Inconsistency in the 11-point (0-10) Likert scale: evidence from subjective well-being survey

Abstract

Abstract In this paper, we verified an inconsistency of understanding in the 0 to 10 Likert Scales with a survey experiment. We recruited 121 college students at a public university in California and had them answer a hypothetical subjective well-being survey. The survey contains 23 happy or unhappy events, and the students are told to report how happy/unhappy they would feel if the event happened to them on 11-point Likert Scales. We found an inconsistent understanding in the responses when the expected value is around 7 to 8 on a 0 to 10 Likert scale. Our finding suggests that a scale of another length or a -5 to 5 scale can be used as an alternative to improve the data quality.