What is it about?
National Statistical Institutes increasingly combine different ways of collecting survey data, such as face-to-face interviews, telephone interviews, and web questionnaires. This became especially important during the COVID-19 pandemic, when direct contact with respondents was often difficult. This review examines how statistical classification and survey weighting can help reduce problems created by mixed-mode data collection. Using Scopus and Web of Science, the study identified 289 research articles on mixed-mode surveys, classification, weighting, and measurement error. The findings show that mixed-mode surveys can provide a practical alternative or complement to traditional face-to-face interviewing, but careful classification of survey items and respondents is essential for controlling non-response bias and coverage errors.
Featured Image
Photo by Nguyen Dang Hoang Nhu on Unsplash
Why is it important?
Mixed-mode surveys can make official data collection more flexible, accessible, and resilient, but different collection methods may produce different response patterns and introduce systematic bias. This study highlights the importance of identifying which survey items and respondent groups are more sensitive to mode effects. Statistical classification and appropriate design weights can help National Statistical Institutes reduce non-response and coverage problems and improve the comparability and quality of official statistics. These methods are particularly important as statistical agencies increasingly combine digital and traditional survey channels.
Perspectives
The expansion of telephone and web-based surveys has made mixed-mode data collection increasingly important for official statistics. However, combining modes is not simply a technical change in how questionnaires are delivered; it can also influence who responds and how respondents interpret and answer questions. Our review suggests that mixed-mode survey design should therefore be accompanied by systematic classification of survey items and respondents, together with appropriate weighting methods. The objective is not to eliminate traditional face-to-face interviewing, but to build more flexible survey systems while preserving representativeness, comparability, and statistical quality.
Prof. Afshin Ashofteh
Universidade Nova de Lisboa
Read the Original
This page is a summary of: A Review on Official Survey Item Classification for Mixed-Mode Effects Adjustment, January 2023, Springer Science + Business Media,
DOI: 10.1007/978-3-031-09034-9_7.
You can read the full text:
Resources
Contributors
The following have contributed to this page
