Evaluation of a technology-aided instruction platform (Mindspark) in government schools in Rajasthan

Last registered on February 02, 2021


Trial Information

General Information

Evaluation of a technology-aided instruction platform (Mindspark) in government schools in Rajasthan
Initial registration date
April 28, 2020

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
April 28, 2020, 10:54 AM EDT

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

Last updated
February 02, 2021, 1:57 AM EST

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



Primary Investigator

University of California, San Diego

Other Primary Investigator(s)

PI Affiliation
Stockholm School of Economics

Additional Trial Information

On going
Start date
End date
Secondary IDs
The problem of low productivity of instruction in government schools in India (“the learning crisis”) is well documented. This study focuses on the increased use of technology in education, which is frequently proposed for improving this low productivity, but where the evidence base for the effectiveness of such policies remains mixed. We are evaluating the impact of a technology-led intervention (Mindspark), developed by Education Initiatives (EI) which provides personalized instruction to students in grades 1-8 which is individually customized to their level of achievement on student learning. We use a randomized control trial method to evaluate the impact of the program on classroom processes and student learning in Adarsh (consolidated) schools in four districts of Rajasthan over three academic years. This trial builds on promising results reported in Muralidharan, Singh and Ganimian (2019) in out-of-school settings in Delhi. The primary outcomes for this study will be student achievement, which will be measured directly using independently-designed student assessments in language and mathematics. In addition, we will be collecting data on program usage from the software as well as information on program implementation through direct observations and interviews with students and teachers.
External Link(s)

Registration Citation

Muralidharan, Karthik and Abhijeet Singh. 2021. "Evaluation of a technology-aided instruction platform (Mindspark) in government schools in Rajasthan." AEA RCT Registry. February 02. https://doi.org/10.1257/rct.2546-1.3
Experimental Details


The intervention in the schools is being implemented by EI in partnership with Government of Rajasthan. Mindspark program (developed by EI) provides personalized instruction using a software (reflecting over 10 years of product development by EI) to students which is individually customized to their level of achievement. The software aims to address several constraints:
• Adaptive instruction addresses the twin constraints of (a) the mismatch between curricular expectations and actual academic levels of students and (b) the wide spread of achievement levels in a single grade, which make delivery of any single curriculum difficult;
• Engaging interactive content, often game-based, aims to improve student attention;
• Real-time assessment and grading allows for immediate feedback to students and continuous diagnostics about student comprehension
• Careful analyses of patterns of student errors, enabled by “big data”, allow for precisely targeting content to clarify specific areas of misunderstanding.

Each class in grades 1-8 to will receive at least four class periods (two per subject of Hindi and Math) per school week in a laboratory class in the school. Each class period is of 40-minute duration.

Intervention Start Date
Intervention End Date

Primary Outcomes

Primary Outcomes (end points)
Student learning levels in Math and Hindi (local language)
Primary Outcomes (explanation)
We will administer independent tests of student achievement which will be designed to capture a broad range of ability. These will be scored using Item Response Theory methods.

Secondary Outcomes

Secondary Outcomes (end points)
Secondary Outcomes (explanation)

Experimental Design

Experimental Design
The study is based on a sample of 80 Adarsh schools across four districts in Rajasthan. The selection of these schools from the population of Adarsh schools in these four districts is based on certain defined criteria by the Education Initiatives based on the infrastructural readiness of the Adarsh schools to accept the Mindspark programs. 40 schools from this sample was randomly assigned to the receive the treatment. The remaining 40 schools are pure controls.
Experimental Design Details
Randomization Method
Randomization done in office on computer, using Stata
Randomization Unit
Was the treatment clustered?

Experiment Characteristics

Sample size: planned number of clusters
80 Schools
Sample size: planned number of observations
Total number of schools: 80 Total number of students in grades 1-8: 160*80= 12,080 (average of around 160 students per school) Total number of teachers in grades 1-8 teaching Math and Hindi: 7*80=560
Sample size (or number of clusters) by treatment arms
40 Treatment schools, 40 control schools
Minimum detectable effect size for main outcomes (accounting for sample design and clustering)

Institutional Review Boards (IRBs)

IRB Name
Institute of Financial Management and Research
IRB Approval Date
IRB Approval Number
IRB Name
University of California, San Diego
IRB Approval Date
IRB Approval Number
Analysis Plan

Analysis Plan Documents

Pre-analysis plan for endline data

MD5: 2ae0d6b6f58ce4c6d632be6067cc716a

SHA1: 732d3b2e09ebf96f6826c48a1270e41c9b0b9ba9

Uploaded At: February 02, 2021


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?
Intervention Completion Date
March 20, 2020, 12:00 +00:00
Data Collection Complete
Data Collection Completion Date
March 03, 2020, 12:00 +00:00
Final Sample Size: Number of Clusters (Unit of Randomization)
80 schools, 40 each in treatment and control
Was attrition correlated with treatment status?
Final Sample Size: Total Number of Observations
Final Sample Size (or Number of Clusters) by Treatment Arms
80 schools -- 40 each in treatment and control status
Data Publication

Data Publication

Is public data available?

Program Files

Program Files
Reports, Papers & Other Materials

Relevant Paper(s)

Reports & Other Materials