Statistical

Analysis
Judequi M. Aquino, LPT
 Objectives

At the end of the Sampling Techniques

session, the participants Levels of Measurement
are expected to learn to
decide and choose the Test of Normality
appropriate statistical Hypothesis Testing
test for analysis of
research data. Basic Statistical Tests
Branches of Statistics: Quick Review

Statistics Science which deals with the collection,

analysis, interpretation, and
presentation of numeric data.

Descriptive Technique that allows us to summarize a

given data set representative of an entire
or sample population.

Inferential Technique that allows us to use

samples to make generalizations
about the population.
 Sampling Technique

Simple Random
Systematic
Stratified Probability
Cluster

Convenience
Purposive
Non-
Snowball Probability
Quota
Simple Random
Systematic
Assign numbers Choose Randomly
Stratified
Cluster
Convenience
Purposive
Snowball
Quota
Simple Random

Systematic
Stratified
Assign numbers Choose Randomly
Cluster
Convenience
Purposive
Snowball
Quota
Simple Random

Systematic Randomly selects

Choose Randomly
from the selected
an area
area
Stratified

Cluster
Convenience
Purposive
Snowball
Quota
Simple Random

Systematic

Stratified
Cluster

Convenience
Purposive
Convenience sampling is a non-probability
Snowball sampling technique where samples are selected
from the population only because they are
Quota conveniently available to the researcher.
Simple Random

Systematic

Stratified
Cluster
Convenience

Purposive
Snowball In the purposive sampling method,
researchers select the samples based purely on
Quota
the researcher’s knowledge and credibility.
Simple Random

Systematic Snowball sampling helps researchers find a sample

when they are difficult to locate. This sampling
system works like the referral program. Once the
Stratified
researchers find suitable subjects, he asks them for
Cluster assistance to seek similar subjects to form a
considerably good size sample.
Convenience
Purposive

Snowball
Quota
Simple Random

Systematic

Stratified
Cluster
Convenience
Purposive Quota sampling is a sampling methodology
wherein data is collected from a homogeneous
Snowball
group.

Quota
 What kind of
How to select data are we
dealing with?

appropriate Is our data

normally
statistical distributed?

test?
What is the
aim of the
study?
 What kind of
data are we
Levels of dealing with?

Measurement
Levels of Measurement
Variable

Qualitative Quantitative

Nominal Ordinal Interval Ratio

 Levels of Measurement
Qualitative data/variables Examples:
that cannot be arranged Sex or Gender, Blood Type,
in order. Religion, Name, Colors

Nominal Ordinal Interval Ratio

 Levels of Measurement
Qualitative or categorical Examples:
data/variables that have natural,
Educational attainment,
ordered categories and the
distances between the Levels, Race rankings
categories are not known.

Nominal Ordinal Interval Ratio

 Levels of Measurement
Quantitative Examples:
data/variables where the Temperature in C or F, IQ
difference between two test, Standardized test
values is meaningful. scores

Nominal Ordinal Interval Ratio

 Levels of Measurement
Quantitative data/variables Examples:
that have all the properties Weight, Height,
of an interval variable, but Temperature in K, Income,
also has a clear definition of
Mass, Number of children
0.0.
Nominal Ordinal Interval Ratio
 Test of
Is our data
Normality normally
distributed?

Data Normality Statistical

Gathering Test Test
 SEARCH
How to test if the data is normal?
 Normality Tests
Visual Method Using Statistical
Software
Kolmogorov-Smirnov (K-S)
test
Frequency Distribution Shapiro-Wilk test
(Histogram) Anderson-Darling test
Stem-and-leaf plot Cramer-von Mises test
D’Agostino skewness test
Boxplot Anscombe-Glynn kurtosis test
P-P plot D’Agostino-Pearson omnibus
Q-Q plot test
Jarque-Bera test
Hypothesis
Testing

What is the
aim of the
study?
 Null Hypothesis

There is no
Hypothesis
significant 𝜇1 − 𝜇2 = 0 that is being
tested (reject
relationship/ 𝜇1 = 𝜇2
or accept)
difference
 Null Hypothesis
Alternative Hypothesis

There is a
Hypothesis that
significant 𝜇1 < 𝜇2 left-tailed test
𝜇1 > 𝜇2 right-tailed test
determines the

relationship/ 𝜇1 ≠ 𝜇2 two-tailed test type of statistical

test to use
difference
Statistical Parametric
Normality
Test

Tests Tests

Know the goal

of the study

Non-
parametric Choose the
statistical test
Tests
 Difference

Non-Parametric Parametric

Relationship
Difference

Z-test
One-sample t-test
Independent t-test
Paired t-test
ANOVA
Repeated Measures of ANOVA
Parametric
 Difference

Mann-Whitney Test
Wilcoxon Test
Kruskal-Wallis Test
Friedman Test
Non-Parametric
Non-Parametric
Chi-square Test
Fisher’s Test
McNemar’s Test
Cochrane Q
Nonparametric Regression
Multiple Logistics Regression
Spearman rho
Relationship
 Parametric

Linear Regression
Pearson r
Relationship
 Difference
Z-test
One-sample t-test
Mann-Whitney Test Independent t-test
Wilcoxon Test Paired t-test
Kruskal-Wallis Test ANOVA
Friedman Test Repeated Measures of ANOVA

Non-Parametric Parametric
Chi-square Test
Fisher’s Test
McNemar’s Test
Cochrane Q
Nonparametric Regression
Multiple Logistics Regression Linear Regression
Spearman rho Pearson r

Relationship
 Basic
Statistical
Treatments
 Type of Data
Goal Binomial (two possible
Measurement Rank, Score, or Measurement
outcomes)

Basic
Compare one group to a
hypothetical value
One Sample t-test Wilcoxon test Chi-square test

Statistical
Fisher’s test (Chi-square for
Compare 2 unpaired groups Unpaired t-test Mann-Whitney
large samples)
Compare 2 paired groups Paired t-test Wilcoxon test McNemar’s test

Treatments
Compare >3 unmatched
groups
One-way ANOVA

Repeated Measures of
Kruskal-Wallis test Chi-square test

Compare >3 matched groups Friedman test Cochrane Q

ANOVA
Quantify association between
Pearson r Spearman rho Contingency coefficients
2 variables
Predict value from another
Simple linear regression Nonparametric regression Simple logistic regression
measured variable
Predict value from several
measured or binomial Multiple linear regression Multiple logistic regression
variables
 Basic
Statistical
Treatments
Basic statistical treatments and their
few examples
Z-test
A herd of 1,500 steer was fed a special high‐protein grain
for a month. A random sample of 30 were weighed and had
gained an average of 6.7 pounds. If the standard deviation
of weight gain for the entire herd is 7.1, test the hypothesis
that the average weight gain per steer for the month was
more than 5 pounds.
Basic statistical treatments and their
few examples
Independent t test
A researcher investigated whether an exercise or weight loss
intervention is more effective in lowering cholesterol levels. The
researcher recruited a random sample of 20 inactive males that
were classified as overweight. This sample was then randomly split
into two groups: Group 1 underwent a calorie-controlled diet and
Group 2 undertook the exercise-training program. Determine which
treatment program is more effective at 0.05 level of significance.
Basic statistical treatments and their
few examples
ANOVA
The pupils at a high school come from three different primary schools. The head teacher
wanted to know whether there were academic differences between the pupils from the three
different primary schools. As such, she randomly selected 20 pupils from School A, 20 pupils
from School B and 20 pupils from School C, and measured their academic performance as
assessed by the marks they received for their end-of-year English and Maths exams. Therefore,
the two dependent variables were "English score" and "Maths score", whilst the independent
variable was "School", which consisted of three categories: "School A", "School B" and "School
C".
Basic statistical treatments and their
few examples
Repeated Measures
of ANOVA
A researcher is investigating the effect of a 6-month
exercise training programme on blood pressure and wants
to measure blood pressure at 3 separate time points (pre-,
midway and post-exercise intervention), which would
allow you to develop a time-course for any exercise
effect. 20 males are randomly selected.
Basic statistical treatments and their
few examples
Pearson r
A researcher wants to know whether a person's height is related to
how well they perform in a long jump. The researcher recruited
untrained individuals from the general population, measured their
height and had them perform a long jump. The researcher then
investigated whether there was an association between height and
long jump performance by running a Pearson's correlation.
Basic statistical treatments and their
few examples
Spearman rank
A teacher is interested in whether those who do better at English
also do better in math. To test whether this is the case, the teacher
records the scores of her 10 students in their end-of-year
examinations for both English and math. Therefore, one variable
records the English scores and the second variable records the
math scores for the 10 pupils.
Basic statistical treatments and their
few examples
Linear Regression
Analysis
A salesperson for a large car brand wants to determine whether
there is a relationship between an individual's income and the price
they pay for a car. As such, the individual's "income" is the
independent variable and the "price" they pay for a car is the
dependent variable. The salesperson wants to use this information
to determine which cars to offer potential customers in new areas
where average income is known.
 https://economictimes.indiatimes.com/definition/quota-sampling
https://statistics.laerd.com/spss-tutorials/independent-t-test-using-spss-

References
statistics.php
https://statistics.laerd.com/spss-tutorials/linear-regression-using-spss-
statistics.php
https://statistics.laerd.com/spss-tutorials/one-way-manova-using-spss-
statistics.php
https://statistics.laerd.com/spss-tutorials/pearsons-product-moment-correlation-
using-spss-statistics.php
https://statistics.laerd.com/spss-tutorials/spearmans-rank-order-correlation-
using-spss-statistics.php
https://statistics.laerd.com/statistical-guides/descriptive-inferential-statistics.php
https://statistics.laerd.com/statistical-guides/repeated-measures-anova-statistical-
guide.php
https://www.cliffsnotes.com/study-guides/statistics/univariate-inferential-
tests/one-sample-z-test
https://www.healthknowledge.org.uk/public-health-textbook/research-
methods/1a-epidemiology/methods-of-sampling-population
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3693611/
http://www.pnrjournal.com/fulltext/219-1599720269.pdf?1631080837
https://www.questionpro.com/blog/non-probability-sampling/
https://www.questionpro.com/blog/probability-sampling/
References

Workshop
Pre-work shop
References
example
Title: Turnaround Time to Predict Out-patient Department Services Patient Satisfaction

Statement of the problem/objectives: The main objective of this study is to assess the influence of
Turnaround Time (TAT) to the Out-patient Department (OPD) patient satisfaction through the different
services delivered (OB-Gyne, Surgical, Medical and Pediatric) in Eversley Childs Sanitarium and General
Hospital (ECSGH) located in Jagobiao, Mandaue City, in the year 2021. The result of the study would be the
bases for recommendations. Moreover, this study aspires to:
1. Determine the information of the patients in terms of:
1. Age;
2. Gender, and
3. Area of service;
2. Determine the mean turnaround time and level of patient satisfaction by area of service visited; and
3. Predict the influence of turnaround time to patient satisfaction in OPD services.
Pre-work shop
References
example
Title: Turnaround Time to Predict Out-patient Department Services Patient Satisfaction

Main Variables: Objective:

Turnaround Time To predict the influence of turnaround time to
Patient Satisfaction patient satisfaction in OPD services.
Variables How to measure What kind of Is it normally What is the aim Possible
these variables? data are we Distributed? of the study? Statistical
getting? treatment
By minutes Interval/ratio To be answered
Turnaround Linear
(arrival time scores after gathering
Time To Predict Regression (if
minus exit time) (continuous) data
(Independent) normal)/ Ordinal
Thru Ordinal levels/ To be answered To Predict Logistic
Patient Standardized weighted mean/ after gathering (dependent) Regression (if
Satisfaction Likert Scale (categorical/ data non-normal)
questionnaire continuous)
 Work shop
References Activity
Title: Contextual Teaching and Learning Approach in Mathematics for STEM Students on Blended Learning Modality

Statement of the problem/objectives: The study aimed to determine the effectiveness of the CTL in enhancing the
academic performance in Mathematics-Basic Calculus of the Senior High School (SHS) Grade 11 STEM students in a blended
learning modality. Specifically, it sought to answer the following questions:
1. What is the pretest Mathematics performance of the students in the:
1.1 control group (conventional lecture method) and
1.2 experimental group (with CTL)?
2. What is the posttest Mathematics performance of the students in the:
2.1 control group and
2.2 experimental group?
3. Is there a significant mean gain from the pretest to the posttest Mathematics performance of the students in the:
3.1 control group and
3.2 experimental group?
4. Is there a significant difference in the mean gains in Mathematics academic performance between control and
experimental group?
 Work shop
References Activity
Questions to answer:
Construct the same
table with the pre-
1. What is the title of the study? work shop example.
2. What are the objectives of the study?
3. What are the main variables of the study? You have 20 minutes
4. How to measure these variables? to finish the
workshop activity.
5. What kind of data are we getting?
6. Is the data normally distributed? Goodluck.
7. What is the aim of the study?
8. What is the possible statistical treatment to use in the study?
 Work shop
References Activity
Thank you for
listening.