The samplemeanˉx of an SRS of size n drawn from a large population with mean μ and standard deviationσ has a sampling distribution with mean and standard deviation
μˉx=μσˉx=σ√n
The sample mean ˉx is an unbiased estimator of the population mean μ and is less variable than a single observation. The standard deviation decreases in proportion to the square root of the sample size n. This means that to reduce the standard deviation by a factor of C, we need to increase the sample size by a factor of C2.
The central limit theorem states that for large n the sampling distribution of ˉx is approximately N(μ,σ/√n) for any population with mean μ and finite standard deviation σ. This allows us to approximate probability calculations of ˉx using the Normal distribution.