1

Section 6.2
Tests of Significance
2
Test of Significance
 Statistical Inference-
 To make conclusion about a population
 To estimate a population parameter
 3 most common ways to make inference
 Point Estimation (x-bar or p-hat)
 Confidence Intervals (Plausible values of parameter)
 Test of Significance (also called Hypothesis Tests)

 Test of Significance is the focus of this section
3
Test of Significance
 Test of Significance:
Assess the evidence provided by data in favor of
some claim about the population
Start by setting up a hypothesis
 This is a statement about a population parameter
Results of the test are expressed in terms of a
probability
 Usually called a p-value
 This probability (p-value) measures how well the data
and the hypothesis agree.
4
Test of Significance
 Is the observed effect “too large” or “too
unusual” to be due to chance variation?
 An approach to significance testing
1. Define a research question in terms of a parameter and
specify the claimed parameter value.
2. Conduct an experiment or survey to obtain data.
3. Plot data and compute observed statistic (x-bar or p-hat).
4. Check sampling distribution for normality.
5. Using the sampling distribution of the statistic with center
given by claimed parameter value, calculate the probability
of getting differences more extreme than the observed effect
6. If the probability is small enough, declare the observed effect
statistically significant (i.e., “too large” to be due to chance).
5
Test of Significance – An example
 The mean yield of corn in the US is about
135 bushels per acre. A survey of 40
randomly selected farmers this year gives a
sample mean yield of bushels per
acre.

We want to know whether this is good
evidence that the national mean this year is
not 135 ushers per acre
x =138.8
6
 Farmers corn yield
 want to measure the average corn yield for the US this year.
 Sample -- n = 40 farmers
 Statistic – sample mean:
– pop std. dev:

 n=40≥30, according to CLT,
 Question: Is it possible that, even though we observed ,
the true µ is in fact 135 bushels per acre?
 (Is it likely that observing is due to pure chance?)
x =138.8
o =10
|
.
|

\
|
n
N x
o
µ, ~

x =138.8
x =138.8
Test of Significance – An example
7
Section 6.2
Test of Significance – An example
 Using z-
calculation and
table A, the
probability of
observing 138.8 or
larger while the
true µ is 135, with
sd = 10/sqrt(40) is
only 0.008 = sd
8

Test of Significance – An example
 The probability 0.008 is very small
 We will only observe eight times per 1000
samples if the true mu = 135
 Hence, it is not likely that the true µ is 135, given that a
sample mean=138.8 is observed
 Two possibilities
 µ=135 and we observed something very unusual
 µ is not 135 but is some other value that makes the
observed data more probable
x >138.8
9
Test of Significance – An example
 What if a sample mean is observed?
 Probability of observing 136.6 given µ=135 is 0.15
 We will observe “ ” 15 times per 100 sample
 This value 0.15 is not as extreme as 0.008, and it could
easily happen
 We don’t have strong evidence to believe µ≠135.
 Conclusion: A sample outcome that would be extreme if a
hypothesis were true is evidence that the hypothesis is not true. In
other words, if the sample result is extreme, we likely have
evidence against our original hypothesis.
x =136.6
x >136.6
10

Test of Significance – An example
 In this example, we considered 2 situations of
how the value of µ can occur:
1. µ=0
2. µ≠0
 These are the hypotheses
 The first step in a test of significance is to state
a claim that we will try to find evidence against
11

Stating hypothesis
 Null Hypothesis (H
0
)
The statement being tested in a test of significance
is called the null hypothesis
 Usually the null hypothesis
is a statement of “no effect” or “no difference”,
is a statement about a population,
is expressed in terms of a (some) parameter(s).
 Example H
0
: µ=0
12
Stating hypothesis
 Alternative Hypothesis ( H
a
)
The name we give to the statement we hope (or
suspect) is true.
 Example H
a
: µ=0
 Hypotheses always refer to some population or
model, not a particular outcome
 We must decide whether the alternative hypothesis
(H
a
) should be one-sided or two-sided
13
Stating hypothesis
 One-sided alternative hypotheses:
Example:

 Two-sided alternative hypothesis:
Example:
0 : < µ
a
H
0 : = µ
a
H
0 : > µ
a
H
14

Stating hypothesis
 Choosing one-sided or two-sided Hypothesis
 The alternative hypothesis should express the hopes or
suspicions we had in mind when we decided to collect the
data.
 You are cheating if you first look at the data and then
frame H
a
to fit what the data show. Choose a one or
two-sided Ha before you look at the data.
 If you do not have a specific direction in advance, use a
two-sided alternative
15
Stating hypothesis
 Example: Your company hopes the reduce the mean time
(µ) required to process customer orders. At present, this
mean is 3.8 days. You study the process and eliminate
some unnecessary steps.
 Q: Did you succeed in decreasing the average process
time?
Target: to show that the mean is now less than 3.8 days.
 So alternative hypothesis is one-sided
 The null hypothesis is “no change” value
8 . 3 : < µ
a
H
8 . 3 : = µ
o
H
16
 The mean area of several thousand
apartments in a new development is
advertised to be 1250 sqft. A tenant
group thinks that the apartments are
smaller than advertised. They hire an
engineer to measure a sample of
apartments to test their suspicion.
H
0
: µ=1250 vs. H
a
: µ<1250
Stating hypothesis
17
 Experiments concerning learning in animals
sometimes measure how long it takes a mouse
to find its way through a maze. The mean time
is 18 seconds for one particular maze. A
researcher thinks that a loud noise will cause
the mice to complete the maze faster. She
measures how long each of 10 mice takes with
a noise as stimulus.
 H
0
: µ=18 vs. H
a
: µ<18

Stating hypothesis
18
 Last year, your company’s service technicians
took an average of 2.6 hours to respond to
trouble calls from business customers who
purchased service contracts. Do this year’s
data show a different average response time?
 H
0
: µ = 2.6 vs. H
a
: µ = 2.6

Stating hypothesis
19

Test of Significance
 The test is based on a statistic that estimates the
parameter appearing in the hypothesis
 Usually this is the same estimate we would use in
a confidence interval for the parameter
 When H
0
is true, we expect the estimate to take a
value near the parameter value specified by H
0

 Values of the estimate far from the parameter
value specified by H
0
give evidence against H
0

 The alternative hypothesis (Ha) determines which
directions count against H
0

20

Test of Significance
 Test statistics
 A test statistic measures compatibility between the null
hypothesis and the data
 Many test statistics can be thought of as a distance
between a sample estimate of a parameter and the
value of the parameter specified by the null hypothesis

21

Test of Significance
 Example:
 The Census Bureau reports that households spend an
average of 31% of their total spending on housing. A
homebuilders association in Cleveland wonders if the
national finding applies in their area. They interview a
sample of 40 households in the Cleveland metropolitan are
to learn what percent of their spending goes toward
housing. Take µ to be the mean percent of spending
devoted to housing among all Cleveland households.
Assume that o = 9.6%.
 What is the null and alternative hypothesis?
 H
0
: µ = 31% vs. H
a
: µ = 31%
22

Test of Significance
 Example: Spending on housing
Sample: n=40 households
sample mean:
Pop. std. dev:
Test:

 The test statistic is the standardized version of
distance between sample mean and parameter value
given in the H
0
:


H
0
: µ = 31%
H
a
: µ = 31%
x = 28.6%
o = 9.6%
z =
x ÷ µ
0
o
n
=
28.6 ÷ 31
9.6
40
= ÷1.58
23

Test of Significance
 Example: Spending on Housing
 The Central Limit Theorem assures us that is
approximately normal
 This implies that the test statistic has an approximately
standard Normal distribution
 To move from the test statistic z to a probability, we
must do Normal probability calculations.


x
24
Test of Significance P-Values
P-values
 A test of significance assesses the evidence against the null
hypothesis and provides a numerical summary of this evidence in
terms of a probability
 The idea is that “surprising” or “unusual” outcomes are evidence
against H
0

 A surprising or unusual outcome is one that is far from what we would
expect if H
0
were true
25
Test of Significance P-Values

 A test of significance finds the probability of getting an outcome as extreme
or more extreme than the actually observed outcome
 The direction or directions that count as “far from what we would expect” are
determined by the alternative hypothesis
 Definition: The probability, computed assuming that H
0
is true, that the test
statistic would take a value as or more extreme than that actually observed
is called the P-value of the test
 The smaller the P-value, the stronger the evidence against H
0

provided by the data in our sample
26
Test of Significance
P-values
 To calculate the P-value, we must use the
sampling distribution of the test statistic
 Since our test statistic z follows a standard
Normal distribution that is all we will need in
chapter 6. (Matters change in Chapter 7)
27

Test of Significance
P-values
 Example: continue Spending on housing


 Previously, we calculated z = -1.58
 If the null hypothesis is true, we expect z to take a value
not too far from 0
 Because the alternative is two-sided, values of z far
from 0 in either direction count as evidence against H
0

and in favor of H
a
H
0
: µ = 31%
H
a
: µ = 31%
28
Test of Significance
P-Values
 Example:Continued
 So the P-value is:
 P(z < -1.58) + P(z > 1.58) =
2*P(z > |1.58|) = 2*0.057 =
0.114

 What is the p-value if
H
a
:µ < 31%
 P-value is:
 P(z < -1.58) = 0.057
29

Test of Significance
Statistical Significance
 Statistical software automates the task of calculating
the test statistic and its P-value
 You must still decide which test is appropriate and
whether to use a one-sided or two-sided test
 You must also decide what conclusion the computer’s
numbers support
 We know that smaller P-values indicate stronger
evidence against the null hypothesis
30
Test of Significance
 How strong is strong enough?
 One approach is to announce in advance how much
evidence against H
0
we will require to reject H
0

 We compare the P-value with a significance level that says
“this evidence is strong enough”
 Significance level is denoted by o
 If we choose o = 0.05, we are requiring that the data give
evidence against H
0
so strong that it would happen no more
than 5% of the time when H
0
is true
 If the P-value is small or smaller than o, we say
that the data are statistically significant at level o
31
Test of Significance
Statistical Significance
 P-value < o => Data is significant. Reject H
0
 P-value > o => Data is not significant at given
significance level. There is not enough evidence to
reject H
0
32

Test of Significance
Statistical Significance
 “Significant” in the statistical sense does
not mean “important”
The term is used to indicate only that the
evidence against the null hypothesis reached
the standard set by o
33

Test of Significance
Test Statistic
 Previously, we calculated P-value = 0.057
 With H
a
:µ < 31%
 Is this significant at the o = 0.10 level?
 0.057 < 0.10 => There is enough evidence to reject H
0
at this
o-level
 Is there statistical significance at the o = 0.05 level?
 0.057 > 0.05 => There is not significant evidence to reject H
0
34

Test of Significance
Test for a population mean
 There are four steps in carrying out a
significance test
1. State the hypothesis (Ho vs. Ha)
2. Calculate the test statistic (x-bar usually)
3. Find the P-value and make a decision
4. State your conclusion in the context of your
specific setting

35
Test of Significance
Test for a population mean
 We have a SRS of size n drawn from a Normal
population with unknown mean µ
 We want to test the hypothesis that µ has a
specified value
Call the specified value µ
0
to represent a specific
value

1. State the null hypothesis
The null hypothesis is H
0
: µ = µ
0
36

Test of Significance
Test for a population mean
 The test is based on the sample mean
2. Calculate the test statistic
 Because Normal calculations require standardized
variables, we will use the standardized sample mean as
our test statistic:


 This one-sample z statistic has the standard Normal
distribution when H
0
is true

n
x
z
o
µ ÷
=
x
37

Test of Significance
Test for a population mean
3. find the P-value and make a decision
 The P-value of the test is the probability that z
takes a value at least as extreme as the value for
our sample
What counts as extreme is determined by the
alternative hypothesis H
a
 One sided H
a
: µ < µ
0
or

H
a
: µ > µ
0

 Two sided H
a
: µ ≠ µ
0
38

Test of Significance (Page 391)
39

Test of Significance
3. Find a p-value and make a decision
 P-value < o => Data is significant. Reject H
0
 P-value > o => Data is not significant at given
significance level. There is not enough evidence to
reject H
0
4. State your conclusion within the context of the problem

40

Test of Significance
z Test for a Population Mean
 Example:
 A manufacturer of cereal wants to test the performance of
one of its filling machines
 The machine is designed to discharge a mean amount of
µ = 12 ounces per box
 The manufacturer wants to detect any departure from this
setting
 Suppose the sample yields the following results
 n = 100 observations (boxes)
 = 11.85 ounces
 o = 0.5 ounces
x
41
Test of Significance
Solution:
1. State the null and alternative hypothesis, specify an o-level
2. Calculate the test statistic
3. find the p-value
4. Conclusion: p-value=0.0026 < Reject H
0
. At this
significance level, the sample provides enough evidence to
believe that mean amount of cereal the machines discharge is
different from 12 ounces per box.
x ÷ µ
o
n
=
11.85 ÷12
0.5
100
= ÷3
H
0
: µ =12 vs. H
a
: µ =12
P ÷ value = 2 * P(z > ÷3.0 ) ~ 0.027
01 . 0 = o
01 . 0 = o
42

Test of Significance
 Remember
 Tests of significance assess the evidence against H
0

 If the evidence is strong, we can confidently reject H
0
in
favor of the alternative
 Failing to find evidence against H
0
means only that the
data are consistent with H
0
, not that we have clear
evidence that H
0
is true
43

Test of Significance
Two-sided Significance Tests and Confidence Intervals:
 A 95% confidence interval captures the true value µ in
95% of all samples
 If we are 95% confident that the true µ lies in our
interval, we are also confident that values of µ that fall
outside our interval are incompatible with the data
That sounds like the conclusion of a test of
significance!
44

Test of Significance
Two-sided Significance Tests and Confidence Intervals:
 There is a close connection between 95% confidence
intervals and significance at the 5% level
 The same connection holds between 99% confidence
intervals and significance at the 1% level, and so on
 So we can use confidence intervals to conduct a two-
sided hypotheses test (in these simple cases)
45

Test of Significance
Two-sided Significance Tests and Confidence Intervals:

46
Test of Significance
Two-sided Significance Tests and Confidence Intervals:
Example cont’d:
 take
 n = 100 observations
 = 11.85 ounces
 .
 99% confidence interval:

x
o = 0.5
01 . 0 = o
) 98 . 11 , 72 . 11 (
100
5 . 0
576 . 2 85 . 11
*
= ± = ±
n
z x
o
47
Section 6.2
Test of Significance
Two-sided Significance Tests and Confidence Intervals:
 Hypotheses:


 Conclusion:
 12 is not in (11.72, 11.98)
 We reject the at significance
level

 Does this match the previous conclusion?
12 :
12 :
0
=
=
µ
µ
a
H
H
12 :
0
= µ H 01 . 0 = o
48
Test of Significance
P-value versus Fixed o
 A P-value is more informative than a “reject-or-not” finding
at a fixed significance level

 Assessing significance at a fixed level o is easier, because
no probability calculation is required
 Simply look up a critical value in a table

 Because the practice of statistics almost always employs
software that calculates P-values automatically, tables of
critical values are basically outdated
49
Section 6.2 Summary
 A test of significance is intended to
assess the evidence provided by data
against a null hypothesis (Ho) and in
favor of an alternative hypothesis Ha.
The test provides a method for ruling out
chance as an explanation for data that
deviate from what we expect under Ho.

50
Section 6.2 Summary
 The hypotheses (Ho and Ha) are stated in
terms of population parameters. Usually
Ho is a statement that no effect is present,
and Ha says that a parameter differs from
its null value, in a specific direction (one-
sided alternative) or in either direction
(two-sided alternative).

51
Section 6.2 Summary
 The test is based on a test statistic. The P-
value is the probability, computed assuming that
Ho is true, that the test statistic will take a value
at least as extreme as that actually observed.
Small P-values indicate strong evidence against
Ho. Calculating P-values requires knowledge of
the sampling distribution of the test statistic
when Ho is true.

52
Section 6.2 Summary
 If the P-value is as small or smaller than a
specified value alpha, the data are
statistically significant at significance
level alpha.

53
Section 6.2 Summary
 Significance tests for the hypothesis H0: μ
= μ0 concerning the unknown mean μ of a
population are based on the z statistic:

54
Section 6.2 Summary
 The z test assumes
A SRS of size n
Known population standard deviation σ
Either a Normal population or a large sample.
P-values are computed from the Normal
distribution (Table A) or from computers.