# STAT231 Lecture Notes - Variance, Random Variable, Statistical Hypothesis Testing

13 pages30 viewsFall 2013

!

!

!

!

!

!

!

!

!

!

!

!

!

!

!

Home Page

Title Page

Contents

Page 46 of 77

Go Back

Full Screen

Close

Quit

•First •Prev •Next •Last •Go Back •Full Screen •Close •Quit

Statistical Inference

•We have looked at the sampling distribution of estimators and

conﬁdence intervals

•Look at the idea of a hypothesis test and the p-value scale of

evidence

!

!

!

!

!

!

!

!

!

!

!

!

!

!

Home Page

Title Page

Contents

Page 47 of 77

Go Back

Full Screen

Close

Quit

•First •Prev •Next •Last •Go Back •Full Screen •Close •Quit

Testing statistical hypotheses

•There are often hypotheses that a statistician or scientist might

want to “test” in the light of observed data.

•Two important types of hypotheses are

(1) that a parameter vector θhas some speciﬁed value θ0; we

denote this as H0:θ=θ0.

(2) that a random variable Yhas a speciﬁed probability distri-

bution, say with p.d.f. f0(y); we denote this as H0:Y∼

f0(y).

•We shall concentrate on the ﬁrst of these.

!

!

!

!

!

!

!

!

!

!

!

!

!

!

!

!

Home Page

Title Page

Contents

Page 48 of 77

Go Back

Full Screen

Close

Quit

•First •Prev •Next •Last •Go Back •Full Screen •Close •Quit

Statistical approach

•Assume that the hypothesis H0will be tested using some ran-

dom data “Data”.

•Deﬁne a test statistic (also called a discrepancy measure)D=

g(Data) that is constructed to measure the degree of “agree-

ment” between Data and the hypothesis H0.

•It is conventional to deﬁne Dso that D=0represents the

best possible agreement between the data and H0, and so that

the larger Dis, the poorer the agreement.

•Once speciﬁc observed “data” have been collected, let dobs =

g(data)be the corresponding observed value of D.

•To test H, we now calculate the observed signiﬁcance level

(also called the p-value), deﬁned as

p−value =Pr(D≥dobs;H0),(5)

where the notation “;H0” means “assuming H0is true”.

#### Loved by over 2.2 million students

Over 90% improved by at least one letter grade.