Difference between revisions of "DataWork Folder"

Jump to: navigation, search
 
(49 intermediate revisions by 3 users not shown)
Line 1: Line 1:
A well-organized data folder reduces the risk for many types of errors. At DIME, we have a standardized folder structure. Some projects have special folder requirements and only use the folder set up as a starting point, but many resources created by DIME are easier to take advantage of if this template is followed. It takes a lot of work to reorganize a project folder, so we strongly recommend that projects follow our standard from the beginning. A poorly set up folder will have inefficiency consequences and increases the risk of errors over several years.
The DataWork folder is a structured, standardized data folder that increases project efficiency and reduces the risk of error. The DataWork folder houses all files related to a project’s data, including data files; questionnaires; data collection documentation; code for sampling, treatment assignment, and [[Data Analysis | analysis]]; analysis output; and survey, monitoring,  [[Administrative and Monitoring Data | administrative]], and secondary data. DIME strongly recommends using the DataWork folder from the beginning of the project and throughout its duration.  
 
We have published a command called [[iefolder]] in our package [[Stata_Coding_Practices#ietoolkit|ietoolkit]] that we have published on SSC. [[iefolder]] sets up the recommended folder structure described in this article for you.


== Read First ==
== Read First ==
* Do not set up these folders manually. [[iefolder]] is a Stata command that easily sets up and updates this folder structure for you.
* Use the <code>[[iefolder]]</code> Stata command to easily set up and update the DataWork folder.
 
*Many DIME resources are easier to take advantage of when the DataWork folder is used.
== Where should the DataWork folder be created? ==
*Use the DataWork folder from the beginning of the project: reorganizing a project folder is time-consuming and cumbersome.  
[[File:FolderBox.png |thumb|350px|Image 1. Example of where the DataWork folder is location in relation to Box/DropBox folders. (Click to enlarge.)]]
*Even if your project has special structural requirements, use the DataWork folder as a starting point.
 
== Creating the DataWork Folder ==
Most project folders are shared across the project teams using a DropBox, Box, or something similar. In this folder, there are different folders for project budget, government communications, etc. The '''DataWork''' folder is assumed to be one of them.
[[File:FolderBox.png |thumb|350px|Image 1. Example of where the DataWork folder is in relation to Box/DropBox folders. (Click to enlarge.)]]
 
See Image 1 on the right with an example of a Box/DropBox folder with three project folders. All three projects have a similar sub-folder structure, but in the image only one of the projects sub-folder structure is shown. The '''DataWork''' folder is highlighted with a red circle.
 
Anything related to the data of a project has a designated location inside this folder. This includes data-files, sampling and treatment assignment code, questionnaires, data collection documentation, analysis code, analysis output etc. This includes data collected by ourselves, both regular survey rounds and monitor data, and also includes other sources of data such as admin data or secondary data.


== Inside the DataWork folder ==
The DataWork folder is easily set up via the Stata command <code>[[iefolder]]</code>, which is part of the package <code>[[Stata_Coding_Practices#ietoolkit|ietoolkit]]</code>.
[[File:FolderDataWork.png |thumb|300px|Image 2. Example of a DataWork folder. (Click to enlarge.)]]


Inside the '''DataWork''' folder there should only be folders and one file that help navigating those folders. The folder structure below is a template that we recommend for all projects, although we understand that some projects have special requirements and therefore will only use this as starting point. Everything described here is easily set up using the Stata command [[iefolder]].
The DataWork folder should be housed within the project folder, which contains a variety of other sub-folders (i.e. project budget and government communications). The DataWork folder and the broader project folder should be shared across project teams via [https://www.box.com Box], [https://www.dropbox.com/ Dropbox], or a similar platform. Image 1 shows a DataWork folder housed within a project folder.


The ''DataWork'' folder should have a folder called ''Encrypted Data''. This folder create a branch in the ''DataWork'' folder that can easily be encrypted using an encryption software like boxcryptor. Note that while iefolder creates a folder called ''Encrypted Data'' when you set up the ''DataWork'' in the first place, iefolder does not encrypt it.
== Contents ==
[[File:Datawork.png |thumb|300px|Image 2. Example of a DataWork folder. (Click to enlarge.)]]


After the project folder is set up initially, there are two types of folder to be added; [[DataWork_Folder#Survey_Round|Survey Rounds]] and [[DataWork_Folder#MasterData|Master Data Sets]]. A survey round can be more than just baseline, endline etc. It can also be data collecting for monitoring purposes, admin data collection or any other source of data used in the project. A project need one master data set for each [[Unit of Observation|unit of observation]] used in the project. When adding a round or another unit of obsrevation, folders are creaetd both inside the encrypted branch of the ''DataWork'' folder and outside it.
The DataWork folder contains a [[Master Do-files|master do-file]], Survey Round folders, a Survey Encrypted Data folder, and a Master Data folder. It may also contain additional documentation (i.e. readme) to help users navigate its contents.  


In addition to the folders described above there is also a Project_MasterDofile inside the '''DataWork''' folder (example master dofile [ https://github.com/worldbank/DIMEwiki/blob/master/Topics/Master_Data_Set/stringMergeWithMasterDataSets.do]). This file has three purposes. The first two are described in detail in the article for [[Master Do-files]], but are describe in short below:
=== Master Do-File ===
*The first reason is that it possible to run all code related to a project by running only one dofile. This is incredible important for replicability.
*The second purpose is to set up globals with folder paths that enables dynamic file paths that in turn allows multiple users run the same code, it shortens the file paths as well as making it possible to move files and folders with minimal updates to the code.


The third purpose is that this file is the main map to the '''DataWork''' folder. Since all code can be run from this file, and since all outputs are (indirectly) created by this file, this file is the starting point to find where any do-file, data set or output is located in the '''DataWork''' folder. Another examples of files that help with the navigation of the folder could be a Word document or a PDF describing how to navigate the sub-folders. Such files are not included in our folder template, but may sometimes be a good addition. However, those files needs to be updated in parallel which often does not happen even if that is the intention.
The project [[Master Do-files|master do-file]] runs all other project do-files from cleaning to final analysis. It also sets up dynamic file paths so that multiple users can work from the same project folder shared via, for example, Dropbox or Box. This ensures that everyone gets the same results.  


===Survey Round===
If you are new to a project folder, always start by finding the master do-file: it serves as a map of all files in the DataWork folder.
--------


===Survey Rounds===
[[File:FolderSurveyRound.png |thumb|300px|Image 3. Example of a Survey Round folder. (Click to enlarge.)]]
[[File:FolderSurveyRound.png |thumb|300px|Image 3. Example of a Survey Round folder. (Click to enlarge.)]]


Baselines, Follow Up Surveys, Midlines, Endlines are all examples of a Survey Round. This is the data that we in Impact Evaluations will test if it changes over time and if that change is significantly different between treatment and control. In contrast, the information in master data sets, like the ID assigned by us, whether you were sampled for baseline, whether you are selected for treatment or control are all examples of information that is time invariant and will remain the same over the course of the project. Monitor data might change over time, for example in a impact evaluation running over many years one observation might not take up the treatment the first year but might do so the next year.
Each [[DataWork Survey Round | Survey Round]] folder contains a master do file specific to its data source, in addition to the following folders: [[DataWork Survey Round#DataSets Folder|DataSets]], [[DataWork Survey Round#Dofiles Folder|Dofiles]], [[DataWork Survey Round#Outputs Folder|Outputs]], [[DataWork Survey Round#Documentation Folder|Documentation]], and [[DataWork Survey Round#Questionnaire Folder|Questionnaire]]. While the folders listed here are <code>[[iefolder]]</code>, you can also create more folders that are unique to your project.
 
Each survey round should have it's own sub-folder inside the '''DataWork''' folder. For example - Inside the main data folder, you can have sub-folders like baseline, follow up 1, follow up 2, midline, endline, etc. See image 3 for an example. When you create a survey round folder using the command [[iefolder]] all sub-folders and sub-sub-folders described below will be created for you and all your master dofiles will be updated or created accordingly.
 
Inside each Survey Round folder you will find a master do file for that survey round as well as the following folders [[DataWork Survey Round#DataSets Folder|DataSets]], [[DataWork Survey Round#Dofiles Folder|Dofiles]], [[DataWork Survey Round#Outputs Folder|Outputs]], [[DataWork Survey Round#Documentation Folder|Documentation]], and [[DataWork Survey Round#Questionnaire Folder|Questionnaire]].


See [[DataWork Survey Round]] for more details if any of the bullet points is not perfectly clear to you.
====What Requires a Survey Round Folder?====
Each source of data (i.e. baseline, follow-up, midline, endline, [[Administrative and Monitoring Data | administrative]], secondary) should have its own Survey Round folder within the DataWork folder. If the data source is collected continuously (i.e. administrative or secondary data as macro data over time), then it requires only one Survey Round folder. However, if the data source is collected in stages (i.e. baseline and endline data), then it requires one Survey Round folder for each stage.  


==== Multiple Units of Observation ====
If you have multiple [[Unit of Observation|units of observation]] in a given data source, each unit of observation for each data source requires its own Survey Round folder. For example, if the units of observation during baseline data collection are students, teachers and schools, then baseline data requires three Survey Round folders: ''baseline_students'', ''baseline_teachers'' and ''baseline_schools''. If you choose, these folders may be nested within a parent ''Baseline'' folder. <code>[[iefolder]]</code> gives you the option of doing this by creating a ''Baseline'' subfolder and then creating Survey Round folders within it.


If you have multiple [[Unit of Observation|units of observation]] in a survey round for example farmers and villages, or students, teachers and schools, then you should create a survey round folder for each unit of observations. For example, you would end up with one survey round folder called ''baseline_students'', one called ''baseline_teachers'' and one called ''baseline_schools''.
Note that each Survey Round needs to have a unique name across the project when using <code>[[iefolder]]</code>.


==== Sampling and Treatment Assignment ====
=== Survey Encrypted Data ===


Sampling and Treatment Assignment folders have intentionally been left out from the survey round folders. Separate folders for those tasks has been created in the master data set folder as we strongly recommend that sampling and treatment assignment is done directly from the master data sets.
Whenever you create either a new survey round or new unit of observation with <code>[[iefolder]]</code>, the command creates a partner folder for each survey round or unit of observation in the Survey Encrypted Data folder. Any identifying or sensitive data should be saved in the Survey Encrypted Data folder; the folder’s contents can easily be [[Encryption | encrypted]] using software like [https://www.veracrypt.fr/en/Home.html VeraCrypt], we previously recommended Boxcryptor but securoty issues were found in that software so we strongly recommend against using Boxcryptor. . Note that while <code>[[iefolder]]</code> creates the Survey Encrypted Data folder, it does not encrypt it.  


==== MonitorData ====
Consider, for example, a master dataset. The version with identifying information should be stored in the Survey Encrypted Data folder. The version [[De-identification | without identifying information]] should be stored in the Master Data folder. The latter version is quicker to access and can often be shared outside the research team.
 
Monitor data is data collected to understand the implementation of the assigned treatment in the field. Typical survey round data helps us understand any changes in outcome variables that the treatment and other factors have caused during the duration of our project, and monitor data helps us the treatment its self. For example, who actually received the treatment and was the treatment carried out according to the research design. Monitor data helps us understand what is usually referred to as [https://en.wikipedia.org/wiki/Internal_validity internal validity]. For the purpose of data folder organisation you can treat them the same way.
 
Since the purpose of survey round data and monitor data is slightly different, we recommend you keep the different types of data in different folders. Sometimes survey round data and monitor data are collected in the same data collection, and then it is not feasible to keep them separated. For example, if an enumerator visited a training for the respondents in the treatment group at the time of a midline survey and recorded attendance then that data should be kept separate from the survey round data. But if the respondents were asked in the a survey round survey if the respondent attended the training, then it not always worth the effort to go through the work of separating the monitor data from the survey data. If they are collected at the same time but in separate data collections, then the folders should be kept separately.
 
==== Admin Data ====
 
Admin data is data that have been collected for other purposes but has been shared with the research team. It can be used both in the way survey round data is used in the analysis or as the way monitoring data can be used. For example, if the outcome variable the research team is trying to evaluate is measured in some other way then that is admin data we can use to measure change in outcome data. One example would be standardized test scores. We can often use the internal data our implementation partner uses as monitor data. That is one example when admin data is monitoring data. There are also many cases when the same admin data set is used for both purposes.
 
Create a new survey round folder for admin data sets.
 
===MasterData===
--------


=== Master Data ===
[[File:FolderMasterData.png |thumb|300px|Image 4. Example of a Master Data Set folder. (Click to enlarge.)]]
[[File:FolderMasterData.png |thumb|300px|Image 4. Example of a Master Data Set folder. (Click to enlarge.)]]
[[Master_Data_Set#Master_Data_Set_Folder|Master Data Sets]] is the best tool to avoid errors related to using multiple sources of data for one project. All impact evaluations use multiple sources of data. Multiple survey rounds are in this sense different sources of data. A census made before a data collection is a different source of data. Monitoring data and admin data combined with any other data are other examples. Master data sets should therefore be used in all projects and [[iefolder]] therefore creates the main folders for Master Data Sets by default when the ''DataWork'' folder is created.
There are two locations where Master Data Sets are stored. One location inside the encrypted brach of the ''DataWork'' folder. Here you can save a Master Data Set with identifying information. In not other data set than here will we have both the ID variable as well as identifying information. This is the key between the IDs that we use and the identity of the respondents. If this data set is shared publicly, then the identity of all of our respondents are revealed.


The Master Data Sets is a listing of all observations we have ever encountered in relation to this project (not just the observations we sampled). In this listing, we keep identifying information and the unique ID that we have assigned. We also keep time invariant information required at multiple stages of the research work. Examples are dummy for being sampled in baseline, categorical variable for treatment arm, dummy for correctly receiving the assign treatment arm etc. See the [[Master_Data_Set|Master Data Sets]] article for more details.
The Master Data folder stores information about all the observations for which data is collected, including observations both in and out of the sample. As it is sometimes necessary to identify observations outside of the sample, the Master Data folder should also include, for example,
*Census observations not sampled for the project, or
*Observations encountered in monitoring activities but not in the sample.  
In the Master Data folder, we can also track any time-invariant information relevant to the project (i.e. assigned treatment status, treatment uptake, identifying information, dummy for being sampled). The datasets where we store this information are called [[Master Data Set |master datasets]].  


Master Data Sets is more than just a folder. It is a methodology for internal research validity in a multi data set environment. See the [[Master Data Set|Master Data Sets]] article for information both on how the master data set folder should be organized but also how it should be used for research quality purposes. One important motto is that if you do any merge (string or numeric) where the variable you merge on is not a proper ID variable, then one of the data set you are merging should always be a master data set.
A project needs one master dataset for each [[Unit of Observation|unit of observation]] used in the project (i.e. households, students, teachers, firms).  


==== Sampling and Treatment Assignment ====
==== Sampling and Treatment Assignment ====


The master data sets folder should also include all activities that is best practice to do directly on the main listing of all observations. The two best examples of such tasks in the context of Impact Evaluation is sampling and treatment assignment. This should never be done directly on census data or baseline data etc. When we have census data we use that data for sampling, but the point here is that we always want to match the census data to the master data and check that it makes sense in relation to whatever data we have there already. After that quality control step, we can sample directly from the master data set knowing that the sample we randomize will make sense in relation to other data sources.
The Master Data folder should also include all activities performed on the main listing of all observations (i.e. sampling and treatment assignment). This should never be done directly on census data or baseline data etc. While census data will be used for sampling, it is important to match the census data to the master data and check that it makes sense in relation to whatever data exists there already. After that quality control step, sample directly from the master data set, knowing that the randomized sample will make sense in relation to other data sources.


== Back to Parent ==
== Back to Parent ==
This article is part of the topic [[Data Management]]
This article is part of the topic [[Data Management]]


[[Category: Data Management ]]
== Additional Resources ==
*DIME Analytics' guidelines on [https://github.com/worldbank/DIME-Resources/blob/master/welcome-iefolder.pdf iefolder]
*DIME Analytics’ [https://github.com/worldbank/DIME-Resources/blob/master/stata1-3-cleaning.pdf Data Management and Cleaning]
*DIME Analytics’ [https://github.com/worldbank/DIME-Resources/blob/master/stata2-3-data.pdf Data Management for Reproducible Research]
[[Category: Data_Management ]]

Latest revision as of 14:31, 12 June 2019

The DataWork folder is a structured, standardized data folder that increases project efficiency and reduces the risk of error. The DataWork folder houses all files related to a project’s data, including data files; questionnaires; data collection documentation; code for sampling, treatment assignment, and analysis; analysis output; and survey, monitoring, administrative, and secondary data. DIME strongly recommends using the DataWork folder from the beginning of the project and throughout its duration.

Read First

  • Use the iefolder Stata command to easily set up and update the DataWork folder.
  • Many DIME resources are easier to take advantage of when the DataWork folder is used.
  • Use the DataWork folder from the beginning of the project: reorganizing a project folder is time-consuming and cumbersome.
  • Even if your project has special structural requirements, use the DataWork folder as a starting point.

Creating the DataWork Folder

Image 1. Example of where the DataWork folder is in relation to Box/DropBox folders. (Click to enlarge.)

The DataWork folder is easily set up via the Stata command iefolder, which is part of the package ietoolkit.

The DataWork folder should be housed within the project folder, which contains a variety of other sub-folders (i.e. project budget and government communications). The DataWork folder and the broader project folder should be shared across project teams via Box, Dropbox, or a similar platform. Image 1 shows a DataWork folder housed within a project folder.

Contents

Image 2. Example of a DataWork folder. (Click to enlarge.)

The DataWork folder contains a master do-file, Survey Round folders, a Survey Encrypted Data folder, and a Master Data folder. It may also contain additional documentation (i.e. readme) to help users navigate its contents.

Master Do-File

The project master do-file runs all other project do-files from cleaning to final analysis. It also sets up dynamic file paths so that multiple users can work from the same project folder shared via, for example, Dropbox or Box. This ensures that everyone gets the same results.

If you are new to a project folder, always start by finding the master do-file: it serves as a map of all files in the DataWork folder.

Survey Rounds

Image 3. Example of a Survey Round folder. (Click to enlarge.)

Each Survey Round folder contains a master do file specific to its data source, in addition to the following folders: DataSets, Dofiles, Outputs, Documentation, and Questionnaire. While the folders listed here are iefolder, you can also create more folders that are unique to your project.

What Requires a Survey Round Folder?

Each source of data (i.e. baseline, follow-up, midline, endline, administrative, secondary) should have its own Survey Round folder within the DataWork folder. If the data source is collected continuously (i.e. administrative or secondary data as macro data over time), then it requires only one Survey Round folder. However, if the data source is collected in stages (i.e. baseline and endline data), then it requires one Survey Round folder for each stage.

If you have multiple units of observation in a given data source, each unit of observation for each data source requires its own Survey Round folder. For example, if the units of observation during baseline data collection are students, teachers and schools, then baseline data requires three Survey Round folders: baseline_students, baseline_teachers and baseline_schools. If you choose, these folders may be nested within a parent Baseline folder. iefolder gives you the option of doing this by creating a Baseline subfolder and then creating Survey Round folders within it.

Note that each Survey Round needs to have a unique name across the project when using iefolder.

Survey Encrypted Data

Whenever you create either a new survey round or new unit of observation with iefolder, the command creates a partner folder for each survey round or unit of observation in the Survey Encrypted Data folder. Any identifying or sensitive data should be saved in the Survey Encrypted Data folder; the folder’s contents can easily be encrypted using software like VeraCrypt, we previously recommended Boxcryptor but securoty issues were found in that software so we strongly recommend against using Boxcryptor. . Note that while iefolder creates the Survey Encrypted Data folder, it does not encrypt it.

Consider, for example, a master dataset. The version with identifying information should be stored in the Survey Encrypted Data folder. The version without identifying information should be stored in the Master Data folder. The latter version is quicker to access and can often be shared outside the research team.

Master Data

Image 4. Example of a Master Data Set folder. (Click to enlarge.)

The Master Data folder stores information about all the observations for which data is collected, including observations both in and out of the sample. As it is sometimes necessary to identify observations outside of the sample, the Master Data folder should also include, for example,

  • Census observations not sampled for the project, or
  • Observations encountered in monitoring activities but not in the sample.

In the Master Data folder, we can also track any time-invariant information relevant to the project (i.e. assigned treatment status, treatment uptake, identifying information, dummy for being sampled). The datasets where we store this information are called master datasets.

A project needs one master dataset for each unit of observation used in the project (i.e. households, students, teachers, firms).

Sampling and Treatment Assignment

The Master Data folder should also include all activities performed on the main listing of all observations (i.e. sampling and treatment assignment). This should never be done directly on census data or baseline data etc. While census data will be used for sampling, it is important to match the census data to the master data and check that it makes sense in relation to whatever data exists there already. After that quality control step, sample directly from the master data set, knowing that the randomized sample will make sense in relation to other data sources.

Back to Parent

This article is part of the topic Data Management

Additional Resources