There are sites that provide downloads of commonly identified data sets.
Some of these pre-created data sets have already been coded and normalized for easy ingestion into standard software packages (i.e. SPSS, SAS, ESRI, QGIS).
The types of data included are census data, government data, World Bank data, ESRI geospatial data, etc.
See the Finding Data page for some important search tools.
In addition, contact discipline-specific associations, research groups, and software vendors to locate the best data repositories in your area.
One tool used to capture published data is the TDM service created by CrossRef. This Text and Data Mining (TDM) tool allows a researcher to download metadata from various publishers sites. This information would then allow you to download the PDF fulltext materials. The final step is to convert the PDF into XML markup for manipulation.
Complex manipulations of data sets often requires significant pre-analysis coding and formatting of the raw data for normalization.
This will allow researchers to merge various calibration and datum standards.
Research groups often create scripts to perform such manipulations and conversions.
Appropriate data analysis requires a deep understanding of best tools, statistical techniques, and software programs.
Research groups and Special Interest Groups (SIGs) can often provide topic-specific assistance.
The campus provides free access to the SPSS Basic tool for data analysis.
Tools such as NVIVO and free alternatives to NVIVO will assist with coding and analyzing text and other types of materials.
Consider using the free Tableau-Public tool to generate powerful visualizations that allow you to analyze your data in real-time.
Visualization tools exist that can provide displays of information with far more visceral impact than simple data dumps.
Visualizations are quite effective in showing patterns, projections, and anomolies.
Consider using the free Tableau-Public tool to generate powerful visualizations from your data. Keep in mind, the free version makes your results public.