Kbjarkefur (talk | contribs) |
|||
Line 15: | Line 15: | ||
We have a standardized folder structure that we want all DIME projects to follow. | We have a standardized folder structure that we want all DIME projects to follow. | ||
== Stata | == Stata Programming == | ||
Best practices and style guides | Best practices and style guides | ||
== Questionnaire | == Questionnaire Programming == | ||
Best practices and style guides for SurveyCTO | Best practices and style guides for SurveyCTO |
Revision as of 17:22, 2 November 2016
Welcome to the DIME Wiki!
We have organized the Wiki in Chapters. Each chapter has a few high level topics. All pages on this Wiki is organized into one of those high level topics. It is always good to start by reading the page associated with the high level task.
Chapter 1: Data Work Management
This chapter relates to general skills in relation to data work, such as how to you organize you data folder so that all members of your team can collaborate on the data work. It also includes
Project Folder Management
We have a standardized folder structure that we want all DIME projects to follow.
Stata Programming
Best practices and style guides
Questionnaire Programming
Best practices and style guides for SurveyCTO
Chapter 2: Data Sources
This chapter deals with the types of data sources we work with at DIME and the best practices associated with each of them
Household Surveys
Everything from survey management, questionnaire development, to processes for data quality assurance
New Sources of Data
Big data, geo data etc. What have we done and what resources do we have?
Admin Data and other data collected by others
Best practices for integrating data not collected by us
Chapter 3: Data Curation - From Raw Data to Final Outputs
This chapter deals with each stage of the data work of a typical impact evaluation. While this chapter takes the perspective of the a SurveyCTO/Stata environment, much of what is written here is still useful if you are using other tools for your data work.
Data Import
Import from different raw formats to Stata's .dta format.
Data Validation and Cleaning
Data validation and cleaning goes hand in hand. Use your critical thinking when validating the data
Constricting variables and data sets for Analysis
After cleaning we need to construct the averages, aggregates, ratios, categories etc. that we will use in analysis. We also need to creaet the data sets needed such as panel data sets from multiple rounds of data.
Data Analysis and Presentation of Results
General advice for analysis and outputting the results. The purpose of this topic is not give you any advise on how to analyse your data, but to give advise on how to implement your analysis after you have made a plan for how to analyse your data.