Chapter 13 Secondary analysis and official statistics Flashcards
Official statistics
that is, statistics collected by government departments in the course of their work or specifically for statistical purposes.
Secondary analysis
Secondary analysis is the analysis of data by researchers who will probably not have been involved in the collection of those data, for purposes that in all likelihood were not envisaged by those responsible for the data collection.
(To put it simply, secondary analysis is when researchers use data that was collected by someone else for a different purpose and analyze it to answer their own research questions.)
Ecological fallacy
The ecological fallacy is when we assume that conclusions drawn from group-level data can be applied to individuals within that group. In other words, it is a mistake to assume that what is true for a population as a whole must also be true for each individual within that population.
Unobtrusive Measure
An unobtrusive measure is a research method in which the researcher collects data without interfering or changing the natural setting or behavior of the participants. This approach is often used in situations where the researcher wants to collect data on behavior that would be difficult or impossible to observe directly.
For example, if a researcher wants to study the reading habits of individuals, they could use an unobtrusive measure such as examining the wear and tear on library books to estimate how frequently they are borrowed. In this case, the researcher is not interacting with the participants or altering their behavior in any way.
Advantages of secondary analysis
- Cost and time
- High-quality data
- Opportunity for longitudinal analysis
- Subgroup or subset analysis (check book)
- Opportunity for cross-cultural analysis
- More time for data analysis
- Reanalysis may offer new interpretations
- The wider obligations of the business researcher (check book)
Limitations of secondary analysis
- Lack of familiarity with data
- Complexity of the data
- No control over data quality
- Absence of key variables