Enumerator Education and Survey Responses: An Experimental Analysis

Last registered on January 20, 2022


Trial Information

General Information

Enumerator Education and Survey Responses: An Experimental Analysis
Initial registration date
January 11, 2022

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
January 20, 2022, 11:10 AM EST

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



Primary Investigator

Bucknell University

Other Primary Investigator(s)

Additional Trial Information

In development
Start date
End date
Secondary IDs
Prior work
This trial does not extend or rely on any prior RCTs.
Based on my prior research in West Africa, I have found variation in the data by enumerator education. The prior data shows a difference by enumerator education. Three of my male enumerators with various levels of education (advanced degree, university degree, elementary education) exhibit different responses to questions about wellbeing/happiness and identity. This paper will test several hypotheses based on the preexisting data to see if there is an effect. Each respondent will collect data as they have done on prior projects asking the same questions. They will reveal nothing explicitly about their education. Based on prior data the hypotheses are as follows: 1. Respondents will report lower personal level of wellbeing to highly educated enumerator compared to enumerator with lower level of education; 2. Respondents will rate enumerator’s level of wellbeing as higher when enumerator has high level of education compared to low level of education; 3. Respondent is more likely to report good things about the government (i.e., less corruption and more support for the current president) to the highly educated enumerator compared to the less educated enumerator. Results of this analysis carry important implications as major surveys of life in Africa and beyond use only highly educated enumerators. Doing so could be producing serious measurement error.
External Link(s)

Registration Citation

Doces, John. 2022. "Enumerator Education and Survey Responses: An Experimental Analysis." AEA RCT Registry. January 20. https://doi.org/10.1257/rct.8798-1.0
Experimental Details


Intervention Start Date
Intervention End Date

Primary Outcomes

Primary Outcomes (end points)
There will be four outcomes: respondent wellbeing; respondent evaluation of enumerator's wellbeing; degree of corruption in the police force; support for current president.
Primary Outcomes (explanation)

Secondary Outcomes

Secondary Outcomes (end points)
Secondary Outcomes (explanation)

Experimental Design

Experimental Design
All enumerators will sample in the same neighborhood of Abidjan. Each will follow a random walk and will use a coin flip to determine if they should ask a person to participate or not. Treatment will be randomly assigned by the random selection process.
Experimental Design Details
Randomization Method
Coin flip in the field.
Randomization Unit
Unit of randomization will be the individual within the same cluster.
Was the treatment clustered?

Experiment Characteristics

Sample size: planned number of clusters
There will be one cluster.
Sample size: planned number of observations
There will be a total of 150 observations, 50 per enumerator.
Sample size (or number of clusters) by treatment arms
50 observations by enumerator. The sample is not pre-selected.
Minimum detectable effect size for main outcomes (accounting for sample design and clustering)
Based on pre-existing research the effect size for the question on wellbeing shows an average level of reported wellbeing or the least educated enumerator at 6.2 and for the highest educate enumerator at 4.6. Based on this pre-existing data, a power analysis indicates each group will need 9 observations. We have funds to collect 50 observations per enumerator. Based on 50 observations per enumerator and assuming this effect size the power is 1.

Institutional Review Boards (IRBs)

IRB Name
Bucknell University Institutional Review Board
IRB Approval Date
IRB Approval Number


Post Trial Information

Study Withdrawal

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

Request Information


Is the intervention completed?
Data Collection Complete
Data Publication

Data Publication

Is public data available?

Program Files

Program Files
Reports, Papers & Other Materials

Relevant Paper(s)

Reports & Other Materials