Skip to content

Commit

Permalink
Merge pull request #522 from worldbank/develop
Browse files Browse the repository at this point in the history
Merge for Arianna 2nd review
  • Loading branch information
kbjarkefur authored Sep 23, 2020
2 parents 13be50b + d6b15aa commit c26a6a8
Show file tree
Hide file tree
Showing 47 changed files with 7,043 additions and 4,355 deletions.
3 changes: 2 additions & 1 deletion .gitignore
Original file line number Diff line number Diff line change
Expand Up @@ -59,6 +59,7 @@
# More
!/**/*.sh
!/**/*.bib
!/diagrams/*.png

# R
!/**/*.R
Expand All @@ -78,7 +79,7 @@
!/**/*.md

# Unignore the pdf file for the io page
!/**/mkdocs/docs/bookpdf/Data-for-Development-Impact.pdf
!/**/mkdocs/docs/bookpdf/*.pdf

#######################
# Include some additional file formats in any output folder. You might have
Expand Down
6 changes: 3 additions & 3 deletions CONTRIBUTING.md
Original file line number Diff line number Diff line change
Expand Up @@ -11,17 +11,17 @@ While our preference is to receive feedback through GitHub you are always welcom

## Feedback through GitHub
If you notice any errors in text or if you need further clarification for any sentence/concept/section that you think is not
exhaustively dealt within the book, you can do so by creating an *issue*. You can read issues submitted by other users or create a new issue [here](https://github.com/worldbank/d4di/issues).
exhaustively dealt within the book, you can do so by creating an *issue*. You can read issues submitted by other users or create a new issue [here](https://github.com/worldbank/dime-data-handbook/issues).

For example, if you think the example the authors have used to explain a particular research design is too convoluted to understand,
For example, if you think the example the authors have used to explain a particular research design is too convoluted to understand,
creating an issue is useful for you to provide us the feedback that we should use a **simpler example** to explain the research design.
Please read already existing issues to check whether someone else has made the same suggestion or reported the same error
before creating a new issue.

### GitHub Issue Submission Format
For us to be able to search through the feedback we will organize all issues in a specific format. **If you do not know how to follow all steps in the bullet point below, then please feel free to post the issue anyways, but we will edit the issue so that it follows our format**.

1. Go to [the issues tab](https://github.com/worldbank/d4di/issues) on the D4DI repository.
1. Go to [the issues tab](https://github.com/worldbank/dime-data-handbook/issues) on the D4DI repository.
1. Search the already posted issues to see if the feedback you are about to give is already posted,
1. If your feedback has not already been brought up, please press the green *New Issue* button to post a new issue.
1. Write your title on the format **`Ch #: description`** where _#_ is the chapter number and _description_ is a **short** description of the issue, and apply the corresponding chapter label
Expand Down
24 changes: 11 additions & 13 deletions chapters/abbreviations.tex → auxiliary/abbreviations.tex
Original file line number Diff line number Diff line change
Expand Up @@ -4,26 +4,28 @@

\noindent\textbf{CAPI} -- Computer-Assisted Personal Interviewing

\noindent\textbf{CI} -- Confidence Interval

\noindent\textbf{DEC} -- Development Economics Group at the World Bank

\noindent\textbf{DD or DiD} -- Differences-in-Differences

\noindent\textbf{DGP} -- Data-Generating Process
\noindent\textbf{DIME} -- Development Impact Evaluation

\noindent\textbf{DIME} -- Development Impact Evaluations
\noindent\textbf{DOI} -- Digital object identifier

\noindent\textbf{FC} -- Field Coordinator
\noindent\textbf{eGAP} -- Evidence in Governance and Politics

\noindent\textbf{FE} -- Fixed Effects
\noindent\textbf{EU} -- European Union

\noindent\textbf{GDPR} -- Global Data Protection Regulation

\noindent\textbf{HFC} -- High-Frequency Checks

\noindent\textbf{IRB} -- Instituional Review Board
\noindent\textbf{IPA} -- Innovations for Poverty Action

\noindent\textbf{IRB} -- Institutional Review Board

\noindent\textbf{IV} -- Instrumental Variables

\noindent\textbf{JPAL} -- The Abdul Lateef Jameel Poverty Action Lab

\noindent\textbf{MDE} -- Minimum Detectable Effect

\noindent\textbf{NGO} -- Non-Governmental Organization
Expand All @@ -38,14 +40,10 @@

\noindent\textbf{PII} -- Personally-Identifying Information

\noindent\textbf{QA} -- Quality Assurance

\noindent\textbf{RA} -- Research Assistant

\noindent\textbf{RD} -- Regression Discontinuity

\noindent\textbf{RCT} -- Randomized Control Trial

\noindent\textbf{SSC} -- Statistical Software Components

\noindent\textbf{WBG} -- World Bank Group
43 changes: 32 additions & 11 deletions chapters/conclusion.tex → auxiliary/conclusion.tex
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
We hope you have enjoyed \textit{Data for Development Impact: The DIME Analytics Resource Guide}.
We hope you have enjoyed \textit{Development Research in Practice: The DIME Analytics Data Handbook}.
Our aim was to teach you to handle data more efficiently, effectively, and ethically.
We laid out a complete vision of the tasks of a modern researcher,
from planning a project's data governance to publishing code and data
Expand All @@ -8,18 +8,29 @@
as your work requires you to become progressively more familiar
with each of the topics included in the guide.

We started the book with a discussion of research as a public service:
one that requires you to be accountable to both research participants
and research consumers.
We then discussed the current research environment,
We started the book with a discussion of
credibility, transparency, and reproducibility in research:
an overarching idea that your work should always be
accessible and available to others, both within and outside your team.
We then discussed the current research work environment,
which necessitates cooperation with a diverse group of collaborators
using modern approaches to computing technology.
We outlined common research methods in impact evaluation,
with an eye toward structuring data work.
We outlined methods for planning your data work
and creating basic documentation for data,
so that multiple data sources can be linked without error
and so that you can map the structure of your data
to your research design.
We discussed how to implement reproducible routines for sampling and randomization,
and to analyze statistical power and use randomization inference.
We discussed data collection
and analysis methods,

We detailed modern data acquisition methods and frameworks,
including data licensing, data ownership,
electronic data collection, and data security.
We provided a detailed workflow for data cleaning and processing,
emphasizing tidy data, quality control, privacy protection, and documentation.
We discuss the creation of derived indicators and analysis outputs,
and give an overview of the workflow required to move these results
to publication -- no matter the format of your work --
as well as tools and practices for making this work publicly accessible.
Throughout, we emphasized that data work is a ``social process'',
involving multiple team members with different roles and technical abilities.
Expand All @@ -40,5 +51,15 @@
(or the PDF on your desktop)
and come back to it anytime you need more information.
We wish you all the best in your work
and will love to hear any input you have on ours!\sidenote{
You can share your comments and suggestion on this book through \url{https://worldbank.github.io/d4di}.}
and will love to hear any input you have on ours!
You can share your comments and suggestion on this book through
\url{https://worldbank.github.io/dime-data-handbook}.

\vspace{1cm}
\begin{fullwidth}
\begin{figure}
\centering
\includegraphics[width=1.5\linewidth]{diagrams/Conclusion}
\label{fig:conclusion}
\end{figure}
\end{fullwidth}
144 changes: 144 additions & 0 deletions auxiliary/dime-analytics-resources.tex
Original file line number Diff line number Diff line change
@@ -0,0 +1,144 @@

%Make each resoruce a paragraph
\newcommand{\resourcepar}{\vspace{.75\baselineskip}\noindent}

%------------------------------------------------

\begin{fullwidth}

The resources listed in this appendix
are mentioned elsewhere in the chapters of this book,
and this appendix includes them all
in one place for easy reference.
All these resources are made public
under generous open-source licenses.
This means that you are free to use, reuse, and adapt these resources
for any purpose as you see fit,
so long as you include an appropriate citation.

\end{fullwidth}

%------------------------------------------------

\section{Public Resources and Tools}

\textbf{DIME Wiki.\sidenote{
\url{https://dimewiki.worldbank.org}}}
One-stop shop for impact evaluation research solutions.
The DIME Wiki is a resource focused on
practical implementation guidelines rather than theory,
open to the public, easily searchable,
suitable for users of varying levels of expertise,
up-to-date with the latest technological advances
in electronic data collection,
and curated by a vibrant network of editors
with expertise in the field.

\resourcepar\textbf{Stata Visual Library.\sidenote{
\url{https://worldbank.github.io/Stata-IE-Visual-Library/}}}
A curated, easy-to-browse selection of graphs created in Stata.
Clicking on each graph reveals the source code,
to allow for easy replication.

\resourcepar\textbf{R Econ Visual Library.\sidenote{
\url{https://worldbank.github.io/r-econ-visual-library/}}}
A curated, easy-to-browse selection of graphs created in R.
Clicking on each graph reveals the source code,
to allow for easy replication.

\resourcepar\textbf{DIME Analytics Research Standards.\sidenote{
\url{https://github.com/worldbank/dime-standards}}}
A repository outlining DIME's public commitments to
research ethics, transparency, reproducibility,
data security and data publication,
along with supporting tools and resources.

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

\section{Flagship Courses}

\textbf{Manage Successful Impact Evaluations (MSIE).\sidenote{
\url{https://osf.io/h4d8y/}}}
DIME Analytics' flagship training is a week-long annual course,
held in person in Washington, D.C.
MSIE is intended to improve the skills and knowledge of
impact evaluation (IE) practitioners,
familiarizing them with critical issues in
IE implementation, recurring challenges,
and cutting-edge technologies.
The course consists of lectures and hands-on sessions.
Through small group discussions and interactive computer lab sessions,
participants work together to apply what they've learned
and have a first-hand opportunity to develop skills.
Hands-on sessions are offered in parallel tracks,
with different options based on software preferences and skill level.

\resourcepar\textbf{Manage Successful Impact Evaluation Surveys (MSIES).\sidenote{
\url{https://osf.io/resya/}}}
A fully virtual course,
in which participants learn the workflow for primary data collection.
The course covers best practices at all stages of the survey workflow,
from planning to piloting instruments
and monitoring data quality once fieldwork begins.
There is a strong focus throughout on research ethics and reproducible workflows.
The course uses a combination of virtual lectures,
case studies, readings, and hands-on exercises.

\resourcepar\textbf{Research Assistant Onboarding Course.\sidenote{
\url{https://osf.io/qtmdp}}}
This course is designed to familiarize Research Assistants and Research Analysts
with DIME's standards for data work.
By the end of the course's six sessions,
participants will have the tools and knowledge to
implement best practices for transparent and reproducible research.
The course will focus on how to set up a collaborative workflow for
code, datasets, and research outputs.
Most content is platform-independent and software-agnostic,
but participants are expected to be familiar with statistical software.

\resourcepar\textbf{Introduction to R for advanced Stata users\sidenote{
\url{https://osf.io/nj6bf}}}
This course is an introduction to the R programming language,
building upon knowledge of Stata.
The course focuses on common tasks in
development research, related to descriptive analysis,
data visualization, data processing, and geospatial data work.

\resourcepar\textbf{DIME Analytics Trainings.\sidenote{
\url{https://osf.io/wzjtk}}}
DIME Analytics' home on the Open Science Framework,
with links to materials for all past courses and technical trainings.

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

\section{Software tools and trainings}

\textbf{\texttt{ietoolkit}.\sidenote{
\url{https://github.com/worldbank/ietoolkit}}}
Suite of Stata commands to routinize common tasks for
data management and impact evaluation analysis.

\resourcepar\textbf{\texttt{iefieldkit}.\sidenote{
\url{https://github.com/worldbank/iefieldkit}}}
Suite of Stata commands to routinize
and document common tasks in primary data collection.

\resourcepar\textbf{DIME Analytics GitHub Trainings and Resources.\sidenote{
\url{https://github.com/worldbank/dime-github-trainings}}}
A GitHub repository containing all
the GitHub training materials and resources developed by DIME Analytics.
The trainings follow DIME's model for organizing research teams on GitHub,
and are designed for face-to-face delivery,
but materials are shared so that they may be used and adapted by others.

\resourcepar\textbf{DIME Analytics \LaTeX-training.\sidenote{
\url{https://github.com/worldbank/DIME-LaTeX-Templates}}}
A user-friendly guide to getting started with LaTeX.
Exercises provide opportunities to
practice creating appendices,
exporting tables from R or Stata to LaTeX,
and formatting tables in LaTeX.

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

\mainmatter
55 changes: 55 additions & 0 deletions auxiliary/notes.tex
Original file line number Diff line number Diff line change
@@ -0,0 +1,55 @@
This is a draft edition of
\textit{Development Research in Practice:
The DIME Analytics Data Handbook}.
We want to thank all the people who helped us get here, especially
Arianna Legovini, for her leadership at DIME, unending support of our work,
and detailed comments on this book; and
Florence Kondylis, for her leadership in founding and growing DIME Analytics
and supporting this project from the very first.
We also thank the following members
of DIME Analytics for their contributions
to the ideas in this book and their help organizing them:
Roshni Khincha, Avnish Singh, Radhika Kaul,
Mizuhiro Suzuki, Yifan Powers, and Maria Arnal Canudo.

Our graditude to the many people who read and offered feedback as the book took shape:
%Alphabetical by last
Stephanie Annijas,
Maria Camila Ayala Guerrero,
Thomas Escande,
Aram Gassama,
Steven Glover,
Nausheen Khan,
Michael Orevba,
Caio Piza,
Francesco Raffaelli,
Daniel Rogger,
Ankriti Singh,
Ravi Somani,
and Leonardo Viotti.
Although they number far too many to name individually,
we also thank all the members of DIME and its teams across all the years
for the innovative work they have done, the lessons learned,
and the team spirit that makes our work so fruitful and rewarding.

This version of the book has been revised since its release in June 2019
with feedback from readers and experts.
It contains most of the content we plan for the finished version.
This book is a living product that is written and maintained publicly.
The code and edit history are at:
\url{https://github.com/worldbank/dime-data-handbook}.
You can get a PDF copy at:
\url{https://worldbank.github.com/dime-data-handbook}.
The website includes updated instructions
for providing feedback, as well as notes on updates to the content.

Whether you work with DIME, the World Bank,
or another organization or university,
we ask that you read the contents of this book critically.
We welcome feedback and corrections to improve the book.
Please visit
\url{https://worldbank.github.com/dime-data-handbook/feedback}
to provide feedback.
You can also email us at \url{[email protected]},
and we will be very thankful.
We hope you enjoy \textit{Development Research in Practice}!
Loading

0 comments on commit c26a6a8

Please sign in to comment.