I was reviewing a paper for a journal, and the authors stated that they randomly selected company reports from several databases to give them a sample size of 600 firms.
I was of the opinion that “sampling” is inherently associated with primary data collection or am I mistaken?
My suggestion would be that the authors state that they selected 600 “cases” for their analysis from the databases (using whatever criteria) and not make reference to the word “sampling”…?
The term "sampling" can indeed be used when utilizing secondary data sources for a study. Sampling refers to the process of selecting a subset of individuals, cases, or data points from a larger population or dataset for analysis. This process can apply to both primary data collection and secondary data analysis.
In the context of the paper you reviewed, where the authors selected company reports from databases as their sample, it is appropriate to use the term "sampling" to describe their process. Even though they did not collect the data themselves through primary research, they still sampled a subset of data from the larger population of available company reports.
It's important to note that the term "sampling" can be used in different research contexts, including both primary and secondary data analysis. However, if the authors prefer to be more precise and avoid any potential confusion, they could explicitly state that they selected 600 "cases" or "data points" for their analysis from the databases instead of using the term "sampling." Ultimately, it would depend on the specific terminology and conventions used in the field and the preferences of the authors and the journal they are submitting to.
As a reviewer, you can certainly provide your suggestion to the authors regarding the use of terminology, offering the option of stating that they selected 600 "cases" rather than using the term "sampling." However, it would be a judgment call for the authors to decide whether to adopt that suggestion based on their understanding of the field's conventions and the specific context of their study.
One can draw a sample from any known population. The procedure you describe is quite common in what is known as bibliometric research.
Thank you so much Ajit Singh and David L Morgan for your valuable insights.
- Badges
- Science topic
- Similar topics
- Computer Science and Engineering
- Artificial Intelligence