Sampling is the process of obtaining a sample from a population.

Statisticians insist on “representativeness” of a sample.

What is a “Representative” sample?

Let’s revisit the cake we talked about last time.

Imagine the cake presented to you was a multi-layered cake with cherries on top.

Now, one could obtain a sample in many ways. Someone I know likes to pick only the cherries. There are others who prefer to eat only the top layer of cream; still others prefer eating only the cream; while some will not eat it unless the cream is removed…

Clearly, any of the above methods of “sampling” the cake would not yield a satisfactory idea about the cake as a whole (which is why we are sampling in the first place).

For us to get a really good idea about the whole cake, we would have to cut a piece of cake that included all the elements of the cake (in the same proportion as the cake itself). That is, we should not deliberately avoid including the cherry or cream (for instance) while cutting the “sample” piece.

Applied to a population, this means that a sample should have similar characteristics as the population it came from. When this happens, the sample is said to be “representative” of the population.

Summary:

Sampling is the process of obtaining a sample from a population.

A representative sample is one that resembles the population from which it was drawn.