Chapter 8
Tests of
Hypotheses Based
on a Single
Sample
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
8.1
Hypotheses
and
Test Procedures
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
Hypotheses
The null hypothesis, denoted H0, is the
claim that is initially assumed to be true.
The alternative hypothesis, denoted by
Ha, is the assertion that is contrary to H0.
Possible conclusions from hypothesis-
testing analysis are reject H0 or fail to
reject H0.
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
Hypotheses
H0 may usually be considered the
skeptic’s hypothesis: Nothing new or
interesting happening here! (And
anything “interesting” observed is due to
chance alone.)
Ha may usually be considered the
researcher’s hypothesis.
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
Rules for Hypotheses
H0 is always stated as an equality claim
involving parameters.
Ha is an inequality claim that contradicts
H0. It may be one-sided (using either >
or <) or two-sided (using ≠).
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
A Test of Hypotheses
A test of hypotheses is a method for
using sample data to decide whether
the null hypothesis should be
rejected.
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
Test Procedure
A test procedure is specified by
1. A test statistic, a function of the
sample data on which the decision is
to be based.
2. (Sometimes, not always!) A
rejection region, the set of all test
statistic values for which H0 will be
rejected
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
Errors in Hypothesis Testing
A type I error consists of rejecting the
null hypothesis H0 when it was true.
A type II error consists of not rejecting
H0 when H0 is false.
and are the probabilities of type
I and type II error, respectively.
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
Level Test
Sometimes, the experimenter will fix
the value of , also known as the
significance level.
A test corresponding to the significance
level is called a level test. A test
with significance level is one for
which the type I error probability is
controlled at the specified level.
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
Rejection Region: and
Suppose an experiment and a sample
size are fixed, and a test statistic is
chosen. Decreasing the size of the
rejection region to obtain a smaller
value of results in a larger value of
for any particular parameter value
consistent with Ha.
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
8.2
Tests About
a
Population Mean
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
Case I: A Normal Population
With Known
Null hypothesis: H 0 : 0
x 0
Test statistic value: z
/ n
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
Case I: A Normal Population
With Known
Alternative Rejection Region
Hypothesis for Level Test
H a : 0 z z
H a : 0 z z
H a : 0 z z / 2 or z z / 2
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
Recommended Steps in
Hypothesis-Testing Analysis
1. Identify the parameter of interest and
describe it in the context of the
problem situation.
2. Determine the null value and state
the null hypothesis.
3. State the alternative hypothesis.
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
Hypothesis-Testing Analysis
4. Give the formula for the computed
value of the test statistic.
5. State the rejection region for the
selected significance level
6. Compute any necessary sample
quantities, substitute into the formula
for the test statistic value, and
compute that value.
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
Hypothesis-Testing Analysis
7. Decide whether H0 should be
rejected and state this conclusion in
the problem context.
The formulation of hypotheses (steps 2
and 3) should be done before examining
the data.
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
Type II Probability ( ) for a Level
Test Type II
Alt. Hypothesis Probability ( )
0
H a : 0 z
/ n
0
H a : 0 1 z
/ n
H a : 0
z / 2
0
z / 2
0
/ n / n
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
Sample Size
The sample size n for which a level
test also has ( ) at the alternative
value is
( z z ) 2
one-tailed test
0
n 2
( z / 2 z )
two-tailed test
0
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
Case II: Large-Sample Tests
When the sample size is large, the z
tests for case I are modified to yield
valid test procedures without
requiring either a normal population
distribution or a known .
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
Large Sample Tests (n > 40)
For large n, s is close to .
X 0
Test Statistic: Z
S/ n
The use of rejection regions for case I
results in a test procedure for which the
significance level is approximately .
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
Case III: A Normal Population
Distribution
If X1,…,Xn is a random sample from a
normal distribution, the standardized
variable X
T
S/ n
has a t distribution with n – 1
degrees of freedom.
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
The One-Sample t Test
Null hypothesis: H 0 : 0
x 0
Test statistic value: t
s/ n
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
The One-Sample t Test
Alternative Rejection Region
Hypothesis for Level Test
H a : 0 t t ,n 1
H a : 0 t t ,n 1
H a : 0 t t / 2,n 1 or t t / 2,n 1
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
A Typical Curve for the t Test
curve for n – 1 df
when
0
Value of d corresponding to
specified alternative to
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
8.3
Tests Concerning
a
Population Proportion
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
A Population Proportion
Let p denote the proportion of
individuals or objects in a
population who possess a specified
property.
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
Large-Sample Tests
Large-sample tests concerning p
are a special case of the more
general large-sample procedures
for a parameter .
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
Large-Samples Concerning p
Null hypothesis: H 0 : p p0
Test statistic value:
pˆ p0
z
p0 1 p0 / n
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
Large-Samples Concerning p
Alternative Rejection Region
Hypothesis
H a : p p0 z z
H a : p p0 z z
H a : p p0 z z / 2 or z z / 2
Valid provided
np0 10 and n(1 p0 ) 10.
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
General Expressions for ( p)
Alt. Hypothesis ( p)
H a : p p0 p0 p z p0 (1 p0 ) / n
p (1 p ) / n
p0 p z p0 (1 p0 ) / n
H a : p p0 1
p (1 p ) / n
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
General Expressions for ( p)
Alt. Hypothesis ( p)
p0 p z p0 (1 p0 ) / n
H a : p p0
p (1 p ) / n
p0 p z p0 (1 p0 ) / n
p (1 p ) / n
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
Sample Size
The sample size n for which a level
test also has ( p) p
z p (1 p ) z p(1 p) 2 one-tailed
0 0
p p0 test
n 2
z / 2 p0 (1 p0 ) z p(1 p) two-tailed
p p0 test
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
Small-Sample Tests
Test procedures when the sample size
n is small are based directly on the
binomial distribution rather than the
normal approximation.
P(type I) 1 B(c 1; n, p0 )
B( p) B(c 1; n, p)
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
8.4
P - Values
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
P - Value
The P-value is the smallest level of
significance at which H0 would be
rejected when a specified test procedure
is used on a given data set.
1. P-value
reject H 0 at a level of
2. P-value
do not reject H 0 at a level of
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
P - Value
The P-value is the probability,
calculated assuming H0 is true, of
obtaining a test statistic value at least as
contradictory to H0 as the value that
actually resulted. The smaller the P-
value, the more contradictory is the data
to H0.
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
P-Values for a z Test
P-value:
1 ( z ) upper-tailed test
P ( z ) lower-tailed test
2 1 ( z ) two-tailed test
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
P-Value (area)
P-value 1 ( z )
Upper-Tailed
P -value ( z ) 0 z
Lower-Tailed
-z 0
P-value 2[1 (| z |)] Two-Tailed
-z 0 z
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
P–Values for t Tests
The P-value for a t test will be a t
curve area. The number of df for the
one-sample t test is n – 1.
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
8.5
Some Comments on
Selecting a
Test Procedure
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
Constructing a Test Procedure
1. Specify a test statistic.
2. Decide on the general form of the
rejection region.
3. Select the specific numerical critical
value or values that will separate the
rejection region from the acceptance
region.
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
Issues to be Considered
1. What are the practical implications
and consequences of choosing a
particular level of significance once
the other aspects of a test procedure
have been determined?
2. Does there exist a general principle
that can be used to obtain best or good
test procedures?
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
Issues to be Considered
3. When there exist two or more tests that
are appropriate in a given situation, how
can the tests be compared to decide
which should be used?
4. If a test is derived under specific
assumptions about the distribution of
the population being sampled, how well
will the test procedure work when the
assumptions are violated?
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
Statistical Versus Practical
Significance
Be careful in interpreting evidence when
the sample size is large, since any small
departure from H0 will almost surely be
detected by a test (statistical significance),
yet such a departure may have little
practical significance.
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
The Likelihood Ratio Principle
1. Find the largest value of the likelihood
for any in 0 .
2. Find the largest value of the likelihood
for any in a .
3. Form the ratio
maximum likelihood for in 0
x1 ,..., xn
maximum likelihood for in a
Reject H0 when this ratio is small.
Copyright (c) 2004 Brooks/Cole, a division of Thomson Learning, Inc.
