•Dr.

Soumen Rej
•Assistant Professor
(Grade-I), Amity
Business School-
Kolkata
•PhD, VGSoM, IIT
Kharagpur
•M.Tech (Silver Medal)
Testing Hypotheses
 • Hypothesis testing begins with an assumption, called
a hypothesis, that we make about a population
parameter.
• Then we collect sample data, produce sample
Function statistics, and use this information to decide how
likely it is that our hypothesized population
of parameter is correct.
• Say that we assume a certain value for a population
hypothesi mean. To test the validity of our assumption, we
s testing gather sample data and determine the difference
between the hypothesized value and actual value of
the sample mean. The smaller the difference, the
greater the likelihood that our hypothesized value for
the mean is correct. The larger the difference, the
smaller the likelihood.
 • Hypothesis is the starting point of research.
• It is an informed/educated guess. It indicates the
expectations of the researcher regarding certain
variables. It is the most specific way in which an answer to
a problem can be stated.
• A hypothesis is an intelligent or educated guess or
proposition, which can be put to test to determine its
validity. In other words it is a logically derived tentative
proposition that needs scientific verification. It tests the
Definition relationships or differences between two or more
variables/constructs.
• Problem vs. hypothesis: A problem is formulated in the
form of a question; it serves as the basis or origin from
which an hypothesis is derived. An hypothesis is a
suggested solution to a problem. A problem (question)
cannot be directly tested, whereas an hypothesis can be
tested and verified.
 The chief
difficulties • (a) lack of knowledge of the problem under
in study,
• (b) absence of knowledge about theoretical
formulating Framework, laws and facts,
hypothesis • (c) lack of ability to utilize the theoretical
framework and existing body of knowledge
are: logically, and
• (d) the failure to be acquainted with the
available research technique, tools and their
limitations so as to phase the hypothesis
properly.
The roof contract for a new sports complex in San Francisco has
been awarded to Parkhill associates, a large building contractor.
Building specification call for a movable roof covered by
approximately 10,000 sheets of 0.04-inch-thick aluminum. The
aluminum sheets cannot be appreciably thicker than 0.04 inch
because the structure could not support the additional weight. Nor
can the sheets be appreciably thinner than 0.04 inch because the
strength of the roof would be inadequate. Because of this
restriction on thickness, Parkhill carefully checks the aluminum
sheets from its supplier. Of course, Parkhill does not want to
measure each sheet, so it randomly samples 100. The sheets in the
sample have a mean thickness of 0.0408 inch. From past
experience with this supplier, Parkhill believes that these sheets
come from a thickness population with a standard deviation of
0.004 inch. On the basis of these data, Parkhill must decide
whether the 10,000 sheets meet specifications.
 • If we assume that the true mean thickness is 0.04 inch,
and we know that the population standard deviation is
0.004 inch, how likely is it that we would get a sample
mean of 0.0408 or more from that population? In other
Formulatin words, if the true mean is 0.04 inch and the standard
deviation is 0.004 inch, what are the chances of getting a
g the sample mean that differs from 0.04 inch by 0.0008 (=
0.0408 – 0.04) inch or more?
hypothesi • These questions show that to determine whether the
population mean is actually 0.04 inch, we must calculate
s the probability that a random sample with a mean of
0.0408 inch will be selected from a population with a μ of
0.04 inch and a σ of 0.004 inch. This probability will
indicate whether it is reasonable to observe a sample like
this if the population mean is actually 0.04 inch.
Calculating
the
standard
error of the
mean
Calculate Z
value
Interpreting
the • Using Appendix Table 1, we learn that 4.5
probability percent is the total chance of our sample mean
differing from the population mean by 2 or
associated more standard errors; that is, the chance that
the sample mean would be 0.0408 inch or
with this larger or 0.0392 inch or smaller is only 4.5 per
cent (P(z >=2 or Z<=-2) = 2(0.5 – 0.4772) =
difference 0.0456, or about 4.5 percent). With this low a
chance, Parkhill could conclude that a
population with a true mean of 0.04 inch would
not be likely to produce a sample like this. The
project supervisor would reject the aluminum
company’s statement about the mean
thickness of the sheets.
t test Table
 • Rejecting a null hypothesis when it is true is called
a Type I error, and its probability (which, as we
have seen, is the also the significance level of the
Type I test) is symbolized as α (alpha).
• Alternatively, accepting a null hypothesis when it is
and Type false is called a Type II error, and its probability is
symbolized β (beta).

II Errors • There is a trade off between these two errors: The

probability of making one type of error can be
reduced only if we are willing to increase the
probability of making the other type of error.
CONDITIONS FOR USING THE NORMAL AND t
DISTRIBUTIONS IN TESTING HYPOTHESES
ABOUT MEANS

When the When the

Population Population
Standard Standard
Deviation is Deviation is Not
Known Known
Sample size n is Normal distribution, Normal distribution,
larger than 30 z table z table
Sample size n is 30 or Normal distribution, t distribution, t
less and we assume z table table
the population is
normal or
approximately so
Description of a
two-tailed
hypothesis test
• A two-tailed test of a
hypothesis will reject
the null hypothesis if
the sample mean is
slightly higher than or
lower than the
hypothesized
population mean.
Left-tailed tests
• In general, a left-tailed
(lower-tailed) test is
used if the hypotheses
are H0 : μ = H0 μ and
H1 : μ < H0 μ .
Right-tailed
tests
• An upper upper-tailed
test is used when the
hypotheses are H0 : μ
= H0 μ and H1 : μ> H0
μ.
Problem statement
• A manufacturer supplies the rear axles for U.S. Postal
Service mail trucks. These axles must be able to withstand
80,000 pounds per square inch in stress tests, but an
excessively strong axle raises production cost significantly.
Long experience indicates the standard deviation of the
strength of its axles is 4,000 pounds per square inch. The
manufacturer selects a sample of 100 axles from production,
tests them and find the mean stress capacity of the sample
is 79600 pounds per square inch. Written symbolically, the
data in this case.
• If the axle manufacturer uses a significance level of 0.05 ,
will the axle meet his stress requirements?
Testing
Hypotheses: Two-
sample Tests
• A manpower-development statistician is asked to
determine whether the hourly wages of
semiskilled workers are the same in two cities.
The results of this survey are presented in Table 9-
1. Suppose the company wants to test the
hypothesis at the 0.05 level that there is no
difference between hourly wages for semiskilled
workers in the two cities.
• Finally, if we had wanted to test whether
wages in Apex were more than ten cents
per hour lower than wages in Eden, then
our hypotheses would have been