Engineering Data Analysis

Notes # 14

Steps in Hypothesis Testing – Traditional Method

Suppose that a certain airline company requires the manufacturer of its aircraft to use
rivets whose mean shearing strength exceeds 120 lbs. Each rivet manufacturer that wants
to sell rivets to the aircraft manufacturer must demonstrate that its rivets meet the
required specification, namely, that the mean shearing strength of all the manufacturer’s
rivets, µ, be greater than 120 lbs.

In this illustration, the rivet supplier is interested in demonstrating that the mean shearing
strength of its rivets is greater than 120 (µ > 120). The statistical procedure used to make
this determination is called a hypothesis test.

There are four steps to a conducting a hypothesis test:

STEP 1: Formulate the null and alternative hypothesis

Hypothesis - A statement that something is true

There are 2 hypotheses:

Null Hypothesis - The hypothesis that we will test. Generally this is a statement that a
population parameter has a specific value. The null hypothesis is so
named because it is the starting point for the investigation. The
phrase “there is no difference” is often used in its interpretation.

Symbol:

Null Hypothesis Clue:

Alternative Hypothesis - A statement about the same population parameter that is used
in the null hypothesis. Generally, this is a statement that
specifies that the population parameter has a value different,
in some way, from the value given in the null hypothesis. The
rejection of the null hypothesis will imply the acceptance of
this alternative hypothesis.

Symbol:

Alt. Hypothesis Clue:

There are four possible outcomes in a Hypothesis Test:

Table 1
Null Hypothesis

Decision True False

Fail to reject H0 Type A Type II

Correct Decision Error

Reject H0 Type I Type B

Error Correct Decision

Table 2
Probability with Which Error Occurs

Error Type Error Probability

Rejection of a true hypothesis I 

Failure to reject a false null hypothesis II β

Illustration

The null hypothesis “the airplane is safe” is being tested.

a) Carefully state the meaning of the four possible outcomes in Table 1.

b) Describe the seriousness of the type I error and the type II error.

STEP 2: Determine the Test Criteria

The test criteria consist of:

1) specifying a level of significance, 

2) determining a test statistic
3) determining the critical region(s)
4) determining the critical value(s)

Level of significance - the probability of committing the type I error,  .

Test Statistic - a random variable used to make the decision “fail to reject H0 ” or
“reject H0 ”

Critical Region - The set of values of the test statistic that will cause us to reject the null
hypothesis.

Critical Value - the first (or boundary) value in the critical region

Illustration

If  = 0.05, and our hypothesis is µ > 120, find the critical region and critical value.

STEP 3: Obtain the Sample Data and Calculate the Value of the Test Statistic

It is known that the population standard deviation of all rivets is 12. A sample of 36 rivets
is tested and the resulting measurements yield a sample mean of 124.4. This sample
statistic must now be converted to a z-score. The resulting z-score will be our evidence.

STEP 4: Make a Decision and Interpret It

Make the decision by comparing the value of the calculated test statistic found in Step 3
to the critical value of the test statistic found in Step 2.

Decision Rule

If the test statistic falls within the critical region, we will reject H0 . If the test statistic
does not fall within the critical region, we will fail to reject H0 . Note: The set of values
that are not in the critical region is called the noncritical region, or sometimes, the
acceptance region.
Conclusion Rule

If the decision is “reject H0 ” then the conclusion should be worded “There is sufficient
evidence at the  level of significance to show that... (the meaning of the alternative
hypothesis).”

If the decision is “fail to reject H0 ” then the conclusion should be worded something like
“There is not sufficient evidence at the  level of significance to show that... (the
meaning of the alternative hypothesis).”

The z-Test for a Mean

First, practice formulating the null and alternative hypotheses:

Illustration 1

An ecologist would like to show that Quiapo has an air pollution problem. Specifically,
she would like to show that the mean level of carbon monoxide along the Recto-Quiapo
area air is higher than 4.9 parts per million. State the null and alternative hypotheses.

Illustration 2

In trying to promote the city, the Engineering Office in charge would be more likely to
want to conclude that the mean level of carbon monoxide in the City of Manila is less
than 4.9 parts per million. State the null and alternative hypotheses related to this
viewpoint.

Illustration 9
The “mean level of carbon monoxide in Quiapo is not 4.9 parts per million.” State the
null and alternative hypotheses that correspond to this statement.
Sign in the
Alternative Hypothesis < ≠ >

Critical Region One Region Two Regions One Region

Left Side One on Each Side Right Side
One-Tailed Test Two-Tailed Test One-Tailed Test

NOTES

THE CLASSICAL HYPOTHESIS TEST

Step 1: State the null hypothesis ( H0 ) and the alternative hypothesis ( H a ).

Step 2: Determine the test criteria:

a. The level of significance,  , to be used
b. The test statistic to be used
c. The critical region(s)
d. The critical value(s)

Step 3: Collect and present the sample evidence.

a. Collect the sample information.
b. Calculate the value of the observed test statistic.

Step 4: Determine the results.

a. Compare the calculated value of the test statistic to the critical value(s) from
Step 2.
b. Make a decision about H0 .
c. State the conclusion about H a .
Illustration

For many semesters an instructor has recorded students’ grades, and the mean µ for all
these students’ grades is 72. The current class of 36 students seems to be better than
average in ability and the instructor wants to show that according to their average “the
current class is superior to previous classes.” Does the class mean x of 75.2 present
sufficient evidence to support the instructor’s claim that the current class is superior? Use
 = 0.05 and σ = 12.0.

Illustration

It has been claimed that the mean weight of women students at a college is 54.4 kg.
Professor Santos does not believe the statement that the mean is 54.4 kg. To test the claim
he collects a random sample of 100 weights from among the women students. A sample
mean of 53.75 kg results. Is this sufficient evidence to reject the null hypothesis? Use 
= 0.05 and σ = 5.4 kg.

Illustration

The student body at many community colleges is considered a “commuter population.”

The following question was asked of the Student Affairs Office: “How far (one way)
does the average community college student commute to college daily?” The office
answered: “No more than 9.0 miles.” The inquirer was not convinced of the truth of this
and decided to test the statement. He took a sample of 50 students and found a mean
commuting distance of 10.22 miles. Test the hypothesis stated above at a significance
level of  = 0.05, using σ = 5 miles.
Hypothesis Testing – t-Test for a Mean

When the population standard deviation is unknown and the sample size is less than 30,
the z-score is inappropriate for testing hypotheses. We have to use the t-test.

x − x
t* = df = n –1
s
n

Ex. 1 A manufacturer of sports equipment has developed a new synthetic fishing line
that he claims has a mean breaking strength of 8 kilograms with a standard
deviation of 0.5 kilogram. Test the hypothesis that μ = 8 kilograms against the
alternative that μ < 8 kilograms if a random sample of 16 lines is tested and found
to have a mean breaking strength of 7.7 kilograms. Use α = 0.05 level of
significance.

Ex. 2 A machine is designed to fill jars with 16 ounces of coffee. A consumer suspects
that the machine is not filling the jars completely. The consumer believes it is
less than 16 ounces of coffee. A sample of 8 jars has a mean of 15.5 ounces and a
standard deviation of 0.3 ounces. At  =0.10, test the consumer’s claim.
Ex. 3 A physician claims that joggers’ maximal volume oxygen uptake is greater than
the average of all adults. A sample of 15 joggers has a mean of 43.6 mL per
kilogram and a standard deviation of 6 ml/kg. If the average of all adults is 36.7
ml/kg, test the physician’s claim at  =0.01.

Ex. 4 A researcher collected a random sample of 25 energy bars from a number of

different stores to represent the population of energy bars available to the general
consumer. The labels on the bars claim that each bar contains 20 grams of protein.

20.70 27.46 22.15 19.85 21.29

24.75 20.75 22.91 25.34 20.33

21.54 21.08 22.14 16.56 21.10

18.04 21.12 19.95 19.72 18.28

16.26 15.46 20.53 22.12 25.06

Do the data present sufficient evidence that the mean weight of protein exceed 20 grams?
Test at the 0.01 level of significance.
Exercises
Ex. 1 Most water-treatment facilities monitor the quality of their drinking water on an
hourly basis. One variable monitored is pH, which measures the degree of
alkalinity or acidity in the water. A pH below 7.0 is acidic, one above 7.0 is
alkaline, and a pH of 7.0 is neutral. One water-treatment plant has a target pH of
8.5 (most try to maintain a slightly alkaline level). The mean and standard
deviation of 1 hour’s test results, based on 17 water samples at this plant, are 8.42
and 0.16, respectively. Does this sample provide sufficient evidence that the
mean pH level in the water differs from 8.5?

Ex. 2 On a popular self-image test, which results in normally distributed scores, the
mean score for public assistance recipients is expected to be 65. A random
sample of 28 public-assistance recipients in Emerson County is given the test.
They achieve a mean score of 62.1, and their scores had a standard deviation of
5.83. Do the Emerson County public assistance recipients test lower, on average,
than what is expected, at the 0.02 level of significance?

Ex. 3 A major car manufacturer wants to test a new engine to determine whether it
meets new air-pollution standards. The mean emission of all engines of this type
must be less than 20 parts per million of carbon. Ten engines are manufactured
for testing purposes, and the emission level of each is determined. The data (in
parts per million) are listed below:

15.6 16.2 22.5 20.5 16.4 19.4 16.6 17.9 12.7 13.9