Based on your analytical plan, identify the criteria your data need to meet so that you can answer your research questions.
For example, if you plan to use a one-sample t test for independent means, your data have to meet the following assumptions:
interval or ratio scale of measurement
random sampling from a defined population
samples or data sets are linked in the population through repeated measures, natural association, or matching
scores are normally distributed in the population; difference scores are normally distributed
Before you can begin to analyze your data, the data may need to be cleaned, processed, screened, and sometimes split into separate data sets. Take snapshots of your data at key points in the collection, screening, processing, and analyzing process. (A snapshot is just a copy of your data files that are not edited and which are saved to a backup storage location).
raw data (before it is cleaned and processed)
your processed data (before it is analyzed)
the data used for your analysis, any analytical scripts or procedures used, and detailed notes about why data were selected for analysis or excluded
If possible, automate repetitive processing steps or use tools that minimize human error. If automating is not an option, keep detailed records of the changes made and reasoning behind your decisions.
The Software Tools database is the product of two NSF-funded Informatics Education Planning Workshops hosted by DataONE. The database provides a brief description of a wide range of tools that are recommended for use by scientists and students, as well as additional information and links to further resources.
IUanyWare is a virtual environment with data processing and analysis tools, among other programs. These include programs like SPSS, Stata, SAS, R & RStudio, MATLAB, ArcGIS, Mathematica, and more.
