Consistency

Summary

Given:

  • A sample x1,x2,...,xn
  • A statistical model where θ is an unknown parameter
  • An estimator θ^n=g(x1,,xn)

Definition: consistency

  • We may view θ^1,θ^2,θ^3, as a sequence of random variables .
  • We say that θ^n is a consistent estimator of θ if θ^n converges in probability to θ ,

plim θ^n=θ

  • or

P(|θ^nθ|<ε)1 as n

  • for all ε>0 .

Example

  • x1,x2,...,xn is an IID random sample where E(xi)=μ and Var(xi)=σ2 . Then x¯n is a consistent estimator of μ ( the weak law of large numbers ).