Scribd
Upload
24 views

Two-Sample T-Test: Independent

The document discusses testing whether the means of two independent samples are equal using a two-sample t-test. It also discusses comparing paired samples, considering both when the pairs are independent and when they are correlated.

Uploaded by

david
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
24 views

Two-Sample T-Test: Independent

The document discusses testing whether the means of two independent samples are equal using a two-sample t-test. It also discusses comparing paired samples, considering both when the pairs are independent and when they are correlated.

Uploaded by

david
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

' $

Two-Sample T-Test

Given two independent samples,


iid iid
{X1 , ..., Xn } ∼ N (µA , σ 2 ) and {Y1 , ..., Ym } ∼ N (µB , σ 2 ),

we are often interested in testing

H0 : µA = µB versus HA : µA 6= µB .

That is, we’d like to know whether there’s any evidence to indicate
that the underlying processes that generated these two samples are
different.

& %
ActSc 613 | Lecture 20 © 2015-17 by M. Zhu, PhD 1 of 2
' $

Paired Comparison

We have two samples:


iid iid
{X1 , ..., Xn } ∼ N (µA , σ 2 ) and {Y1 , ..., Yn } ∼ N (µB , σ 2 ).

(a) First, suppose the two samples are independent of each other.
Clearly, X̄ − Ȳ is an unbiased estimator of µA − µB . How big
is Var(X̄ − Ȳ )?
(b) Now, suppose (Xi , Yi ) forms a “natural” pair with

Corr(Xi , Yi ) = ρ for all i,

but the pairs (X1 , Y1 ), ..., (Xn , Yn ) are still independent of each
other. Let Di = Xi − Yi . Clearly, D̄ = X̄ − Ȳ is still an
unbiased estimator of µA − µB . How big is Var(D̄)?

& %
ActSc 613 | Lecture 20 © 2015-17 by M. Zhu, PhD 2 of 2

You might also like