Maximising responses to discrete choice experiments: a randomised trial
Objective: To identify any differences in response and completion rates acrosstwo versions of a questionnaire, in order to determine the trade-off between apotentially higher response rate (from a short questionnaire) and a greater level ofinformation from each respondent (from a long questionnaire).Methods: This was a randomised trial to determine whether response rates and/orresults differ between questionnaires containing different numbers of choices: ashort version capable of estimating main effects only and a longer version capableof estimating two-way interactions, provided certain assumptions hold. Bestworstscaling was the form of discrete choice experimentation used. Data werecollected by post and analysed in terms of response rates, completion rates anddifferences in mean utilities.Results: Fifty-three percent of individuals approached agreed to take part. Fromthese, the response to the long questionnaire was 83.2% and the short questionnairewas 85.1% (difference 1.9%,95% CI -7.3,11.2; P = 0.68). The two versionsof the questionnaire provided similar inferences.Discussion/conclusion: This trial indicates that, in a healthcare setting, for thiscomplexity of questionnaire (i.e. four attributes and the best-worst scaling design),the use of 16 scenarios obtained very similar response rates to those obtainedusing half this number.
Year of publication: |
2001
|
---|---|
Authors: | Flynn Terry ; Coast Joanna ; Louviere Jordan ; Salisbury Chris ; Peters Tim |
Publisher: |
American Society for Testing and Materials |
Saved in:
freely available
Saved in favorites
Similar items by person
-
Flynn Terry, (2008)
-
Probabilistic Models of Set-Dependent and Attribute-Level Best-Worst Choice
Marley Anthony, (2008)
-
Economic Rationality, Risk Presentation, and Retirement Portfolio Choice.
Bateman, Hazel, (2011)
- More ...