for several U.S. National Science Foundation and National Institute of Health research projects. 

Data integration: a new paradigm  for survey statistics

Finite population inference is a central goal in survey sampling. Probability sampling is the gold standard statistical approach to finite population inference. Challenges arise due to high costs and increasing non-response rates. Data integration provides a timely solution by leveraging multiple data sources to provide more robust and efficient inference than using any single data source alone. The technique for data integration varies depending on the types of samples and available information to be combined. This talk provides a systematic review of data integration techniques for combining probability and non-probability samples and for combining probability and big data samples. A wide range of integration methods will be covered such as calibration weighting, inverse probability weighting, mass imputation, and doubly robust methods. Finally, I will highlight important questions for future research.

Prof. Dr.  Piet Daas (Eindhoven University of Technology & Statistics Netherlands) image2021-5-28_16-7-8.png

Prof. Dr. Piet Daas is a senior-methodologist at Statistics Netherlands where he leads the research on Big Data. He is a professor by  special appointment on ‘Big Data in Official Statistics’ at the Eindhoven University of Technology where his work focuses on the development of Big Data methodology. Piet teaches Big Data (on-line) at Statistics Netherlands, the University of Utrecht, University of Maryland, and the University of Mannheim.

Identifying different types of companies via their website text

The internet and especially web pages are a very interesting source of data. It has very interesting potential applications such as providing novel insights on the activities of companies, to inform policy makers and also for official statistics, especially when performed at large scale. However, extracting relevant and reliable information from big data sources in a reproducible way is not an easy task. In this presentation results of Machine Learning based classifications of web sites texts are discussed in relation to the identification of innovative, platform economy and AI companies.

photo_Szymkowiak2.jpg

Associate Professor,  Deputy Director Marcin Szymkowiak, (Department of Statistics, Poznan University of Economics and Business;  Statistical Office in Poznan)Associate Professor at Department of Statistics, Poznan University of Economics and Business and  Deputy Director at Statistical Office in Poznan, with many years of experience in the field of statistical data analysis. He specializes in small area estimation, methods of dealing with nonresponse (imputation and calibration), survey sampling, statistical methods of data integration (probabilistic record linking, statistical matching), and multivariate data analysis. He has participated in many domestic and international projects in cooperation with the Central Statistical Office in Poland, the World Bank and Eurostat (for instance Eurarea, ESSnet on Small Area Estimation, MEETS, ESSnet on Data Integration, VIP Admin, Memobust, Improvement of EU censuses quality from 2021, Foreigners in the Polish regional labour market, Extension of the Labour Force Survey indicators of labour market and education).

Small area estimation in official statistics - past, present and future directions of applications

Small area estimation methodology (SAE) has been developed to produce reliable estimates of different characteristics of interest, such as means, counts, quantiles or ratios for domains for which only small samples are available. From that point of view SAE has become a topic of great importance due to the growing demand for reliable small area statistics. SAE methodology is used by different national statistical institutes in different areas, in particular to estimate quantities that are related to the labour market, agriculture or business statistics. It is also useful for mapping poverty. For instance, the World Bank has used SAE methodology to prepare poverty maps for tens countries all over the world. The main purpose of this presentation is to provide a review of the main applications in SAE methods, mainly in official statistics. Presentation will be based on earlier and present applications which serve as a necessary background for the new directions of the SAE development, including using big data sources as an example.

Invited lecturers in Russian

Speaker

Title

Abstract

Tetiana Ianevych (Taras Shevchenko National University of Kyiv, Ukraine)

Sample Surveys: Main Estimation Methods

Iryna Rozora (Taras Shevchenko National University of Kyiv, Ukraine)

Calibration Estimation for Nonresponse Bias Reduction

Tetiana Manzhos (Kyiv National Economic University, Ukraine)

Big Data and Sample Surveys: Problems of Use

Olga Vasylyk (National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”, Ukraine)

Estimation for Domains and Small Areas

Invited speakers

Speaker

Title

Abstract

Kaja Sõstra (Estonia)

SAE Methods for Developing the Digital Economy and Society Index (DESI) at local level

Tomas Rudys (Lithuania)

The use of alternative data sources at Statistics Lithuania

Signe Bāliņa (Latvia)

What is behind statistics?

 

Sylwia Filas-Przybył (Statistical Office in Poznań, Adam Mickiewicz University in Poznań) and Tomasz Klimanek (Statistical Office in Poznań, Poznań University of Economics and Business)

Income stratification of the urban population in Poland

Krista Lagus (University of Helsinki, Finland)

Open-ended questions in surveys: Exploring the possibilities of NLP and data science

 

Blaise Ngendangenzwa and Joel Tolsheden  (Statistics Sweden)

Machine Learning and Automatic Editing

Mykola Sydorov (Taras Shevchenko National University of Kyiv, Ukraine) and Oleksiy Sereda (Taras Shevchenko National University of Kyiv, Ukraine)

UniDOS online with LimeSurvey

Contributed papers

Speaker

Title

Abstract

Vilma Nekrašaitė-Liegė (Vilnius Gediminas technical University and Statistics Lithuania, Lithuania)

A COMPARISON OF URL FINDERS FOR ONLINE-BASED ENTERPRISE CHARACTERISTICS

Milda Šličkutė-Šeštokienė (Statistics Lithuania, Lithuania)

Register based census in Lithuania

Ieva Burakauskaitė (Statistics Lithuania, Lithuania) and Vilma Nekrašaitė-Liegė (Vilnius Gediminas technical University and Statistics Lithuania, Lithuania)

Selective Editing Using Contamination Model

Baiba Zukula (Central Statistical Bureau of Latvia, Latvia)

CAWI-mobile FOR HOUSEHOLD SURVEYS

Ruāna Pavasare (Central Statistical Bureau, Latvia)

Statistical Editing and Imputation of Missing values for the Population Census 2021 in Latvia

Ance Cerina (Central Statistical Bureau of Latvia, Latvia) and Zane Matveja (Central Statistical Bureau of Latvia, Latvia)

Statistical Disclosure Control for Census 2021

Jelena Voronova (Central statistical bureau of Latvia, Latvian University, Latvia)

OBSERVING NONRESPONSE BIAS AND OPTIMISING DATA COLLECTION STRATEGY FOR ADAPTIVE SAMPLE SURVEY DESIGN

Ulrich Rendtel, Andreas Neudecker and Lukas Fuchs

The display of Corona incidences in space and time

Liliāna Roze (Central Statistical Bureau of Latvia, Latvia)

Optimal identification of auxiliary variables in sample surveys to reduce nonresponse bias

Mārtiņš Liberts (Central Statistical Bureau of Latvia, Latvia)

Unequal Probability Sampling for the European Interview Health Survey in Latvia

Darja Goreva (Central StatisticalBureau of Latvia, Latvia) and Viktors Veretjanovs (Central StatisticalBureau of Latvia, Latvia)

ANALYSIS OF EU-SILC DATA DEPENDING ON MODES OF DATA COLLECTION IN LATVIA

Danute Krapavickaite

Highlights of the WSC 2021 in Survey Statistics

Yana Bondarenko

A Sequential Probability Ratio Test for Online Experiments

Andrius Čiginas

On design mean square error estimation for model-based small area estimators

Natalia Bokun

Enterprises Survey on Personnel Demand

Maria Valaste and Hanna Wass

Data Collection Mode and Nonresponse: Practical Experiences

Anastasiia Volkova

On the importance of conceptualization and operationalization in survey design: lessons from the Morally Debatable Behaviors scale

Sakovich N.

Consumer Prices Sample Surveys in Belarus / Выборочные обследования потребительских цен в Беларуси (Contributed paper for Russian Saturday)

Natalia Bokun

Labor Market Surveys in Belarus / Выборочные обследования на рынке труда в Беларуси (Contributed paper for Russian Saturday)

Sharilova Eugenia

Sample surveys in assessing the main determinants of fertility decline in the Republic of Belarus /  Выборочные обследования в оценке основных детерминантов снижения рождаемости в Республике Беларусь (Contributed paper for Russian Saturday)

Korolenok A.

PROBLEMS OF SURVEY OF UNPAID ACTIVITIES (Contributed paper for Russian Saturday)

Nataliya Pekarskaya

HOUSEHOLDS SURVEY TO MEASURE THE AGRICULTURAL ACTIVITY (Contributed paper for Russian Saturday)

Liudmila Soshnikava

Using logistic regression to analyze the results of statistical observations

---

Last update 13 September 2021