Increasing respondents' willingness to participate in questionnaire surveys

Last registered on October 17, 2023

View Trial History

Pre-Trial

Trial Information

General Information

Title

Increasing respondents' willingness to participate in questionnaire surveys

RCT ID

AEARCTR-0011804

Initial registration date

October 10, 2023

Initial registration date is when the trial was registered.

It corresponds to when the registration was submitted to the Registry to be reviewed for publication.

First published

October 17, 2023, 11:46 AM EDT

First published corresponds to when the trial was first made public on the Registry after being reviewed.

Locations

Country

Slovakia

Region

Primary Investigator

Name

Zuzana Brokesova

Affiliation

University of Economics in Bratislava

Contact Primary Investigator

Other Primary Investigator(s)

PI Name

Andrej Cupak

PI Affiliation

National Bank of Slovakia

Contact Investigator

PI Name

Sofie Waltl

PI Affiliation

University of Cambridge

Contact Investigator

PI Name

Judita Jurasekova Kucserova

PI Affiliation

National Bank of Slovakia

Contact Investigator

PI Name

Anna Strachotová

PI Affiliation

National Bank of Slovakia

Contact Investigator

PI Name

Boris Frankovic

PI Affiliation

Statistical Office of the Slovak Republic

Contact Investigator

Additional Trial Information

Status

In development

Start date

2023-10-12

End date

2024-01-31

Keywords

Behavior, Other

Additional Keywords

survey participation, incentives, higher socio-demographic groups

JEL code(s)

C93, D19, C81

Secondary IDs

Prior work

This trial does not extend or rely on any prior RCTs.

Abstract

Sample surveys are an effective tool for collecting microeconomic data on the population. Despite the many advantages of such data collection, it is often the case that selected groups of respondents systematically refuse to complete questionnaires. Previous research shows that this is particularly true for high-income groups and individuals with high social status. Such non-participation of important groups of individuals may lead to underestimates of income or wealth inequality. In the experiment, we aim to test whether the pre-announced provision of monetary gifts (such as a voucher and a silver collector's coin) can motivate otherwise hard-to-reach household groups to participate in the Household Finance and Consumption Survey (HFCS). The experiment will be conducted as part of the fifth wave of the HFCS survey, which the National Bank of Slovakia and the Statistical Office of the Slovak Republic plan to conduct in autumn 2023. The results of the experiment should be useful for the design of representative surveys, which should not miss high-income and wealthy household groups in their samples.

External Link(s)

Registration Citation

Citation

Brokesova, Zuzana et al. 2023. "Increasing respondents' willingness to participate in questionnaire surveys ." AEA RCT Registry. October 17. https://doi.org/10.1257/rct.11804-1.0

Sponsors & Partners

There is information in this trial unavailable to the public. Use the button below to request access.

Request Information

Experimental Details

Interventions

Intervention(s)

In the experiment, we will use a pre-announced provision of gifts (monetary and silver collector coin) for participation in the survey to motivate otherwise hard-to-reach household groups (higher socio-economic groups) to participate in the Household Finance and Consumption Survey (HFCS).

Intervention Start Date

2023-10-12

Intervention End Date

2024-01-31

Primary Outcomes

Primary Outcomes (end points)

participation in the HFCS survey in control and treatment groups, quality of the survey responses in control and testament group

Primary Outcomes (explanation)

participation in the HFCS survey in control and treatment groups will be measured as binary variable - respond/ do not respond

Secondary Outcomes

Secondary Outcomes (end points)

quality of the responses of participants in control and treatment groups and based on different socio-demographic characteristics

Secondary Outcomes (explanation)

quality of the survey responses in control and testament group will be measured by the number of non-responses questions, don't know answers and overal assessment of the survey respondents cooperation by interviewer (available as paradata)

Experimental Design

The experiment is based on a between-subjects design. The experiment will be conducted within the fifth wave (2023) of the HFCS survey in the Slovak Republic, where different incentives will be used to increase the willingness to participate in the survey among subjects from the high socio-economic group subpopulation.

Experimental Design Details

The experiment is based on a between-subjects design. The experiment will be conducted within the fifth wave (2023) of the HFCS survey in the Slovak Republic where subjects from the sub-population of high socio-economic group will be randomly assigned to the control and treatment groups. In the treatment group, the invitation letter will announce a reward for participation in the survey in the form of a silver collector euro coin, and the subject will be rewarded in case of participation.

Randomization Method

Randomisation will be ensured by the Slovak Statistical Office using random sampling algorithms.

Randomization Unit

The randomisation unit will be a household in the sub-population of high socio-economic group identified ex ante from the Slovak Population and Housing Census 2021, based on the estimated value of the dwelling and the occupation of the main person living in the dwelling.

Was the treatment clustered?

Experiment Characteristics

Sample size: planned number of clusters

400 households

Sample size: planned number of observations

400 households

Sample size (or number of clusters) by treatment arms

200 households control group, 200 households in treatment group

Minimum detectable effect size for main outcomes (accounting for sample design and clustering)

Based on the power analysis calculations, our samples provide us medium effect size of intervention in comparison to control group with more than 91% power for treatment effect. We use G*Power for power calculations.

Supporting Documents and Materials

IRB