WP176: The autocratic trust bias: Politically sensitive survey items and self-censorship

Welcome to the Afrobarometer publications section. For short, topical analyses, try our briefing papers (for survey rounds 1-5) and dispatches (starting with Round 6). For longer, more technical analyses of policy issues, check our policy papers. Our working papers are full-length analytical pieces developed for publication in academic journals or books. You can also search the entire publications database by keyword(s), language, country, and/or author.

Can't find a document?

As we work to upgrade our website, occasional technical issues may cause some links to break and some documents to be temporarily unavailable. If you're unable to find a specific document, please email snkomo@afrobarometer.org

Filter content by:

Working papers
Marcus Tannenberg

Because of a perceived risk of repressive action, some survey questions are likely sensitive in more autocratic countries while less so in more democratic countries. Yet survey data on potentially sensitive topics are frequently used in comparative research despite concerns about comparability.

In a novel approach to examining the comparability of politically sensitive questions, I employ a multilevel analysis with more than 140,000 respondents in 36 African countries to test for systematic bias when survey respondents believe (fear) that the government, rather than an independent research institute, has commissioned the survey.

The findings indicate that fear of the government induces a substantial and significant bias on questions regarding the citizen-state relationship in more autocratic countries, but not in more democratic countries. Moreover, respondents who think the government commissioned the survey do not answer differently on innocuous, apolitical questions than respondents who believe the survey to be independent, regardless of regime type. This has practical implications for the comparative use of survey data.