Impact of the level of aggregation on response accuracy in surveys of behavioral frequency
β Scribed by Michael Y. Hu; Rex S. Toh; Eunkyu Lee
- Publisher
- Springer US
- Year
- 1996
- Tongue
- English
- Weight
- 1007 KB
- Volume
- 7
- Category
- Article
- ISSN
- 0923-0645
No coin nor oath required. For personal study only.
β¦ Synopsis
Through observations
of AT&T data and the results of two of our own studies, we discovered interesting asymmetrical effects of the level of aggregation of the question on the response accuracy in surveys of behavioral frequency. We find that disaggregating a question to a lower, less comfortable level of aggregation creates greater uncertainty, leading to larger absolute errors in survey responses. However, if a question is asked at a higher less comfortable level, the majority of respondents escape by splitting questions down to the natural level, thereby avoiding greater uncertainty and thus responding more accurately. We argue that for greater accuracy in surveys, one should identify the natural level of aggregation at which a question should be posed. But when in doubt, it is better to ask a question at a higher level of aggregation because of possible escapability downward.
π SIMILAR VOLUMES
## Abstract In this study the influence of topic involvement on mailβsurvey response rate and speed was experimentally investigated. The results show that response rates for topics that are generally considered as high involvement were higher than for topics that are generally considered as low inv
## Abstract In this article, we discuss the accuracy of behavioral models in simulating the intermodulation distortion (IMD) of microwave GaNβbased highβpower amplifiers in the presence of strong electrothermal (ET) feedback. Exploiting an accurate selfβconsistent ET model derived from measurements
In social and psychological research, respondents are often asked to report the frequency of a behaviour by checking the appropriate alternative from a list of response categories provided to them. Previous research indicated that respondents extract comparison information from the range of the resp
This article evaluates two alternative ways to execute the sampling of modulated data for large-signal behavioral modeling. We show that the nonlinear metric domain uniform sampling outperforms the time-domain uniform approach, and examine how the level of improvement depends on the number of sample