1

If a large sample of volunteers were not representative of a specific population, would it necessarily mean that any conclusion of a study performed with sound methodology on this sample could not be generalized to that population?

Orion
  • 194
  • 2
  • 15
  • What exactly does "representativeness" mean for you here? – gung - Reinstate Monica Jan 25 '15 at 23:01
  • No bias in selecting subjects. See http://stats.stackexchange.com/a/16848/27782 – Orion Jan 25 '15 at 23:24
  • 1
    No - but it means that the generalization is justified only by domain knowledge, not by statistics. – Scortchi - Reinstate Monica Jan 26 '15 at 17:04
  • If the sample was really large, for example if it included a good majority of the population, you could start to claim the sample represented the population, absent strong reason to think otherwise. So, what do you mean by large and how strong is the evidence that the sample is not representative? – Joel W. Jan 26 '15 at 22:34

0 Answers0