Since I am almost done with my first year of PhD (apart from a research proposal which is due three weeks from now) and I am exempted from qualifiers, I have started my own research project on household migration decisions in Indonesia.
I have realized that good project management practices are essential to productive researchers. This (continuously updating) post will jot down some useful tips from my view.
I: General Project Management Practices
- Make plans for the implementation of research projects and monitor progress on a regular basis.
- Create separate folders for research projects and research methods. The latter is more of a toolbox and not necessarily research-topic-specific, and separating it out makes it more readily accessible.
- Have a readme file for every folder. Five years from now, you are going to forget what “figure1″ means, and you need a master file documenting (at the proper level of detail) what each file is about.
II. Data Management Using Stata
While reading this great book on data management with Stata, I took down the following notes which I found to be most helpful.
- create a master do file to link all steps in data cleaning and analysis.
- ask a friend to check my do files to make sure others can understand.
- create documentation for each project
- document key information that you may forget over time
- labeling data is not the only way; comments in do files, a journal, flow diagrams, etc can be useful.
- pick something that works for you and stick with it.
- add “version” at the top of each do file to make sure it will be executed accordingly.
- separate intermediate work from final work by
- regularly checking the old/new versions of the documents and pruning the unused ones
- create a separate folder for the intermediate work, or
- use version control software
- develop routines: use the “research methodology” folder; decompose big tasks into smaller ones; be aware of the steps to identify a research topic, find relevant literature and gaps in the literature, and data analysis.
- back up your data: use a hard drive and save it in Dropbox.
- A few notes about macros
- can be used to set “default” options for regressions, e.g. “local regopts noheader beta vce(robust)”
- identify multiple assertions without halting the do file: assert …,rc0
- locals can be combined by defining a new local
- Accessing saved results
- use “quietly summarize” and refer to the results r() to immediately generate new variables.
- for estimation results, use “ereturn list” to list the estimation results.
- use “statsby” to save estimation results in a new dataset.