Copyright © 2024 National Laboratory for Social Innovation (TINLAB) All rights reserved
Return To TopThe research project “Simulation study, secondary analysis and implementation of international best-practices” at Eötvös Loránd University (2022-2023).
The increase in internet penetration and evolving technological possibilities have made online self-administered survey data collection easily available, with which, we can achieve a seemingly impressive sample size (i.e. a sufficiently large number of people respond to our survey). However, reliability and generalizability of the data is significantly lower than a probability sample (for example, a face-to-face survey). In Hungary, based on the current internet coverage, samples collected online lead to unreliable estimates in 80% of cases and are significantly biased when generalized to the entire Hungarian population. The reason for this is that in most of the research questions, there is a difference between the groups of the population that are online and those that are not. In recent years, a considerable part (40%) of social science research has been carried out with poor quality online samples, and the vast majority (70%) of online news articles report statistically low-quality data. In social sciences, it is essential to follow an appropriate data collection protocol, and to generalize from the data to the entire population only if strict conditions are met. Although the international literature deals intensively with the methodological foundations of renewable data collection techniques, similar protocols are not yet available in Hungary. However, statistical expertise, data collection experience and adequate in-depth data on the internal demographic distribution of the Hungarian population are needed to develop appropriate guidelines. Our research aims to address this problem/gap by taking the first steps towards the establishment of protocols.
The main result of the research is a guideline based on the demographic parameters of the Hungarian population, which helps social scientists to find the most appropriate research method and to design their data collection.
Blanka SZEITL, Assistant Lecturer (Department of Statistics, ELTE Faculty of Social Sciences)
E-mail
MTMT