TESTING OF HYPOTHESIS:

STATISTICAL HYPOTHESIS:
A Statistical hypothesis is a statement or assumption about a
population- parameter or a population distribution.
This hypothesis is to be verified based on the available information.
For a researcher a hypothesis is a formal question or predictive
statement that can be tested by scientific methods.
For instance, in a study of smoking and lung cancer, the statistical
hypothesis could be “there is association between smoking and lung
cancer” or “development of lung cancer is associated with smoking”.
Characteristics of statistical hypothesis:
A hypothesis should be clear and precise, explain facts, state the
relationship between variables, amendable to statistical testing.
NULL HYPOTHESIS:
It is denoted by the symbol H0, assumes that there is no statistically
significant difference between the population parameters.
In general, H0 suggests an absence of difference, association or the
effect, the negotiation of which provides evidence for presence of
difference, association or effect.
The basic question asked while testing a hypothesis is – “ is the sample
evidence strong enough to reject H0 ?”.
H0 Will be rejected only if there is strong sample evidence against it.
If the sample evidence is not strong enough, H0 cannot be rejected and
so H0 is accepted by default.
ALTERNATIVE HYPOTHESIS:
It is denoted by symbol H1 .
Alternative hypothesis is accepted when null hypothesis is rejected due
to a strong statistical-evidence against the null hypothesis.
Both H0 and H1 cannot be true; only one of them will always be true.
 Null hypothesis (H0): There’s no effect in the population.
 Alternative hypothesis (Ha or H1): There’s an effect in the
population.

Example of Hypothesis:
In a study there are 2 groups of children, with group 1 receiving routine
diet and group 2 receiving routine diet with dietary supplements.
The mean weights (μ1 and μ2) and variance (σ1 2, σ2 2) are estimated.
NULL HYPOTHESIS:
The null hypothesis would be: H0 : μ1 = μ2 .
This indicates that the mean weights of the two groups are equal or
there is no change in the mean weights of two groups.
It implies that the nutritional supplements are not effective in
increasing the weights of children.
ALTERNATIVE HYPOTHESIS:
H1 : μ1 ≠ μ2 (the mean weight of group 1 is more than or less than that
of group 2)
H1: μ1 >μ2 (the mean weight of group 1 is more than that of group 2)
H1:μ1<μ2 (the mean weight of group 1 is less than that of group 2)
ESTIMATION:
It is the process by which inferences are made about a population,
based on information obtained from a sample.
For example, sample means are used to estimate population means.
An estimate of population parameter may be expressed as:
POINT ESTIMATE: A point estimate of a population parameter is a single
value of statistic.
INTERVAL ESTIMATE: An interval estimate is defined by two numbers,
between which a population-parameters is said to lie.
For example, a < μ < b is an interval estimate of the population mean μ.
It indicates that the population mean is greater than a; but less than b.
LEVEL OF SIGNIFICANCE:
The level of significance, often denoted by the symbol α (alpha), is a
threshold value used in hypothesis testing to determine the likelihood
of rejecting the null hypothesis when it is actually true.
When conducting a hypothesis test, if the probability of obtaining the
observed data or more extreme data under the assumption that the
null hypothesis is true (p-value) is less than the chosen level of
significance (α), then the null hypothesis is rejected. Conversely, if the
p-value is greater than α, then the null hypothesis is not rejected.
It represents the maximum acceptable probability of making a Type I
error, which is the error of rejecting the null hypothesis when it is true.
The level of significance is always expressed as a percentage. Commonly
used levels of significance are 5 % and 1%.
If the level of significance is taken at 5%, the researcher can take the
risk of rejecting the null hypothesis, if the sampling result has less than
0.05 probability (p < 0.05) of occurring even if H0 is true.
If the level of significance is taken at 1%, the sampling result has less
than 0.001 or 0.01 probability (p < .01 or p <0.001 of occurring,
respectively, even if H0 is true.
Example: Let us consider a study of association between smoking and
lung cancer. If there is an association between smoking and lung cancer
at 5% level of significance, it means that smoking would be associated
with lung cancer in 95 out of 100 lung cancer patients.
CRITICAL REGION:
A critical region, also known as the rejection region, is a set of values for
the test statistic for which the null hypothesis is rejected.
i.e. if the observed test statistic is in the critical region, then we reject
the null hypothesis and accept the alternative hypothesis.
If the test statistic is more extreme than the critical value, the null
hypothesis is rejected. If the test statistic is not as extreme as the critical
value, the null hypothesis is not rejected. The critical value is computed
based on the given significance level α and the type of probability
distribution. The critical value divides the area under the probability
distribution curve in rejection region(s) and non-rejection region.

TAIL OF TEST:
The tail of a test refers to the area(s) under the probability distribution
curve that represent extreme values of the test statistic.
ONE TAILED TEST
In a one-tailed test, there is only one tail of interest, which is either the
right tail or the left tail of the distribution, depending on the direction
specified by the alternative hypothesis.
When using a one-tailed test, the analyst is testing for the possibility of
the relationship in one direction of interest and completely disregarding
the possibility of a relationship in another direction.
For a right-tailed test, the critical region (the tail) is on the right side of
the distribution. This is used when the alternative hypothesis suggests
that the population parameter is greater than the value specified in the
null hypothesis.
For a left-tailed test, the critical region (the tail) is on the left side of the
distribution. This is used when the alternative hypothesis suggests that
the population parameter is less than the value specified in the null
hypothesis.

TWO TAILED TEST:

In a two-tailed test, both tails of the distribution are of interest.
This is used when the alternative hypothesis suggests that the
population parameter is different from the value specified in the null
hypothesis, but without specifying whether it is greater or less than the
null value.
If the sample being tested falls into either of the critical areas, the
alternative hypothesis is accepted instead of the null hypothesis.
By convention two-tailed tests are used to determine significance at the
5% level, meaning each side of the distribution is cut at 2.5%.
In a two-sided test the null hypothesis is rejected, if the test statistic is
either too small or too large. Thus, the rejection region for such a test
consists of two parts: one on the left and one on the right.
For a left-tailed test the null hypothesis is rejected, if the test statistic is
too small. Thus, the rejection region for such a test consists of one part,
which is left from the center.
For a right-tailed test the null hypothesis is rejected, if the test statistic
is too large. Thus, the rejection region for such a test consists of one
part, which is right from the center.

TYPE I AND TYPE II ERROR