{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

L23-stats-post

# L23-stats-post - X X Estimator W f W(w Readings Section 9.1...

This preview shows pages 1–2. Sign up to view the full content.

LECTURE 23 Readings: Section 9.1 (not responsible for t -based confidence intervals, in pp. 471-473) Outline Classical statistics Maximum likelihood (ML) estimation Estimating a sample mean Confidence intervals (CIs) CIs using an estimated variance Classical statistics Estimator ˆ Θ X N p X ( x ; θ ) θ also for vectors X and θ : p X 1 ,...,X n ( x 1 , . . . , x n ; θ 1 , . . . , θ m ) These are NOT conditional probabilities; θ is NOT random mathematically: many models, one for each possible value of θ Problem types: Hypothesis testing: H 0 : θ = 1 / 2 versus H 1 : θ = 3 / 4 Composite hypotheses: H 0 : θ = 1 / 2 versus H 1 : θ = 1 / 2 Estimation: design an estimator ˆ Θ , to keep estimation error ˆ Θ - θ small Maximum Likelihood Estimation Model, with unknown parameter(s): X p X ( x ; θ ) Pick θ that “makes data most likely” ˆ θ ML = arg max θ p X ( x ; θ ) Compare to Bayesian MAP estimation: ˆ θ MAP = max θ p X | Θ ( x | θ ) p Θ ( θ ) p X ( x ) Example: X 1 , . . . , X n : i.i.d., exponential( θ ) max θ n i =1 θ e - θ x

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}