You are on page 1of 47

GRR 7501 Statistical

Methods Applied to
Research
DR. REBECCA V. PINEDA
Faculty, Graduate School
Suppose you met a person
who is feeling unwell and
somewhat coughing with
difficulty, what would be
your reaction? What would
you think?
Are you done with all the anti-
covid vaccine? Why?
HYPOTHESIS
- an educated guess that is subjected for testing
- a tentative explanation, a claim or assertion about people,
objects or events.
TYPES OF HYPOTHESIS
1. NULL HYPOTHESIS (Ho) is a statement about a population parameter
developed for the purpose of testing numerical evidence

There usually a “not” or a “no” term in a null hypothesis


meaning there is no change.
Example:
The mean number of miles driven on the steel-belted tire
is not different from 60,000.

“There is no significant difference between…” or The


mean impact significant strength of the glass is not
significantly different from…”
2. Alternative Hypothesis
A statement that is accepted if the sample data provide sufficient
evidence that the null hypothesis is false.
“Research hypothesis”
Example:
The mean number of miles driven on the steel-belted tire is different
from 60,000.
Sample Research Topic and/or Titles

 The effect of sales promotion strategies on local make-up brands

Null Hypothesis: There is no significant effect of sales promotion strategies on local make-up brands.

Alternative Hypothesis: There is a significant effect of sales promotion strategies on local make-up brands.

 Comparative study on efficiency of service, between traditional


and kiosk ordering system of McDonald’s.

Null Hypothesis: There is no significant difference on the efficiency of service, between traditional and
kiosk ordering system of McDonald’s.

Alternative Hypothesis: There is a significant difference on the efficiency of service, between traditional
and kiosk ordering system of McDonald’s.
Sample Research Topic and/or Titles

 The effect of binge-watching Netflix Series on the social skills of


the UE SHS Grade 12 students
Null Hypothesis: There is no significant effect of binge-watching Netflix Series on the social skills of
the UE SHS Grade 12 students

Alternative Hypothesis: There is a significant effect of binge-watching Netflix Series on the social skills of the UE
SHS Grade 12 students

 On-line Classes vs. Traditional Face-to-face classes on the academic


performance of UE SHS students
Null Hypothesis: There is no significant difference on the academic performance between On-line and
Traditional Face-to-face classes of the UE SHS students
Alternative Hypothesis: There is a significant difference on the academic performance between On-line
and Traditional Face-to-face classes of the UE SHS students
A chemist invents an additive to increase the life of an
automobile battery. If the mean lifetime of automobile
battery without additive is 36 months. Then write
hypothesis
A contractor wishes to lower heating bills by using a
special type of insulation in houses. If the average of
the monthly heating bills is Php 576, write the
hypothesis about the heating costs with the use of
insulator
A psychologist feels that playing soft music during
a test will change the results of the test. The
psychologist is not sure whether the grades will
be higher or lower . In the past the mean score
was 73.
Stating the null and alternative hypothesis in symbols

1. A teacher wants to know if listening to popular music affects the performance of students. A
class of 40 SHS students was used in the experiment. A previous study revealed that the
average score is 82 with a standard deviation of 10. State the null and alternative hypothesis
in symbols.

2. A farmer believes that using organic fertilizers on his plants will yield greater income.
His average income from the past was Php. 200, 000.00 per year. State the null and
alternative hypothesis in symbols.
Level of Significance
Level of significance or level of risk is the probability of rejecting the
null hypothesis when it is true.
0.05 level - selected consumer research project
0.01 level – quality assurance
0.10 level – political polling

Level of Confidence (C) C = 1-


0.95 level
0.99 level
0.90 level
The four possible outcomes of decision-making concerning
rejection of the null hypothesis
Researcher’s Decision

Null Does not Rejects


Type I Error. Rejecting
the null hypothesis Hypothesis Reject
when it is true.
is true Correct Type I Error
Type II Error. Accepting decision
the null hypothesis when
it is false.
is false Type II Error Correct
decision
)
TE
S
SIG T O
NI F
FIC
AN
CE
Critical Value. The dividing point between the region
where the null hypothesis is rejected and the region
where it is not rejected.

The Critical Values of z in testing hypothesis are as follows:


Directional
(Left-tailed)

Directional
(Right-Tailed)

Non-Directional
HYPOTHESIS TESTING
• Hypothesis testing is a decision-making process for
evaluating claims about a population.
• Starts with the statement, or assumption, about a
population parameter such as the population mean.
• A procedure based on sample evidence and probability
theory to determine whether the hypothesis is a
reasonable statement.
Four assumptions of parametric tests
 Normal distribution of the dependent
variable
 Interval or ratio data
 Independence of subjects
 Homogeneity of variance
Advantages of parametric tests
 statistically more powerful and versatile
Assumptions of nonparametric tests
 No assumptions about the shape of the
distribution of the dependent variable
 Ordinal or categorical data 
Disadvantages of nonparametric tests
 Less statistically powerful
 Require large samples
 Cannot answer some research questions
Five –Step Procedure for Testing a Hypothesis

1. State the Null Hypothesis and the


Alternate Hypothesis
2. Identify the level of significance, type of
test, critical values
3. Select the Test Statistic
Test Statistic . A value, determined from sample
information, used to determine whether to
reject the null hypothesis. (e.g. z-test, t-test, etc.)
Testing a Mean, Known
Difference between sample means

𝑥 1 − 𝑥2
𝑧=


2 2
𝑠1 𝑠2
+
𝑛1 𝑛2
4. Formulate the Decision Rule
Critical Value. The dividing point between the
region where the null hypothesis is rejected
and the region where it is not rejected.

5. MAKE A DECISION
Computing the test statistic, comparing it to the
critical value, and making a decision to reject or not
to reject the null hypothesis.
Example 1:

The following information is available

The sample mean is 49 , and the sample size is


36. The population standard deviation is 5. Use
the .05 significance level.
1.) The following information is available

The sample mean is 49 , and the sample size is 36. The population standard deviation is 5. Use the .05 significance
level.

1.

2. 𝛼=0.05 𝑡𝑤𝑜− 𝑡𝑎𝑖𝑙𝑒𝑑 𝑡𝑒𝑠𝑡


3. 𝐶𝑟𝑖𝑡𝑖𝑐𝑎𝑙 𝑉𝑎𝑙𝑢𝑒 :± 1.96

4. Test Statistic
Example 2:

A sample of 36 observations is selected from a normal


population. The population mean is 24 with standard
deviation of 5. A researcher want to prove that the
given mean is not true, thus conducted an
investigation which resulted to a sample mean of 21.
Conduct the following test of hypothesis using the .o5
significance level.
2. A sample of 36 observations is selected from a normal population. The population mean is 24 with standard deviation of
5. A researcher want to prove that the given mean is not true, thus conducted an investigation which resulted to a sample
mean of 21. Conduct the following test of hypothesis using the .05 significance level.

1. 𝛼
𝛼
2
2

2. 𝛼=0.05 𝑡𝑤𝑜− 𝑡𝑎𝑖𝑙𝑒𝑑 𝑡𝑒𝑠𝑡


3. 𝐶𝑟𝑖𝑡𝑖𝑐𝑎𝑙 𝑉𝑎𝑙𝑢𝑒 :± 1.96

4. Test Statistic
Example 3:
Automotive engineers tested the gas mileage (in kilometers
per liter or km/L) of a passenger car model from a certain
company. A random sample of 38 cars resulted to a mean
gas mileage of 16 km/L and a standard deviation of 3.5
km/L. The car company claims that the passenger car model
has an average gas mileage of 18 km/L. Test if the claim is
valid at 95% level of confidence.
1.

2. 𝛼=0.05 𝑙𝑒𝑓𝑡 − 𝑡𝑎𝑖𝑙𝑒𝑑 𝑡𝑒𝑠𝑡 the passenger car model has an


average gas mileage not equal to
3. 𝐶𝑟𝑖𝑡𝑖𝑐𝑎𝑙 𝑉𝑎𝑙𝑢𝑒 :−1.645 18km./L.

4. Test Statistic
4. The cashier department of VQT University claims that
the mean monthly salary of their employees is Php 22,
500.00 or more with a standard deviation of Php 7000.00.
A researcher takes a random sample of 80 employees and
found out that they have a mean monthly salary of Php
18,750.00. Do the 80 selected employees have lower
salaries than the rest? Test the claim at 5% level of
significance.
4. The cashier department of VQT University claims that the mean monthly salary of their employees is Php 22,
500.00 or more with a standard deviation of Php 7000.00. A researcher takes a random sample of 80 employees and
found out that they have a mean monthly salary of Php 18, 750.00. Do the 80 selected employees have lower
salaries than the rest? Test the claim at 5% level of significance.

2. left-tailed test
3.

4.
Difference between two sample means

𝑥 1 − 𝑥2
𝑧=


2 2
𝑠1 𝑠2
+
𝑛1 𝑛2

Ex. 1. A sample of 50 observation is selected from a normal population with a sample


mean of 3.75 and a sample standard deviation of 0.65. Another sample of 60 observations
is selected from a normal population with a sample mean of 3.60 and a sample standard
deviation of 0.55. Test the hypothesis that at 5 % level of significance.
Ex. 1. A sample of 50 observation is selected from a normal population with a sample
mean of 3.75 and a sample standard deviation of 0.65. Another sample of 60 observations
is selected from a normal population with a sample mean of 3.60 and a sample standard
deviation of 0.55. Test the hypothesis that at 5 % level of significance.

1. ( The 1st sample mean is equal to the 2nd sample mean)


( The 1st sample mean is not equal to the 2nd sample mean)

2.

3. Critical Values: -1.96 and 1.96 5. Decision:


The computed value of z is 1.29 and it lies
4. Test Statistic under the acceptance region. Thus, base from the
given data, it is not sufficient to reject the null
hypothesis. Hence, there is no significant
difference between the two sample means.
Testing for a Population Mean :
Population Standard Deviation Unknown

Testing a Mean, Unknown Usually n < 30

With n-1 degrees of freedom


Where:
– sample mean
- hypothesized population mean
s - sample standard deviation
n- number of observations in the sample
Characteristics of the t-distribution:
1. It is a continuous distribution.
2. It is bell-shaped and symmetrical.
3. There is a family of t distributions. Each time the degrees
of freedom change, a new distribution is created.
4. As the number of degrees of freedom increases the
shape of the t distribution approaches that of the
standard normal distribution.
5. The t distribution is flatter, or more spread out , than the
standard normal distribution.
1. The School’s Division Superintendent claims that elementary
teachers work an average of 40 hours per week during the school
year. A superintendent from a certain province surveyed 20
randomly selected teachers and found that they work for an
average of 41.5 hours a week with a standard deviation of 2.5
hours. Test if the mean number of the teacher’s work hours
recorded by the supervisor ‘s school district differs from the
recorded national average. Use
1.

2. Critical Values:
4. Test Statistic

5. Decision:
The computed value of is 2.68 and it lies under the rejection region.
Hence, reject the null hypothesis. Therefore, the average working hours of
elementary teachers is not 40 hours.
2. Farland Inssurance Company Claims Department reports that the
mean cost to process a claim is Php 60. An industry comparison
showed this amount to be larger than most other insurance
companies, so the company instituted cost-cutting measures. To
evaluate the effect of the cost-cutting measures, the supervisor of
the Claims Department selected a random sample of 26 claims
processed last month with a sample mean of Php 55 with a standard
deviation of 2.5. Test whether the claim of the company is valid with
a 95 % level of confidence.
1.

2. Critical Values:
4. Test Statistic

5. Decision:
The computed value of is -10.20 and it lies under the rejection region.
Hence, reject the null hypothesis. Therefore, the average cost to process a
claim is less than Php 60.
References:

Bluman, Allan G. ( 2016) . Elementary statistics a step by step approach. Seventh edition. Mc
Graw Hill, New York.

Cardenas, M.C. and Gabuyo, Y.A., Statistics and Probability, The Inteligente Publishing, Inc. 2016

Ocampo, S.R. and Tresvalles, R.M., Probability, Statistics and Applications, Abiva Publishing House,
Inc., 2017

Baltazar, E.C., Ragasa, C.,and Evangelista, J., Mathematics in the Modern World, C&E Publishing,
Inc. 2018

You might also like