Capturing Individuals' Uncertainties–On Establishing the Validity of an Interval-Valued Survey Response Mode

09/16/2020 ∙ by Zack Ellerby, et al. ∙ 0

Obtaining quantitative survey responses that are both accurate and informative is crucial to a wide range of fields (e.g. perceptual and categorical judgement, expert risk assessment, attitudinal measurement, consumer and public opinion research). Traditional and ubiquitous response formats such as Likert and Visual Analogue Scales require condensation of responses into discrete or point values-but sometimes a range of options may better represent the correct answer. In this paper, we propose an efficient interval-valued response mode, whereby responses are made by marking an ellipse along a continuous scale. We discuss its potential in the context of survey research, describing how this approach can capture and quantify valuable information arising from multiple sources of response uncertainty-which would be lost using conventional approaches–while preserving a high degree of response-efficiency. We then report a validation study, which utilizes our recently introduced open-source software (DECSYS) to administer an electronic interval-valued survey. This is designed to explore how interval-values reflect experimental manipulations of response (un)certainty across multiple contexts. Results consistently indicated that respondents used interval widths effectively-to communicate uncertainty (e.g. lack of available information), ambiguity (e.g. lack of clarity in question phrasing), and inherent variability in their responses. Subjective participant feedback was also positive. We present this as initial empirical evidence for the efficacy and value of interval-valued response capture. Interestingly, intervals also provided insight into respondents' reasoning about different types of uncertainties, suggesting a tendency to underestimate lack of available information relative to observable variability when making a stimulus judgement.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 20

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.