Hypothesis testing

Hypothesis
• Hypothesis simply means a mere
assumption or some supposition to be
proved or disproved
• For researcher hypothesis is a formal
question that he intends to resolve
• Hypothesis may be defined as a
proposition or a set of proposition forth
as an explantion for the occurrence of
some specified group of phenomena

12/08/09 Research methodolgy 2

• Research hypothesis is a predictive
statement ,capable of being tested
by scientific methods

12/08/09 Research methodolgy 3

 Characteristics of
Hypothesis
• Hypothesis should be clear and precise, if not
clear and precise inferences drawn on its
basis cannot be taken as reliable
• Should be capable of being tested
• Should state relationship between variables
• Should be limited in scope and must be
specific

12/08/09 Research methodolgy 4

• Should be stated as far as possible in
most simple terms so that the same
is easily understandable by all
concerned
• Should be consistent with most
known facts
• Must explain the facts that gave rise
to the need for explanation

12/08/09 Research methodolgy 5

 Basic concepts concerning
testing of hypothesis
• Null hypothesis and alternate
hypothesis
• If we are to compare method A with
method B about its superiority and if
we proceed on the assumption that
both methods are equally good, than
this assumption is termed as null
hypothesis

12/08/09 Research methodolgy 6

• As against this, we may think method
A is superior or the method B is
inferior ,we are than stating what is
termed alternate hypothesis
• Null hypothesis h0
• Alternate hypothesis ha

12/08/09 Research methodolgy 7

 The level of significance
• It is always some percentage which
should be chosen with great care
,thought and reason
• In case we take significance level at
5 percent ,than this implies that H0
will be rejected when the sampling
results has a less than o.o5
probability of occurring if H0 is true

12/08/09 Research methodolgy 8

 Test of hypothesis
• Given a hypothesis H0 and an
alternate hypothesis Ha ,we make a
rule which is known as decision rule
according to which we accept H0 or
reject H0

12/08/09 Research methodolgy 9

 Type 1 and type 2 errors
• We may reject H0 when H0 id true
and we may accept H0 when in fact
H0 is not true
• The former is known as type 1 error
and letter as type 2 error

12/08/09 Research methodolgy 10

 Two tailed and one-tailed
tests
• A two tailed test rejects the null
hypothesis ,if the sample mean is
significantly higher or lower than the
hypothesized value of the mean of the
population
• One tailed test would be used when
we are to test, whether population
mean is either lower than or higher
than some hypothesized value
12/08/09 Research methodolgy 11
 Procedure for hypothesis
testing
• Making a formal statement
• The formulation of hypothesis is an
important step which must be
accomplished with due care in
accordance with the object and
nature of the problem under
consideration also indicates whether
we should use a one tailed test or two
tailed test
12/08/09 Research methodolgy 12
 Selecting a significance
level
• The hypothesis are tested on a pre-
determined level of significance and as
such the same should be specifdied
• Generally 5%level or 1% level is adopted
for the purpose
• Factors affecting level of significance
• Magnitude of the difference between
sample means

12/08/09 Research methodolgy 13

• Size of the samples
• Variability of measurements within
samples
• Whether hypothesis is directional or
non-directional

12/08/09 Research methodolgy 14

 Deciding the distribution to
use
• Choice remains between normal
distribution and t-distribution

12/08/09 Research methodolgy 15

 Selecting a random sample
and comting an appropriate
value
• Sample to furnish empirical data

12/08/09 Research methodolgy 16

 Calculation of probability
• The sample result would diverge as
widely as it has from expectations

12/08/09 Research methodolgy 17

 Comparing the probability
• Calculated with the specified value
for

12/08/09 Research methodolgy 18

 Flow diagram for Hypothesis
testing

12/08/09 Research methodolgy 19

12/08/09 Research methodolgy 20
 Test of hypothesis
• Hypothesis testing determines the
validity of the assumption with a
view to choose between two
conflicting hypothesis about the
value of a population parameter

12/08/09 Research methodolgy 21

• Parametric tests or standard tests of
hypothesis
• Non-parametric test or distribution
free test of hypothesis

12/08/09 Research methodolgy 22

• Parametric tests usually assume certain
properties of the parent population from
which we draw samples
• Assumptions like observations come from
a normal population ,sample size is
large ,assumptions about the population
parameters like mean,variance etc
• Must hold good before parametric tests
can be used

12/08/09 Research methodolgy 23

 Non parametric tests
• Because such tests do not depend on
any assumption about the
parameters of the parent population
• Non-parametric tests need more
observations than parametric tests to
achieve the same size of type 1 and
type 2 errors

12/08/09 Research methodolgy 24

 Limitations of the tests of
hypothesis
• Tests should not be used in a
mechanical fashion. testing is not
decision making itself; tests are only
useful aids for decision making
• Tests do not explain the reasons as
to why does differences exist
• Results of significance tests are
based on probabilities

12/08/09 Research methodolgy 25

• Statistical inferenses based on the
significant tests cannot be said to be
entirely correct evidenses concerning
the truth of the hypothesis
• Inference techniques must be
combined with adequate knowledge
of the subject matter along with the
ability of good judgement

12/08/09 Research methodolgy 26

 QUESTIONS

Thank
you

12/08/09 Research methodolgy 27