Analysis Data Files

Although your Input Data Files contain all the data you need for your project, they are typically not formatted and organized in such a way that you can use them for the analysis you plan to conduct.

The modifications you make to the Input Data Files to prepare them for analysis are referred to as the data processing phase of your project. The data processing for your project may involve dropping variables and/or observations, generating new variables, combining data from multiple sources, performing simulations, and a vast array of other operations.

After the necessary steps of processing have been completed, the data is saved in one or more Analysis Data Files. You will use the data in these files when you execute the procedures that generate the results for your project.

Analysis Data Files are created by your processing scripts, which contain commands that execute all the steps of data processing necessary to transform your Input Data Files into your Analysis Data Files.

All of your Analysis Data Files should be stored in the AnalysisData/ folder.

Naming Analysis Data Files

If you have a single Analysis Data File, name it Analysis.xxx

If you have more than one Analysis Data File, choose names that distinguish them from one another in some meaningful way. For example:

• analysis_individual.xxx and analysis_household.xxx

or

• analysis2012.xxx, analysis2013.xxx, ...

where .xxx represents the filename extension assigned to data files by the software you are using. (For example, if you are using Stata, .xxx would be replaced by .dta; if you are using R, .xxx would be replaced by .rda or .Rdata; and if you are using SPSS, .xxx would be replaced by .sav.)