Show Menu

Statistical Inference Cheat Sheet (DRAFT) by

This is a draft cheat sheet. It is a work in progress and is not finished yet.

Sampling Distri­bution

Inference: statistic (sample, x̅) --> parameter (popul­ation, μ)
CLT: large n --> x̅~N(μ­,σ/√n) - as n increases, x̅ approaches μ
Sample Propor­tion: mean = p and s.d. = √[p(1-­p)/n]
Z-stat­istic: when n>30, z=(x̅-­μ)/­(σ/√n) --> z-table
T-stat­istic: when n<30, d.f.=n-1 --> t-table

Statis­tical Inference

Confidence Interval
Tests of Signif­icance
- probab­ility --> trustw­orthy?
estima­te+/- MoE
H0: "no effect­"
- sample --> population
x̅ +/- z∗(σ/√n)
Ha: what we are testing
- based on sampling distri­bution
MoE ↓ = σ↓ = n↑= confidence ↓
Assume H0 --> what is the P of a result as/more extreme than statistic --> reject if P≤α