Measurement error when surveying issue positions: a MultiTrait MultiError approach

Abstract Voters’ issue preferences are key determinants of vote choice, making it essential to reduce measurement error in responses to issue questions in surveys. This study uses a MultiTrait MultiError approach to assess the data quality of issue questions by separating four sources of variation: trait, acquiescence, method, and random error. The questions generally achieved moderate data quality, with 76% on average representing valid variance. Random error made up the largest proportion of error (23%). Error due to method and acquiescence was small. We found that 5-point scales are generally better than 11-point scales, while answers by respondents with lower political sophistication achieved lower data quality. The findings indicate a need to focus on decreasing random error when studying issue positions.