Central Limit Theorem - lec. 26

ucla | MATH 170E | 2023-03-19T23:48


Table of Contents

Definitions


  • e.g. Uniform approximation using CLT

  • e.g. DeMoivre-Laplace for P(X < k)

Big Ideas


Central Limit Theorem

Let X1, be i.i.d. with finite mean and variance μ,σ2

Xnμσ/nN(0,1)in distribution asn\infin

Relation to standard normal

if ZN(0,1)σZ+μN(μ,σ2), then CLT says

$\overline X_n\approx \mathcal N(\mu,\frac{\sigma^2}n)\quad E[\overline X_n]=\mu\quad \text{var}(\overline X_n)=\frac{\sigma^2}n$

Because Xn is the mean of the seq.

Sn=jXjN(nμ,nσ2)

DeMoivre-Laplace Correction

Resources


📌

**SUMMARY
**