Data and Analytics

DIME Analytics supports quality research processes across the DIME portfolio, offers public trainings, and develops tools for the global community of development researchers. DIME’s primary portfolio includes: the DIME Wiki, a one-stop shop for practical guidance and resources on impact evaluation research and the accompanying guidebook Data for Development Impact; ietoolkit and iefieldkit, Stata code packages featuring commands to routinize common impact evaluation tasks; and Manage Successful Impact Evaluations, our flagship training designed to improve the skills and knowledge of impact evaluation practitioners.


DIME Analytics creates tools that improve the quality of impact evaluation research for all. We take advantage of the concentration and scale of research at DIME to develop and test solutions to ensure high quality of data collection and research quality across our portfolio, and to make public training and tools available to the larger community of development researchers who might not have the same capabilities.  

Public Resources and Training

Manage Successful Impact Evaluations
DIME Analytics’ flagship training is a week-long annual course, open to the public (2018 course website). 

DIME Wiki
One-stop shop for impact evaluation research solutions.

Data for Development Impact
A new “user manual” for development data, complementing the DIME Wiki with a narrative approach. 

IE Summer School
A week-long course for graduate students in partnership with the University of Rwanda, covering the theoretical underpinnings of causal inference and offering hands-on tutorials on data analysis and survey design.

Stata training (Stata, R, GitHub, LaTeX)
Trainings for World Bank staff and government counterparts on common software for impact evaluation research. 

Reproducible Research

Code Review
Analytics leads two types of in-house code review to ensure all DIME outputs are fully reproducible and reflect best coding practices. Prior to publication, we review the analytical code and outputs for all DIME working papers. In addition, we facilitate monthly code exchanges among Research Assistants, to improve code while data work is ongoing. 

Version Control
Training and promotion of version control with Git. 

Reproducible Research Agenda
Regular events and trainings to promote reproducible research, in collaboration with the Berkeley Institute for Transparency in Social Science (BITSS) and other partners. 

Quality Assurance for Data Collection

SurveyCTO Platform
Management of the World Bank’s SurveyCTO platform for electronic data collection, and organized trainings on the tool.

Survey Review
Open source resources for data collection (e.g. checklists), and technical support to all DIME teams preparing for data collection. 

Measurement Conference
Annual conference on data and measurement innovations in partnership with the Center for Effective Global Action (CEGA). 

Open Source Research Tools

Take advantage of scope and scale of DIME research to develop and test econometric and technical solutions and develop public tools. 

ietoolkit: Suite of stata commands to routinize common tasks for primary data collection.

iefieldkit: Suite of Stata commands to routinize common tasks for data management and impact evaluation analysis. 

Stata Visual Library: Reproducible code for graphs and maps in an easy-to-browse format.

Stata codingblogpost & repo.


Experts

Florence Kondylis

Senior Economist

Maria Ruth Jones

Survey Specialist