Central Limit Theorem Conducting Hypothesis Testing

Statistics is the most commonly used branch of In studying statistics, making decisions based on
mathematics. Central limit theorem is the observations or data that are considered random
cornerstone of it. variables is an essential concept to learn, such
procedure of making decision is called hypothesis
In statistics, the given data set represents a sample testing.
from the entire population. Using this sample, we
try to see the patterns in the data. We then try to Hypothesis Testing
generalize the patterns in the sample to the
population while making the predictions. Central It is a decision-making process for evaluating
limit theorem helps us to make inferences about claims about a population.
the sample and population parameter. It is basically testing an assumption that we can
Central Limit Theorem states that the sampling make about a population.
distribution of the mean approaches a normal A hypothesis is a proposed explanation, assertion,
distribution, as the sample size increases. It also or assumption about a population parameter or
justifies the use of normal curve methods for a about the distribution of a random variable.
wide range of problems.
NULL AND ALTERNATIVE HYPOTHESES

Null Hypothesis Alternative Hypothesis

It is the initial claim It is contrary to the null
based on previous hypothesis, which shows
analyses, which the that observations are the
Formula used when Dealing with data researcher tries to result of a real effect.
dealing with about the sample disprove, reject, or
individual data means nullify.
obtained from the It shows no significant It shows that there is a
population difference/ relationship significant
between two difference/relationship
parameters. between two parameters.

Steps in Solving Sampling distribution of Sample

The null hypothesis is Also known as research
Means
formulated for the hypothesis. This is what
Identify the given information purpose of either the researcher believed to
accepting or rejecting be true. The alternative
Identify what is asked for. the statement. The null hypothesis will be
hypothesis is accepted if accepted if the sample
Identify the formula to be used the sample data failed to data provides an
offer a convincing evidence that null
Solve the problem evidence that is false. hypothesis is false.
State the final answer.

Problem :

In a study of the life expectancy of 400 people in a

certain geographic region, the mean age at death
was 70 years, and the standard deviation was 5.1 Example :
years. If a sample of 50 people from this region is
selected, what is the probability that the mean life The average age of bus drivers in Metro Manila is
expectancy will be less than 68 years? 38.8 years.
What relationship exists between the amount of ✓ Statistician commonly use 1%, 5% or 10%.
sleep and eating habits in kids aged 6 to 12?
✓ Using 0.05 level of significance in testing
hypothesis implies that the probability of
Types of Errors accepting to commit an error in rejecting null
hypothesis is 5%, but the researcher is 95% sure
There is also a possibility of committing an error that the decision made is correct.
in deciding whether to accept of reject the null
hypothesis. ✓ The probability of committing type I error is the
probability of rejecting null hypothesis. It is the
In hypothesis testing, four outcomes are possible; probability that the test statistic will be in
two of which lead to incorrect decisions. rejection region if the null hypothesis is true. (𝛼)
The four possible outcomes are described in the ✓ The probability of committing type II error is
table below ; the probability of accepting a true null hypothesis.
It is the probability that the test statistic will be in
Decision
non-rejection region if the null hypothesis is false.
Correct
decision (𝛽 ).
Correct Acceptance and Rejection of Region
decision
Illustration of the Rejection Region
Type I error: this type of error rejects the null ✓ Test Statistic is used as basis of deciding
hypothesis when in fact it is true. Type I error is whether the null hypothesis should be rejected.
also known as alpha (𝛼) error.
✓ The rejection region (or critical region) is the
Type II error: this type of error fails to reject the set of all values of the test statistic that causes us
null hypothesis when in fact it is false. Type II to reject the null hypothesis.
error is also known as beta (β) error.
✓ The non-rejection region (or acceptance region)
The probability of committing type I error is the
is the set of all values of the test statistic that
probability of rejecting null hypothesis. It is the
causes us to fail to reject the null hypothesis.
probability that the test statistic will be in
rejection region if the null hypothesis is true. The ✓ The critical value is a point (boundary) on the
probability of type I error is called the level of test distribution that is compared to the test
significance. statistic to determine if the null hypothesis would
be rejected.
Level of Significance

✓ The level of significance denoted by alpha or 𝛂

refers to the degree of significance in which we
accept or reject the null hypothesis.

✓ 100% accuracy is not possible in accepting or

rejecting a hypothesis.

✓ The significance level α is also the probability of Two – tailed Test VS. One – tailed Test
making the wrong decision when the null
✓ When the alternative hypothesis is two-sided
hypothesis is true.
like 𝐻𝑎:𝜇≠𝜇, it is called two-tailed test.
✓ The choice of level of significance depends on
✓ When the given statistics hypothesis assumes a
the statistician or researcher who is willing to
less than or greater than value, it is called one-
commit a type I error.
tailed test.
Example : characterizes a given population or some of its
aspects.
The school registrar believes that the average
number of enrollees this school year is not the However, the numerical measure that is
same as the previous school year. calculated from the sample is called statistic.
Statistic is a known number and a variable that
depends on the portion of the population.

A parameter denotes the true value that

would be obtained if a census rather than a
sample was undertaken.
However, if the school registrar believes that the
average number of enrollees this school year is Examples of parameters are the measures of
less than the previous school year, central tendency. These tell us how the data
behave on an average basis.

For example, mean, median, and mode are

measures of central tendency that give us an idea
about where the data concentrate.

Meanwhile, standard deviation tells us

On the other hand, if the school registrar believes how the data are spread from the central
that the average number of enrollees this school tendency, i.e. whether the distribution is wide or
year is greater than the previous school year. narrow. Such parameters are often very useful in
analysis.

Test Statistics
Steps in Hypothesis Testing
A test statistic is a random variable that is
Identify the claim and formulate the null and calculated from sample data and used in a
alternative hypothesis. hypothesis test. You can use test statistics to
determine whether to reject or accept the null
Set the level of significance and determine
hypothesis. The test statistic compares your data
whether the test is one-tailed or two-tailed by
with what is expected under the null hypothesis.
looking at how the alternative hypothesis is
expressed

Compute the test value, using the test statistic or Test for Difference of Two Variables
formula for the test
z-test if the sample size is greater than 30
Make a decision whether to accept or reject the
null hypothesis t-test if the sample size is less than 30

Formulate a conclusion by answering the research Test for Relationship of Two Variables
question. Pearson’s R

Correlation
Parameters in statistics are important component
of any statistical analysis. In simple words, a
parameter is any numerical quantity that