Combining Data from Multiple Sources: Potential and Challenges of Data Linkages
The second webinar in the NCAER Seminar series on Data Collection Methodology organised by the NCAER National Data Innovation Centre was held virtually on June 24, 2021. The webinar is part of a series of thought-provoking discussions on research methodologies in which distinguished speakers in the field will share their views and one or more discussants will reflect on them from an Indian perspective. This talk was delivered by Frauke Kreuter, Professor of Statistics and Data Science for the Social Sciences and Humanities at the Ludwig-Maximilians-University of Munich (Germany) and Professor at the Joint Program in Survey Methodology at the University of Maryland. K.S. James from the International Institute for Population Sciences and Soumya Bhaduri from the Reserve Bank of India (RBI) were the discussants.
Combining data from different sources has become essential for social scientists and policy makers to take full advantage of the data deluge in an increasingly digitalised society. While we see many attempts at using a single approach (big data sources) with mixed results, the most exciting projects rely on a combination of different data, some of which are still collected through traditional modes. In this talk, Professor Kreuter highlighted a few approaches and provide a framework enabling researchers to think about creating new data products.
Professor Kreuter used several examples from economic research, with a specific focus on the IAB-SMART research project to discuss privacy issues and approaches deployed to create high-quality combined data sources (read more here). The IAB-SMART study uses innovative data sources, such as administrative records, surveys, and digital traces from smart phones, to measure the effects of long-term unemployment on social integration and social activity. Using the case study from different countries, the talk demonstrated how to handle potential coverage bias and biases due to non-response and measurement errors, while being cognisant of privacy norms.
Professor Kreuter co-founded and co-directs the Data Science Centers at the Universities of Maryland (USA) and Mannheim (Germany). She is an elected fellow of the American Statistical Association and the 2020 recipient of the Warren Mitofsky Innovators Award of the American Association for Public Opinion Research. Dr. Kreuter is the Founder of the International Program for Survey and Data Science, developed in response to the increasing demand from researchers and practitioners for the appropriate methods and right tools to face a changing data environment.
K.S. James is the Director and Senior Professor, International Institute for Population Sciences (IIPS), Mumbai. Prior to joining IIPS, he was Professor of Demography, Jawaharlal Nehru University, New Delhi. He works extensively on demographic changes with a focus on population and development, and ageing issues. He has published widely on the demographic transition and demographic dividend in India.
Soumya Bhadury is a macroeconomist currently working with the Strategic Research Unit at the RBI. His research interests include understanding macro-financial linkages in emerging markets. Before joining RBI, he worked as an economist at NCAER.
The first seminar was presented by Stanley Presser, Distinguished University Professor at the University of Maryland.
These two workshops focused on the banking sector and were held virtually . The fourth workshop addressed issues in the
The fifth workshop focused on
In mid-February this year, India was registering some 12,000 cases of covid-19 a day, fewer than many advanced countries in Europe. On April 23, India clocked some 333,000 new, positive cases, far higher than any other country at any time during this pandemic. The Economist notes that epidemiologists estimate the numbers could be 10 to 30 times higher, since testing is limited outside India’s cities. What happens in India will also matter for the world. Besides inexpensive vaccines, India may end up exporting dangerous, new SARS-CoV-2 strains.
Researchers at Yale University and the Stanford Medical School, along with IPA and local partners, have run a large, 350,000-person, randomized control trial in rural Bangladesh to evaluate ways to increase mask wearing in communities and to measure its impact on covid-19 transmission rates. The research identified the precise combination of mask design, distribution and promotion strategies that led to sustained increases in mask-wearing in the community. Their work answers questions such as, which interventions increase mask wearing the most? Do social nudges or incentives increase mask wearing? Does mask promotion inadvertently decrease social distancing? What kinds of masks work best? Urgent answers to these practical questions can help as India grapples with the mounting tragedy of its second wave.