Date of this Version
In survey research, the use of decomposition can lead to pronounced reporting errors as seen by overreporting and overall reporting error. A total of 87 subjects answered either decomposed or undecomposed questions concerning telephone calls made by them while at work. The questionnaire conditions varied the length of the reference period (1 week or 6 months), and the type of call (local or long-distance). Decomposition conditions introduced either spatial or temporal cues. In all comparisons, decomposed questions increased over- reporting bias relative to undecomposed questions. In addition, undecomposed questions with a 1-week reference period led to increased overreporting bias in comparison to undecomposed/ 6-month questions. Results are consistent with a category split estimation model in which smaller categories are predicted to lead to overreporting, and larger categories to under- reporting. Decomposition is not recommended for gaining retrospective reports of non-distinctive, frequent events.