DataVsStatistics
- 1. Defining Datasets and Statistics
- 2. What is Data? da·ta noun plural but singular or plural in construction, often attributive ˈdā-tə, ˈda- also ˈdä- 1: factual information (as measurements or statistics) used as a basis for reasoning, discussion, or calculation 2: information output by a sensing device or organ that includes both useful and irrelevant or redundant information and must be processed to be meaningful 3: information in numerical form that can be digitally transmitted or processed Merriam-Webster (http://www.merriam-webster.com/dictionary/data)
- 3. Data can be • Observational: Captured in real-time, typically outside the lab – Examples: Sensor readings, survey results, images, audio, video • Experimental: Typically generated in the lab or under controlled conditions – Examples: test results • Simulation: Machine generated from test models – Examples: climate models, economic models • Derived /Compiled: Generated from existing datasets – Examples: text and data mining, compiled database, 3D models
- 4. Data can be • Text: field or laboratory notes, survey responses • Numeric: tables, counts, measurements • Audiovisual: images, sound recordings, video • Models, computer code, geospatial data • Discipline-specific: FITS in astronomy, CIF in chemistry • Instrument-specific: equipment outputs
- 5. Microdata • Data directly observed or collected from a specific unit of observation. • Contain individual cases, usually individual people, or in the case of Census data, individual households Examples: • Census: the unit of observation is probably an individual, a household or a family. • Survey or poll: the responses of a single respondent
- 6. Aggregate Data Is higher-level data that have been compiled from smaller units of data. Examples: inflation rate, consumer price index, demographic data for city or state
- 7. Statistics are numerical data that has been organized and interpreted, usually displayed in tables.
- 8. Datasets • A dataset or study is made up of the raw data file and any related files, usually the codebook and setup files. • Most data sets require at least basic statistical analysis (Stata, SPSS, R, etc.) or spreadsheet programs (Excel) to use.
- 9. Repositories • A data repository is a collection of datasets that have been deposited for storage and findability. • They are often – discipline specific and/or – affiliated with a research institution • Examples – ICPSR – Harvard Dataverse Network – University institutional repositories
- 10. To recap: • Data are raw ingredients from which statistics are created. • Statistical analysis can be performed on data to show relationships among the variables collected. • Through secondary data analysis, many different researchers can re-use the same data set for different purposes.
- 11. Finding Datasets
- 12. 1. Think about who might collect the data. • Could it have been collected by a government agency? • A nonprofit or nongovernmental organization? • A private business or industry group? • Academic researchers?
- 13. 2. Look for publications that use the kind of data you’re looking for and that cite the dataset In other words, is the data you want mentioned in scholarly articles or government reports or some other source?
- 14. 3. Once you know that what you want exists, it's time to hunt it down. • Is it freely available on the web? • Or part of a package to which the library already subscribes? • Is it something we can buy? (And is it within the library's budget and can the purchase be made quickly enough to fit your timeframe?) • Can it be requested directly from the researcher?
- 15. Credits: adapted from and used with permission from UC SanDiego Library, “What is Data,” August 2018. http://ucsd.libguides.com/data-statistics/whatisdata.