Researchers are often confronted with questions about how big should their sample size be in order to generate representative good quality data within a reasonable margin of error (in probability samples).

Read this article for an overview of the inverse relationship between sample size and margin of error (the more the sample, the less the margin of error), and to understand the concept of "diminishing returns," where beyond a certain point increasing the sample size will cause negligible impact or reduction on the margin of error.