Good morning, James, The term population as used in mathematical statistics does not necessarily refer to a collection of human individuals. It is a very abstract and general term. In our case, it could be nails. In biostatistics and epidemiology usage, population ordinarily does refer to an ensemble of human beings. This is what makes it possible to draw inferences and make rational decisions about public health problems. But "we seekers," as Richard so aptly puts it, are on a different level of hypothesis testing.
Incidentally, small-sample statistics should not be a hobgoblin. Exact, small-sample statistics is almost a hundred years old. It started in 1908 when the Student t-Test was discovered by Gosset as a correction to approximate methods based on the Gaussian normal distribution. Best regards, Matthew

