|
Field
Last Published
|
Before
September 07, 2024 11:13 PM
|
After
September 30, 2024 05:15 PM
|
|
Field
Intervention Start Date
|
Before
June 03, 2024
|
After
October 01, 2024
|
|
Field
Experimental Design (Public)
|
Before
We recruit 300 loan underwriters/officers and other participants to make loan application decisions.
|
After
We recruit 150 loan underwriters/officers, and other participants to make loan application decisions.
|
|
Field
Planned Number of Clusters
|
Before
300 individuals.
|
After
150 loan underwriters.
|
|
Field
Planned Number of Observations
|
Before
We will aim to recruit 300 subjects. We will filter out subjects in our analysis based on attention and time checks.
|
After
We will aim to recruit 150 subjects. We will filter out subjects in our analysis based on attention and time checks.
|
|
Field
Sample size (or number of clusters) by treatment arms
|
Before
300 in each arm. Each subject will see every treatment arm in randomised order.
|
After
150 in each arm. Each subject will see every treatment arm in randomised order.
|
|
Field
Power calculation: Minimum Detectable Effect Size for Main Outcomes
|
Before
|
After
See PAP.
|
|
Field
Intervention (Hidden)
|
Before
In a cross-randomised design, we vary: (i) the type of AI signal that is shown {binary, probability, none}, with sub-treatments varying the thresholds at which the binary signals are shown, and (ii) whether or not participants are put through "loan underwriter training". [we omit this latter treatment for those who are already experienced loan underwriters].
We also vary at a question-level (i) whether the AI signal or real loan application is shown first, and (ii) whether the human posterior is elicited after seeing just the loan application.
|
After
In a cross-randomised design, we vary the type of AI signal that is shown {binary, probability, none}, with sub-treatments varying the thresholds at which the binary signals are shown, and (ii) potentially, whether or not participants are put through "loan underwriter training". [we omit this latter treatment for those who are already experienced loan underwriters].
We also vary at a question-level (i) whether the AI signal or real loan application is shown first, and (ii) whether the human posterior is elicited after seeing just the loan application.
See the pre-analysis plan for more info.
|