Projects / Programmes
Probability web panels in national statistics for persons and households
| Code |
Science |
Field |
Subfield |
| 5.03.00 |
Social sciences |
Sociology |
|
| Code |
Science |
Field |
| 5.04 |
Social Sciences |
Sociology |
Probability sampling, nonprobability sampling, web panels, web surveys, national probability surveys, accuracy of survey estimates, response quality, costs
Data for the last 5 years (citations for the last 10 years) on
April 26, 2024;
A3 for period
2018-2022
Data for ARIS tenders (
04.04.2019 – Programme tender,
archive
)
| Database |
Linked records |
Citations |
Pure citations |
Average pure citations |
| WoS |
54 |
1,320 |
1,253 |
23.2 |
| Scopus |
71 |
1,955 |
1,868 |
26.31 |
Researchers (10)
Organisations (1)
Abstract
Due to developments in information and communication technologies and the growing problems associated with traditional survey modes (i.e., increasing costs and decreasing cooperation), survey research is shifting to web-based surveys or mixed-mode surveys. In this context, web panels, where panel members agree in advance to regularly participate (e.g., monthly) in various web surveys for an incentive, present a very specific challenge. In the realm of business and opinion surveys of the general population, the web panels already dominate, especially the nonprobability web panel (i.e., access panels), where the probabilities of the units included in the panel are not known in advance. However, official statistics standards require probability surveys, in which the probabilities of the units potentially included in the panel are positive and known in advance for the entire population. Probability web panels have spread rapidly in recent years in academic research and in some areas of the public sector, but they have not yet gained acceptance in official statistics. Nevertheless, recent challenges in survey research caused by the COVID-19 pandemic, particularly the difficulties in conducting face-to-face interviews, have accelerated the process of considering the suitability of probability web panels also in official statistics. On the one hand, probability web panels reduce costs while retaining the principles of probability sampling; on the other hand, they omit the population that does not use the internet and provide lower response rates, at least when compared to face-to-face surveys (which, however, are not feasible in COVID-19 circumstances). In general, the literature reports that probability web panels are as successful as traditional probability surveys in terms of the quality of survey estimates and, notably, that they are more successful than nonprobability web panels. Against this background, the Statistical Office of the Republic of Slovenia is also confronted with the challenges of probability web panels, although—similar to other statistical offices—it does not yet use these panels in its general population surveys. The project will therefore test the potential of probability web panels comprised of the general population (i.e., persons and households) for the needs of official statistics. The objectives are as follows: 1.provide a comprehensive and up-to-date overview of the global state-of-the-art on the topic in the literature and of the related activities in the leading statistical offices;2.review the content of potential survey questions suitable for inclusion in such a panel in official statistics, and also consider potential synergies with other public sector stakeholders with relevant survey content and similar interests;3.conduct a pilot probability web panel to gain insight into survey costs and the quality of statistical estimates and to develop an integrated comparative approach for assessing the quality and costs; 4. conduct a comprehensive feasibility study for the establishment of a probability web panel for official statistics in Slovenia that discusses all related financial, methodological, legal and organizational aspects. The results will provide the stakeholders with new and up-to-date knowledge, including about the corresponding dilemmas. This information will also be the basis for competent decisions.The proposed research group is globally recognized in the field of web surveys. It has conducted pioneering research, published with major publishers and authored highly cited articles and a central monograph in this field. The group has excellent links to leading international researchers and has developed an open-source tool to support the web survey process (1KA). Nationally, the group has established annual professional events on web surveys. This proven track record ensures that the ambitious goals of the proposed project will be fully achieved.
