x

Please fill out this short user survey of only 3 questions in order to help us improve the site. We appreciate your feedback!
Likert versus Slider
Last registered on September 14, 2020
View Trial History

Pre-Trial

Trial Information
General Information
Title
Likert versus Slider
RCT ID
AEARCTR-0006444
Initial registration date
September 14, 2020
Last updated
September 14, 2020 1:46 PM EDT
Location(s)

This section is unavailable to the public. Use the button below to request access to this information.

Request Information
Primary Investigator
Name
Yujung Hwang
Affiliation
Johns Hopkins University
Contact Primary Investigator
Other Primary Investigator(s)
PI Name
Huan Deng
PI Affiliation
Johns Hopkins University
Contact Investigator
Additional Trial Information
Status
In development
Start date
2020-09-14
End date
2020-12-31
Keywords
Behavior, Other
Additional Keywords
Likert, Slider, latent variable, survey format
JEL code(s)
C10, C30, C50, C81, C83
Secondary IDs
Abstract
We randomize different survey formats (Likert, Slider) to understand how the survey format affects the estimation of continuous latent variables, such as attitude and perception. One half of survey participants will respond to a questionnaire using Likert scale and another half will respond to a questionnaire using Slider. Using survey responses from two different formats, we will estimate the nonparametric densities of latent variables and will discuss which survey method can provide responses that are more aligned with standard identification assumptions in the measurement error literature.
External Link(s)
Registration Citation
Citation
Deng, Huan and Yujung Hwang. 2020. "Likert versus Slider." AEA RCT Registry. September 14. https://doi.org/10.1257/rct.6444-1.0.
Sponsors & Partners
Experimental Details
Interventions
Intervention(s)
We randomize survey formats between Likert and Slider.
Intervention Start Date
2020-09-14
Intervention End Date
2020-09-28
Primary Outcomes
Primary Outcomes (end points)
We have two primary sets of outcome variables.
The first set of outcome variables is about anti-Asian sentiments. The second set of outcome variables is about perception about racism in the US. We include one List randomization question to assess the degree of social desirability bias.
Primary Outcomes (explanation)
We collect multiple measurements for each set of outcome variables, not to cherry-pick the most responsive survey items later, but to apply nonparametric estimation techniques to estimate measurement errors. Having multiple measurements is one of the essential identifying assumptions.
The first set of outcome variables on anti-Asian sentiment is a shorter version of the realistic threat measure and prejudice measures used in Stephan et al. (1999). The second set of outcome variables on perception about racism in the US is measured by asking how much respondents agree to three statements. The statements are (1) whether a person who publicly claims to be a racist can maintain good social relationships with most people, (2) whether typical American citizens will tolerate racial bias to some degree, as long as it does not violate the law evidently, and (3) if a person refers to the novel corona virus as “China virus”, the person will face severe criticism.

Reference
Stephan, Walter G., Oscar Ybarra, and Guy Bachman. "Prejudice toward immigrants 1." Journal of Applied Social Psychology 29.11 (1999): 2221-2237.
Secondary Outcomes
Secondary Outcomes (end points)
Secondary Outcomes (explanation)
Experimental Design
Experimental Design
To screen out survey participants who pay little attention to the survey, we have inserted an attention check question just before starting to ask about sentiment and perception. In an attention check question, we ask respondents how they are currently feeling, but we tell them to check only “None of the above” option in the middle of the question. Survey participants who fail to pay attention to our message and thus choose any other choices will be screened out.
Experimental Design Details
Not available
Randomization Method
randomization is done using a randomizer in a Qualtrics program.
Randomization Unit
individual
Was the treatment clustered?
No
Experiment Characteristics
Sample size: planned number of clusters
1300 individuals
Sample size: planned number of observations
1300 individuals
Sample size (or number of clusters) by treatment arms
650 (we do 50:50 randomization).
Minimum detectable effect size for main outcomes (accounting for sample design and clustering)
Supporting Documents and Materials
IRB
INSTITUTIONAL REVIEW BOARDS (IRBs)
IRB Name
The Homewood Institutional Review Board (Johns Hopkins University)
IRB Approval Date
2020-08-20
IRB Approval Number
HIRB00011674
Analysis Plan