Professional Documents
Culture Documents
and Statistics
Twelfth Edition
Chapter 9
Large-Sample Tests of
Hypotheses
Some graphic screen captures from Seeing Statistics Copyright 2006 Brooks/Cole
Some images 2001-(current year) www.arttoday.com A division of Thomson Learning, Inc.
Introduction
Suppose that a pharmaceutical company
is concerned that the mean potency of an
antibiotic meet the minimum government
potency standards. They need to decide between
two possibilities:
The mean potency does not exceed the
mean allowable potency.
The mean potency exceeds the mean
allowable potency.
This is an example of a test of hypothesis.
Copyright 2006 Brooks/Cole
A division of Thomson Learning, Inc.
Introduction
Similar to a courtroom trial. In trying a person
for a crime, the jury needs to decide between
one of two possibilities:
The person is guilty.
The person is innocent.
To begin with, the person is assumed innocent.
The prosecutor presents evidence, trying to
convince the jury to reject the original
assumption of innocence, and conclude that the
person is guilty. Copyright 2006 Brooks/Cole
A division of Thomson Learning, Inc.
Parts of a Statistical Test
1. The null hypothesis, H0:
Assumed to be true until we can prove
otherwise.
2. The alternative hypothesis, Ha:
Will be accepted as true if we can
disprove H0
Court
Courttrial:
trial: Pharmaceuticals:
Pharmaceuticals:
H
H00::innocent
innocent H00:: does
H doesnot
notexceeds
exceedsallowed
allowedamount
amount
H
Haa::guilty
guilty Haa:: exceeds
H exceedsallowed
allowed amount
amount
Copyright 2006 Brooks/Cole
A division of Thomson Learning, Inc.
Parts of a Statistical Test
3. The test statistic and its p-value:
A single statistic calculated from the sample
which will allow us to reject or not reject H 0,
and
A probability, calculated from the test statistic
that measures whether the test statistic is likely
or unlikely, assuming H0 is true.
4. The rejection region:
A rule that tells us for which values of the
test statistic, or for which p-values, the null
hypothesis should be rejected.
Copyright 2006 Brooks/Cole
A division of Thomson Learning, Inc.
Parts of a Statistical Test
5. Conclusion:
Either Reject H0 or Do not reject H0,
along with a statement about the reliability
of your conclusion.
How do you decide when to reject H0?
Depends on the significance level, the
maximum tolerable risk you want to have
of making a mistake, if you decide to reject
H0.
Usually, the significance level is
or
Copyright 2006 Brooks/Cole
A division of Thomson Learning, Inc.
Example
The mayor of a small city claims that the average
income in his city is $35,000 with a standard
deviation of $5000. We take a sample of 64
families, and find that their average income is
$30,000. Is his claim correct?
1-2.
1-2. We
Wewant
wantto
totest
testthe
thehypothesis:
hypothesis:
HH00::==35,000
35,000(mayor
(mayorisiscorrect)
correct)versus
versus
HHaa::35,000
35,000(mayor
(mayorisiswrong)
wrong)
Start
Startby
byassuming
assumingthat
thatH
H00isistrue and ==35,000.
trueand 35,000.
Copyright 2006 Brooks/Cole
A division of Thomson Learning, Inc.
Example
3.3. The
Thebest
bestestimate
estimateof
ofthe
thepopulation mean isisthe
populationmean thesample
sample
mean,
mean,$30,000:
$30,000:
From
Fromthe
theCentral
CentralLimit
LimitTheorem
Theoremthethesample
samplemean
meanhashasan
an
approximate
approximatenormal
normaldistribution
distributionwith mean ==35,000
withmean 35,000
and
andstandard
standarderror
errorSE
SE==5000/8
5000/8==625.
625.
The
Thesample
samplemean,
mean,$30,000
$30,000lies
lieszz==(30,000
(30,00035,000)/625
35,000)/625
==-8
-8standard
standarddeviations
deviationsbelow
belowthethemean.
mean.
The
Theprobability
probabilityof
ofobserving
observingaasample
samplemean
meanthis
thisfar
farfrom
from
==35,000
35,000(assuming
(assumingHH00isistrue)
true)isisnearly
nearlyzero.
zero.
4.4. From
Fromthe theEmpirical
EmpiricalRule,Rule,values
valuesmore
morethan
thanthree
threestandard
standard
deviations
deviationsaway
awayfrom fromthe
themean
meanareareconsidered
consideredextremely
extremely
unlikely.
unlikely.Such
Suchaavaluevaluewould
wouldbebeextremely
extremelyunlikely
unlikelyto
tooccur
occur
ififindeed
indeedHH00isistrue,
true,and
andwould
wouldgive
givereason
reasonto
toreject
rejectHH00..
5.5. Since
Sincethe
theobserved
observedsample
samplemean,
mean,$30,000
$30,000isisso
sounlikely,
unlikely,we
we
choose
choosetotoreject
rejectHH00:: ==35,000
35,000and
andconclude
concludethat
thatthe
the
mayors
mayorsclaim
claimisisincorrect.
incorrect.
6.6. The
Theprobability that==35,000
probabilitythat 35,000and
andthat
thatwe
wehave
haveobserved
observed
such
suchaasmall
smallsample
samplemean
meanjust
justby
bychance
chanceisisnearly
nearlyzero.
zero.
H00 :: 880
H 880 Test
Test statistic
statistic::
xx 00 871 880
Haa :: 880
H 880 zz 871 880 3.03
3.03
ss// nn 21 21// 50
50
Copyright 2006 Brooks/Cole
A division of Thomson Learning, Inc.
MY APPLET
Example
What is the probability that this test
statistic or something even more extreme (far
from what is expected if H0 is true) could have
happened just by chance?
value::PP((zz 33..03
pp--value 03)) PP((zz 33..03
03))
22PP((zz 33..03
03)) 22(.(.0012
0012)) ..0024
0024
This is an unlikely
occurrence, which
happens about 2 times in
1000, assuming = 880!
Copyright 2006 Brooks/Cole
A division of Thomson Learning, Inc.
Example
To make our decision clear, we choose
a significance level, say = .01.
IfIfthe
thep-value
p-valueisisless than,
lessthan ,HH00isisrejected
rejectedas
asfalse.
false.You
You
report
reportthat
thatthe
theresults
resultsare
arestatistically
statisticallysignificant
significantatat
level
level
IfIfthe
thep-value
p-valueisisgreater than,
greaterthan ,HH00isisnot
notrejected.
rejected.You
You
report
reportthat
thatthe
theresults
resultsare
arenot
notsignificant level
significantatatlevel
Since our p-value =.0024 is less than, we
reject H0 and conclude that the average yield
has changed.
Copyright 2006 Brooks/Cole
A division of Thomson Learning, Inc.
Using a Rejection Region
If = .01, what would be the critical
value that marks the dividing line between not
rejecting and rejecting H0?
p-value<<,
IfIfp-value ,HH00isisrejected.
rejected.
p-value>>,
IfIfp-value ,HH00isisnot
notrejected.
rejected.
The dividing line occurs when p-value = . This is
called the critical value of the test statistic.
Test
Teststatistic
statistic>>critical
criticalvalue
valueimplies p-value<<,
impliesp-value ,HH00isisrejected.
rejected.
Test
Teststatistic
statistic<<critical
criticalvalue
valueimplies p-value>>,
impliesp-value ,HH00isisnot
not
rejected.
rejected. Copyright 2006 Brooks/Cole
A division of Thomson Learning, Inc.
MY APPLET
Example
What is the critical value of z that
cuts off exactly /2 = .01/2 = .005 in the tail
of the z distribution?
For our example, z
= -3.03 falls in the
rejection region
and H0 is rejected
at the 1%
significance level.
Rejection
RejectionRegion:
Region:Reject
RejectHH00ififzz>>2.58
2.58or
orzz<<-2.58.
-2.58.IfIfthe
the
test
teststatistic
statisticfalls
fallsin
inthe
therejection
rejectionregion,
region,its
itsp-value
p-valuewill
willbe be
less than==.01.
lessthan .01.
Copyright 2006 Brooks/Cole
A division of Thomson Learning, Inc.
One Tailed Tests
Sometimes we are interested in a detecting a
specific directional difference in the value of .
The alternative hypothesis to be tested is one
tailed:
Ha: or Ha: <
Rejection regions and p-values are calculated
using only one tail of the sampling distribution.
Define:
= P(Type I error) = P(reject H0 when H0 is true)
P(Type II error) = P(accept H0 when H0 is false)
Copyright 2006 Brooks/Cole
A division of Thomson Learning, Inc.
Two Types of Errors
We want to keep the probabilities of
error as small as possible.
The value of is the significance level, and
is controlled by the experimenter.
The value of is difficult, if not impossible
to calculate.
Rather than accepting H0 as true without being
able to provide a measure of goodness, we
choose to not reject H0.
We write: There is insufficient evidence to reject H0.
Copyright 2006 Brooks/Cole
A division of Thomson Learning, Inc.
Other Large Sample Tests
There were three other statistics in Chapter 8
that we used to estimate population
parameters.
These statistics had approximately normal
distributions when the sample size(s) was
large.
These same statistics can be used to test
hypotheses about those parameters, using the
general test statistic:
statistic
statistic--hypothesiz
hypothesiz ed
ed value
value
zz
standard
standarderror
errorof
of statistic
statistic
Copyright 2006 Brooks/Cole
A division of Thomson Learning, Inc.
Testing the Difference
between Two Means
AArandom
randomsample
sampleofof size
sizenn11drawn
drawnfrom
from
population with mean and variance 22
population 1 with mean 11 and variance 11..
1
AArandom
randomsample
sampleofof size
sizenn22 drawn
drawnfrom
from
population with mean and variance
population 2 with mean 22 and variance 22..
2 22
Calculate p 1 65 / 80 .81
x1 x2 104
p 2 39 / 70 .56 p .69
n1 n2 150
Test statistic :
p 1 p 2 0 .81 .56
z 3.30
1 1 1 1
p q .69(.31)
n1 n2 80 70
value::PP((zz 33..30
pp--value 30))PP((zz 33..30
30))22(.(.0005
0005))..001
001
Since the p-value is less than = .01, H0 is rejected. The
results are highly significant. There is evidence to indicate
that the rates of participation are differentCopyright
for boys 2006and girls.
Brooks/Cole
A division of Thomson Learning, Inc.
Key Concepts
I. Parts of a Statistical Test
1. Null hypothesis: a contradiction of the alternative
hypothesis
2. Alternative hypothesis: the hypothesis the researcher
wants to support.
3. Test statistic and its p-value: sample evidence calculated
from sample data.
4. Rejection regioncritical values and significance levels:
values that separate rejection and nonrejection of the null
hypothesis
5. Conclusion: Reject or do not reject the null hypothesis,
stating the practical significance of your conclusion.
Copyright 2006 Brooks/Cole
A division of Thomson Learning, Inc.
Key Concepts
II. Errors and Statistical Significance
1. The significance level is the probability if rejecting H 0
when it is in fact true.
2. The p-value is the probability of observing a test statistic
as extreme as or more than the one observed; also, the
smallest value of for which H 0 can be rejected.
3. When the p-value is less than the significance level , the