Chapter 5: Hypothesis Testing

and Statistical Inference

© 2007 Pearson Education

Hypothesis Testing
 Hypothesis testing involves drawing
inferences about two contrasting propositions
(hypotheses) relating to the value of a
population parameter, one of which is
assumed to be true in the absence of
contradictory data.
 We seek evidence to determine if the
hypothesis can be rejected; if not, we can
only assume it to be true but have not
statistically proven it true.
Hypothesis Testing Procedure
1. Formulate the hypothesis
2. Select a level of significance, which defines
the risk of drawing an incorrect conclusion
that a true hypothesis is false
3. Determine a decision rule
4. Collect data and calculate a test statistic
5. Apply the decision rule and draw a
conclusion
Hypothesis Formulation
 Null hypothesis, H0 – a statement that is
accepted as correct
 Alternative hypothesis, H1 – a proposition that
must be true if H0 is false
 Formulating the correct set of hypotheses
depends on “burden of proof” – what you wish
to prove statistically should be H1
 Tests involving a single population parameter
are called one-sample tests; tests involving two
populations are called two-sample tests.
 Types of Hypothesis Tests
 One Sample Tests
 H0 : population parameter  constant vs.
H1 : population parameter < constant
 H0 : population parameter  constant vs.
H1 : population parameter > constant
 H0 : population parameter = constant vs.
H1 : population parameter  constant
 Two Sample Tests
 H0 : population parameter (1) - population parameter (2)  0 vs.
H1 : population parameter (1) - population parameter (2) <0
 H0 : population parameter (1) - population parameter (2)  0 vs.
H1 : population parameter (1) - population parameter (2) >0
 H0 : population parameter (1) - population parameter (2) = 0 vs.
H1 : population parameter (1) - population parameter (2) 0
 Four Outcomes
1. The null hypothesis is actually true, and the test
correctly fails to reject it.
2. The null hypothesis is actually false, and the
hypothesis test correctly reaches this conclusion.
3. The null hypothesis is actually true, but the
hypothesis test incorrectly rejects it (Type I
error).
4. The null hypothesis is actually false, but the
hypothesis test incorrectly fails to reject it (Type
II error).
Quantifying Outcomes
 Probability of Type I error (rejecting H0 when
it is true) =  = level of significance
 Probability of correctly failing to reject H0 = 1
–  = confidence coefficient
 Probability of Type II error (failing to reject
H0 when it is false) = 
 Probability of correctly rejecting H0 when it is
false = 1 – = power of the test
Decision Rules
 Compute a test statistic from sample data and
compare it to the hypothesized sampling
distribution of the test statistic
 Divide the sampling distribution into a
rejection region and non-rejection region.
 If the test statistic falls in the rejection
region, reject H0 (concluding that H1 is true);
otherwise, fail to reject H0
Rejection Regions
 Hypothesis Tests and
Spreadsheet Support
Type of Test Excel/PHStat Procedure

One sample test for mean,  unknown PHStat: One Sample Test – Z-test for
the Mean, Sigma Known
One sample test for mean,  unknown PHStat: One Sample Test – t-test for the
Mean, Sigma Unknown
One sample test for proportion PHStat: One Sample Test – Z-test for
the Proportion
Two sample test for means,  known Excel z-test: Two-Sample for Means
PHStat: Two Sample Tests – Z-Test for
Differences in Two Means
Two sample test for means,  unknown, Excel t-test: Two-Sample Assuming
unequal Unequal Variances
 Hypothesis Tests and
Spreadsheet Support (cont’d)
Type of Test Excel/PHStat Procedure

Two sample test for means,  unknown, Excel t-test: Two-Sample Assuming
assumed equal Equal Variances
PHStat: Two Sample Tests – t-Test for
Differences in Two Means

Paired two sample test for means Excel t-test: Paired Two-Sample for
Means

Two sample test for proportions PHStat: Two Sample Tests – Z-Test for
Differences in Two Proportions
Equality of variances Excel F-test Two-Sample for Variances
PHStat: Two Sample Tests – F-Test for
Differences in Two Variances
One Sample Tests for Means –
Standard Deviation Unknown
 Example hypothesis
 H0:   0 versus H1:  < 0
 Test statistic:
x  0
t
s/ n

 Reject H0 if t < -tn-1, 

 Example
 For the Customer Support Survey.xls data, test the
hypotheses
 H0: mean response time  30 minutes
 H1: mean response time < 30 minutes
 Sample mean = 21.91; sample standard deviation =
19.49; n = 44 observations

 Reject H0 because t = –2.75 < -t43,0.05 = -1.6811

PHStat Tool: t-Test for Mean
 PHStat menu > One Sample
Tests > t-Test for the Mean,
Sigma Unknown
Enter null hypothesis and alpha
Enter sample statistics or data
range
Choose type of test
Results
 Using p-Values
 p-value = probability of obtaining a test
statistic value equal to or more extreme than
that obtained from the sample data when H0
is true

0 0

Test Statistic Test Statistic

Lower one-tailed test Two-tailed test

One Sample Tests for
Proportions
 Example hypothesis
 H0:   0 versus H1:  < 0
 Test statistic:
p 0
z
 0 (1   0 )
 Reject if z < -z
 Example
 For the Customer Support Survey.xls data, test the hypothesis that the
proportion of overall quality responses in the top two boxes is at least
0.75
 H0:   
 H0:  < 
 Sample proportion = 0.682; n = 44

 For a level of significance of 0.05, the critical value of z is -1.645;

therefore, we cannot reject the null hypothesis
PHStat Tool: One Sample z-
Test for Proportions
 PHStat > One Sample Tests > z-Tests
for the Proportion
Enter null hypothesis,
significance level, number
of successes, and sample
size
Enter type of test
Results
Type II Errors and the Power
of a Test
 The probability of a Type II error, , and the
power of the test (1 – ) cannot be chosen by
the experimenter.
 The power of the test depends on the true
value of the population mean, the level of
confidence used, and the sample size.
 A power curve shows (1 – ) as a function of

Example Power Curve
Two Sample Tests for Means –
Standard Deviation Known
 Example hypothesis
 H0:  – 2  0 versus H1:  - 2 < 0
 Test Statistic:
x1  x 2
z
 12 / n1   22 / n2

 Reject if z < -z

Two Sample Tests for Means –
Sigma Unknown and Equal
 Example hypothesis
 H0:  – 2  0 versus H1:  - 2 > 0
 Test Statistic:
x1  x 2
z
(n1  1) s12  (n2  1) s 22 n1  n2

n1  n 2  2 n1 n2

 Reject if z > z
Two Sample Tests for Means –
Sigma Unknown and Unequal
 Example hypothesis
 H0:  – 2 = 0 versus H1:  - 2  0
 Test Statistic:
s12 s 22
t = (x1 - x2 ) / 
n1 n2
2
 s12 s 22 
  
 n1 n2 
with df =
 ( s12 / n1 ) 2   ( s 22 / n2 ) 2 
   
 1 n  1   2 n  1 

 Reject if z > z or z < - z

Excel Data Analysis Tool: Two
Sample t-Tests
 Tools > Data Analysis > t-test: Two Sample
Assuming Unequal Variances, or t-test: Two
Sample Assuming Equal Variances
 Enter range of data, hypothesized mean
difference, and level of significance
 Tool allows you to test H0: 1 - 2 = d
 Output is provided for upper-tail test only
 For lower-tail test, change the sign on t
Critical one-tail, and subtract P(T<=t) one-tail
from 1.0 for correct p-value
PHStat Tool: Two Sample
t-Tests
 PHStat > Two Sample Tests > t-Test
for Differences in Two Means
 Test assumes equal variances
 Must compute and enter the sample
mean, sample standard deviation, and
sample size
Comparison of Excel and PHStat
Results – Lower-Tail Test
Two Sample Test for Means
With Paired Samples
 Example hypothesis
 H0: average difference = 0 versus
 H1: average difference  0
 Test Statistic:
D  D
t
sD / n

 Reject if t > tn-1, or t < - tn-1,

Two Sample Tests for
Proportions
 Example hypothesis
 H0:  – 2 = 0 versus H1:  - 2  0
 Test Statistic:
p1  p 2
z
1 1
p (1  p )  
 n1 n2 
number of successes in both samples
where p
n1  n 2

 Reject if z > z or z < - z

Hypothesis Tests and
Confidence Intervals
 If a 100(1 – )% confidence interval contains
the hypothesized value, then we would not
reject the null hypothesis based on this value
with a level of significance .
 Example hypothesis
 H0:   0 versus H1:  < 0
 If a 100(1-)% confidence interval does not
contain 0, then we can reject H0
F-Test for Differences in Two
Variances
 Hypothesis
 H0:  – 2 2= 0 versus H1:  - 22  0
 Test Statistic: 2
s
F 1
2
s 2
 Assume s12 > s22
 Reject if F > Fn1-1,n2-1 (see Appendix A.4)
 Assumes both samples drawn from normal
distributions
Excel Data Analysis Tool: F-
Test for Equality of Variances
 Tools > Data Analysis > F-test for
Equality of Variances
 Specify data ranges
 Use /2 for the significance level!
 If the variance of Variable 1 is greater
than the variance of variable 2, the
output will specify the upper tail;
otherwise, you obtain the lower tail
information.
PHStat Tool: F-Test for
Differences in Variances
 PHStat menu > Two Sample Tests > F-
test for Differences in Two Variances
 Compute and enter sample standard
deviations
 Enter the significance level , not /2
as in Excel
Excel and PHStat Results
Analysis of Variance (ANOVA)
 Compare the means of m different
groups (factors) to determine if all are
equal
 H0: m
 H1: at least one mean is different from the
others
 ANOVA Theory
 nj = number of observations in sample j
nj
 SST = total variation in the data n
SST   ( X ij  X ) 2
j 1 i 1

 SSB = variation between groups n

SSB   n j ( X j  X ) 2
j 1
 SSW = variation within groups n nj

SSW    ( X ij  X j ) 2
j 1 i 1

SST = SSB + SSW

ANOVA Test Statistic
 MSB = SSB/(m – 1)
 MSW = SSW/(n – m)
 Test statistic: F = MSB/MSW
 Has an F-distribution with m-1 and n-m
degrees of freedom
 Reject H0 if F > F/2,m-1,n-m
Excel Data Analysis Tool for
ANOVA
 Tools > Data Analysis > ANOVA: Single
Factor
ANOVA Results
ANOVA Assumptions
 The m groups or factor levels being studied
represent populations whose outcome
measures are
 Randomly and independently obtained
 Are normally distributed
 Have equal variances
 Violation of these assumptions can affect the
true level of significance and power of the
test.
Nonparametric Tests
 Used when assumptions (usually
normality) are violated. Examples:
 Wilcoxon rank sum test for testing
difference between two medians
 Kurskal-Wallis rank test for determining
whether multiple populations have equal
medians.
 Both supported by PHStat
Tukey-Kramer Multiple
Comparison Procedure
 ANOVA cannot identify which means
may differ from the rest
 PHStat menu > Multiple Sample Tests >
Tukey-Kramer Multiple Comparison
Procedure

Enter Q Statistic from Table A.5

Chi-Square Test for
Independence
 Test whether two categorical variables
are independent
 H0: the two categorical variables are
independent
 H1: the two categorical variables are
dependent
Example
 Is gender independent of holding a CPA
in an accounting firm?
Chi-Square Test for
Independence
Test statistic  2  ( fo  fe )2



fe
where f0 = observed frequency

fe = expected frequency if H0 true

in the cells of the contingency table
 Reject H0 if 2 > 2, (r-1)(c-1)
 PHStat tool available in Multiple Sample
Tests menu
Example
Expected No CPA CPA Total
Female 6.74 7.26 14
Male 6.26 6.74 13
Total 13 14 27

Critical value with  = 0.05 and (2 - 1)(2 - 1) - 1 df =

3.841; therefore, we cannot reject the null hypothesis
that the two categorical variables are independent.
PHStat Procedure Results
Design of Experiments
 A test or series of tests that enables the
experimenter to compare two or more
methods to determine which is better,
or determine levels of controllable
factors to optimize the yield of a
process or minimize the variability of a
response variable.
 Factorial Experiments
 All combinations of levels of each factor are considered.
With m factors at k levels, there are km experiments.
 Example: Suppose that temperature and reaction time
are thought to be important factors in the percent yield
of a chemical process. Currently, the process operates
at a temperature of 100 degrees and a 60 minute
reaction time. In an effort to reduce costs and improve
yield, the plant manager wants to determine if changing
the temperature and reaction time will have any
significant effect on the percent yield, and if so, to
identify the best levels of these factors to optimize the
yield.
Designed Experiment
 Analyze the effect of two levels of each
factor (for instance, temperature at 100
and 125 degrees, and time at 60 and 90
minutes)
 The different combinations of levels of
each factor are commonly called
treatments.
Treatment Combinations

Low High

Low

High
Experimental Results
Main Effects
 Measures the difference in the response that results
from different factor levels
 Calculations
 Temperature effect = (Average yield at high level) – (Average yield at low
level)
= (B + D)/2 – (A + C)/2
= (90.5 + 81)/2 – (84 + 88.5)/2
= 85.75 – 86.25 = –0.5 percent.
 Reaction effect = (Average yield at high level) – (Average yield at low level)
= (C + D)/2 – (A + B)/2
= (88.5 + 81)/2 – (84 + 90.5)/2
= 84.75 – 87.25 = –2.5 percent.
Interactions
 When the effect of changing one factor
depends on the level of other factors.
 When interactions are present, we
cannot estimate response changes by
simply adding main effects; the effect
of one factor must be interpreted
relative to levels of the other factor.
Interaction Calculations
 Take the average difference in response
when the factors are both at the high or low
levels and subtracting the average difference
in response when the factors are at opposite
levels.
 Temperature × Time Interaction
= (Average yield, both factors at same level) –
(Average yield, both factors at opposite levels)
= (A + D)/2 – (B + C)/2
= (84 + 81)/2 – (90.5 + 88.5)/2 = -7.0 percent
Graphical Illustration of
Interactions
 Two-Way ANOVA
 Method for analyzing variation in a 2-factor
experiment
 SST = SSA + SSB + SSAB + SSW
where
SST = total sum of squares
SSA = sum of squares due to factor A
SSB = sum of squares due to factor B
SSAB = sum of squares due to interaction
SSW = sum of squares due to random variation (error)
Mean Squares
 MSA = SSA/(r – 1)
 MSB = SSB/(c – 1)
 MSAB = SSAB/(r-1)(c-1)
 MSW = SSW/rc(k-1),
where k = number of replications of
each treatment combination.
 Hypothesis Tests
 Compute F statistics by dividing each mean square
by MSW.
 F = MSA/MSW tests the null hypothesis that means for
each treatment level of factor A are the same against
the alternative hypothesis that not all means are equal.
 F = MSB/MSW tests the null hypothesis that means for
each treatment level of factor A are the same against
the alternative hypothesis that not all means are equal.
 F = MSAB/MSW tests the null hypothesis that the
interaction between factors A and B is zero against the
alternative hypothesis that the interaction is not zero.
Excel Anova: Two-Factor with
Replication
Results

Examine p-
values for
significance