An Algorithmic Approach to Reducing Gender Discrimination: Evidence from a Large-Scale Experiment on Tracking Decisions

Last registered on January 08, 2026
View Trial History

Pre-Trial

Trial Information

General Information

Title
An Algorithmic Approach to Reducing Gender Discrimination: Evidence from a Large-Scale Experiment on Tracking Decisions
RCT ID
AEARCTR-0015384
Initial registration date
February 13, 2025

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
February 19, 2025, 9:29 AM EST

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

Last updated
January 08, 2026, 11:24 AM EST

Last updated is the most recent time when changes to the trial's registration were published.

Locations

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

Request Information

Primary Investigator

Name
Francesca Miserocchi
Affiliation
Contact Primary Investigator

Other Primary Investigator(s)

PI Name
Michela Carlana
PI Affiliation
Harvard Kennedy School
PI Name
Will Dobbie
PI Affiliation
Harvard Kennedy School
PI Name
Eleonora Patacchini
PI Affiliation
Cornell University
PI Name
Francesca Miserocchi
PI Affiliation
Contact Investigator

Additional Trial Information

Status
On going
Start date
2024-03-01
End date
2027-02-01
Keywords
Education, Gender, Labor
Additional Keywords
Gender, bias, teachers, track choice
JEL code(s)
I24, J16, D90
Secondary IDs
This trial does not extend or rely on any prior RCTs.
Prior work
This trial does not extend or rely on any prior RCTs.
Abstract
We study how to equalize students’ educational opportunities in a tracked high school system. We will use a randomized control trial in nearly 370 Italian middle schools to test two conceptually different ways to close gender gaps in high school track recommendations. To help teachers predict future performance, our first treatment provides teachers with a simple algorithmic recommendation that indicates whether students are likely to excel in the more rigorous scientific high school tracks. To address behavioral biases and awareness issues, our second treatment provides teachers with real-time feedback on the diversity of their track recommendations compared to an algorithmic benchmark, which they can then adjust before communicating their recommendations to students. We hypothesize that the first intervention will lead to fairer track recommendations if teacher biases are driven by inaccurate mental models of how individual students will perform in high school. Meanwhile, the second intervention will lead to fairer recommendations if teachers are best able to correct behavioral biases when considering the aggregate diversity of their track recommendations.
External Link(s)

Registration Citation

Citation
Carlana, Michela et al. 2026. "An Algorithmic Approach to Reducing Gender Discrimination: Evidence from a Large-Scale Experiment on Tracking Decisions." AEA RCT Registry. January 08. https://doi.org/10.1257/rct.15384-2.0
Sponsors & Partners
Experimental Details

Interventions

Intervention(s)
Intervention Start Date
2024-11-04
Intervention End Date
2025-12-19

Primary Outcomes

Primary Outcomes (end points)
The primary outcome will include:
(1) Administrative outcomes on the gender gap in the teachers' scientific track recommendations, for baseline high-achievers.
Primary Outcomes (explanation)

Secondary Outcomes

Secondary Outcomes (end points)
The secondary outcomes will include:
(1) Administrative outcomes on the gender gap in the students' track enrollment decisions, for baseline high-achievers.
(2) Administrative outcomes on the gender gaps in the teachers' scientific track recommendations and students' track enrollment decisions, for the general population of eighth graders.
(3) Administrative outcomes on the proportion of baseline high-achievers recommended to and enrolled in the scientific track, compared to baseline low-achievers, both in aggregate and by gender.
(4) Administrative outcomes on students' academic performance in high school, conditional on scientific track enrollment, both in aggregate and by gender.
(5) Data collected from a teacher questionnaire on teachers' beliefs about the gender gaps in their own track recommendations and their students' track enrollment decisions.
(6) Data collected from a teacher questionnaire on scientific track recommendations for hypothetical students' profiles with randomized genders.
Secondary Outcomes (explanation)

Experimental Design

Experimental Design
Information intervention with teachers
Experimental Design Details
Not available
Randomization Method
Randomization was done in an office by a computer.
Randomization Unit
The unit of randomization is the school. When teachers report teaching in multiple participating middle school buildings, these buildings were treated as a single school to prevent exposure to multiple treatments. Schools were then randomly assigned to the control group or to one of three treatment groups, with equal probability (25% each).
Was the treatment clustered?
Yes

Experiment Characteristics

Sample size: planned number of clusters
Around 368 schools
Sample size: planned number of observations
Our estimation sample consists of 8th-grade students in treatment-eligible classes within the 368 randomized schools. We expect approximately 39,600 8th-grade students to be in treatment-eligible classes. Furthermore, we will assess spillover effects by comparing the gender gaps in track recommendation and track choice using administrative outcomes of 8th-grade students in ineligible classes in treated and control schools. We expect approximately 19,000 8th-grade students to be in ineligible classes in treated or control schools.
Sample size (or number of clusters) by treatment arms
The schools will be randomized into the control group or one of three treatment groups, with 25% probability each.
Minimum detectable effect size for main outcomes (accounting for sample design and clustering)
Considering an ICC of 0.07, approximately 368 schools, and around 108 students per school in treatment-eligible classes (about 32 high-achieving students per school), the minimum detectable effect (MDE) for the gender interaction among high achievers is 7.5 percentage points, corresponding to approximately 0.16 standard deviations, assuming mean recommendation rates of 55% for high-achieving boys and 34% for high-achieving girls. The MDE for the average treatment effect on all students in treatment-eligible classes is around 4.5 percentage points, or 0.12 standard deviations. We expect to achieve higher power once we control for teacher characteristics (from surveys) and rich baseline information on students (from INVALSI administrative and survey data).
Supporting Documents and Materials
IRB

Institutional Review Boards (IRBs)

IRB Name
Harvard
IRB Approval Date
2024-10-01
IRB Approval Number
IRB24-1047
Analysis Plan