STATISTICAL TREATMENT OF DATA

[email protected]
RECALL ON POPULATION & SAMPLES

• POPULATION (N)- is the entirety of the group

including all the members that forms a set of data.
• SAMPLE (n)- contains a few members of the
population. Samples were taken to represent the
characteristics or traits of the population.

[email protected]
 The whole pie
stands for the
POPULATION
The RED part of
the pie stands
for the SAMPLES

[email protected]
DATA
TYPES OF DATA
DISCRETE FINITE
NUMERICAL
(Quantitative)

DATA CONTINUOUS INFINITE

CATEGORICAL
(Qualitative)

[email protected]
 MEASUREMENT SCALES
• Measurement – is the process of assigning value to a
variable.
• There are four levels pf scales of measurement

Ratio
NUMERICAL
Interval

Ordinal
CATEGORICAL
Nominal
[email protected]
 DATA

NOMINAL DATA NOMINAL DATA

- Qualitative/Categorical
- Observations can be Example:
named without particular SEX: M - Male
order or ranking imposed F - Female
Types of Electric Consumption:
on the data. Words, 1- Residential
letters, and even numbers 2- Commercial
are used to classify the 3- Industrial
data. Note: Order does not matter
[email protected]
 DATA

NOMINAL DATA
- Qualitative/Categorical
Example: SEX= Male and Female
Types of Electric Consumption:
1- Residential
2- Commercial
3- Industrial
Note: Order does not matter
[email protected]
 DATA
• ORDINAL DATA Example: Competition Placement:
1. Describes ranking or order. 1- Champion
The difference or ratio 2- 1st Runner-up
between two rankings may 3- 2nd Runner-up
not always be the same. 4-4th Runner - up

• ORDINAL DATA Level of Satisfaction

1. Ranking/Placement 1- Very satisfies
2- Satisfied
2. The order matters 3- Unsatisfied
3. Differences cannot be 4- Very unsatisfied
measured
[email protected]
 DATA
• INTERVAL DATA
- Indicates an actual amount
(numerical). The order and the 1. Temperature (in Celsius or
difference between the variables Fahrenheit)
can be known, Its limitation is “it 2. Mark grading, IQ test and CGPA.
has no true Zero”. 3. These interval data examples are
measured with equal intervals in
• Example their respective scales.
Temperature 4. Interval data are often used for
60oC statistical research, school grading,
20oC scientific studies and probability
10oC
-15oC
[email protected]
 DATA
• RATIO DATA
- It has the same properties as the
interval level. The order and the
difference can be described. Additionally,
1. AGE
it has a true ZERO and the ratio between
two points has a meaning. 2. Weight
3. Length
4. Distance
• Example
- Mass
80kg
40kg
10kg
0kg
[email protected]
Date Name Order Difference True Zero

Nominal X X
X
Ordinal
X X
Interval
X
Ratio
[email protected]
 DESCRIPTIVE AND
INFERENTIAL STATISTICS
[email protected]
 QUANTITATIVE
DATA

can be analyzed using

Descriptive Statistics Inferential Statistics

Uses procedures like Involves
Hypothesis
Frequency Charts and
Count Percentage Testing
Graphs
using
Measures Measures
of of Central
Tendency Statistical Tests of Significance
Variability
[email protected]
DESCRIPTIVE STATISTICS INFERENTIAL STATISTICS
- used to describe a set of - used to say something about a
information/data collected. larger group (population) using
- It can also be represented with information collected from a
graphs. small part of that population
Common tools are: (sample).
- Measures of Central tendency VS - Using sample data to make
- Measures of Variability
inference or draw a conclusion of
the population.
Example:
In a math test, 32 out of - Example:
40 students were able to receive a - In a sample conducted, 65% of
passing mark. The average score Filipino Generation Z prefer to
of the class is 82 out of 100. drink milk tea than coffee while
34% of Filipino Millennials prefer
to drink milk tea than coffee.
[email protected]
 Preparing quantitative data for analysis
• After gathering needed data it is important that these data are prepared for analysis.

• One way to prepare the data for analysis is through coding

Coding scheme for demographic
profile
Coded Data on Demographic profile of Respondents
Variable Coding scheme
Respondent Sex Grade Level Age
Sex 1 – Male
2- Female Respondent 1 1 2 2

Grade 1 – Grade school Respondent 2 1 2 2

Level 2 - Junior High School Respondent 3 2 1 1
3 – Senior High School Respondent 4 2 3 3
4- College
Respondent 5 1 4 3
Age 1- 10– 15 years old
2- 16 – 20 years old
[email protected]
3- 21- 25 years old
 Preparing quantitative data for analysis
Coding Scheme for Survey on Competency Level
Variable Coding Scheme
Item Rating 4- Very High Level
3- High Level
2- Moderate Level
1- Low Level

Coded Data on Survey on Competency level

Respondent 1 2 3 4 5 6 7 8 9
Respondent A 2 4 3 2 3 3 3 4 2
Respondent B 3 2 4 3 4 2 2 4 1
Respondent C 2 3 2 4 3 3 3 2 3
Respondent D 1 4 3 1 2 4 3 3 4
[email protected]
 Descriptive Frequency Counts and
statistics Percentage
• One way to interpret quantitative data us through descriptive statistics.
• DESCRIPTIVE statistics are procedures that researchers use to describe data.

Tells how many times a certain item in a

Frequency Counts
scale is rated.
Tells how many of the respondents belong to a category
The proportion of responses out of the
Percentage
total based on 100.
% = part x 100
whole
[email protected]
 Frequency Counts and Percentage
Descriptive statistics Variable f %
Male 3 60
Coded Data on Demographic Profile Sex Female 2 40
Respondent Sex Grade Age Total 5 100
level Grade School 1 20
Respondent 1 2 2 Junior HS 2 40
Respondent 1 2 2
Grade Level Senior HS 1 20
Respondent 2 1 1 College 1 20
Respondent 2 3 3 Total 5 100
Respondent 1 4 3 10-15 1 20
Age
% = part x 100 16-20 2 40
21-25 2 40
whole [email protected]
Total 5 100
GRAPH
Demographic Profile for SEX

Female , 2,
40%
Male, 3, 60%

Male Female
[email protected]
 Preparing quantitative data for analysis
Respondent 1 2 3 4 5
Respondent A 2 4 3 2 3
Respondent B 3 2 4 3 4
Respondent C 2 3 2 4 3
Respondent D 1 4 3 1 2
Items Very High High Moderate Low Total
f % f % f % f % f %
1 0 0 1 25 2 50 1 25 4 100
2 2 50 1 25 1 25 0 0 4 100
3 1 25 2 50 1 25 0 0 4 100
4 1 25 1 25 1 25 1 25 4 100
5 1 25 2 50 1 25 0 0 4 100
[email protected]
Measures of Central Tendency

• A measure of central tendency describes how data

are grouped together around a central value.
• Helps give a picture of what is typical in the sample
or what ids the most apparent and representative
characteristics of the sample.

[email protected]
MEAN Is the most common form of reporting central
tendency.

Done by taking the sum of all the answers divided by

the total number of those who answered.

= X where: = mean
n X = X1, X2,….Xn = Data
n = Respondents

[email protected]
Example

Average Score
Respondents Scores
A 95
B 80 Mean = 424 = 84.80
C 87 8
D 76
E 86

[email protected]
MEAN RATING Also known as the WEIGHTED MEAN.

Used for summarizing the results for rating scales.

An average of the values of each item assigned for a weight

MR = f(1) + f(2) +f(3) + f(4) + f(5)

N

[email protected]
 MR = f(1) + f(2) +f(3) + f(4) + f(5)
MEAN RATING N

Items Very High High Moderate Low Mean Interpretation

Rating
N = 10
f f f f
1 3 1 3 3 2.4 Moderate
2 2 2 4 2 2.4 Moderate
3 2 2 3 3 2.3 Moderate
4 2 2 4 2 2.4 Moderate
5 1 3 3 3 2.2 Moderate

[email protected]
 Interval Description/Interpretation
3.26 – 4.00 Very High
2.51 – 3.25 High
1.76 – 2.50 Moderate
1.0 - 1.75 Low

[email protected]
Inferential Statistics
• Is using probability to determine whether it is likely that a
particular sample (or test outcome) is representative of
the population.
• This concerns with the population and use sample data
to make inference about the population or to test
hypothesis.
• It is also known as the HYPOTHESIS TESTING.
• A hypothesis is a testable prediction about a real
phenomenon.
[email protected]
 Inferential Statistics
• Parametric statistics are based
on assumptions about the • Nonparametric
distribution of population from statistics are not based
which the sample was taken.
• Variables are normally on assumptions, that is,
distributed. the data can be collected
• A normal distribution of data
is one in which the majority of from a sample that does
data points are relatively not follow a specific
similar, meaning they occur
within a small range of values distribution.
with fewer outliers on the high
and low ends of the data range
[email protected]
 Inferential Statistics
• Parametric Test • Non- Parametric Test
1. T- Test 1. Chi- Square
A. One- Sample T-Test
2. Mann-Whitney Test
B. Two- Sample T-Test
C. Independent - Sample T-Test
3. Kruskal-Wallis Test
4. Friedman Test
2. One - Way ANOVA
5. Wilcoxon Signed Rank Test Test
3. Regression
a. Simple Linear Regression
b. Multiple Linear Regression [email protected]
T-test
• A t-test is used to compare the mean of two
given samples.

• Example:
• Is there a significant difference between the
teachers’ teaching performance when data are
analyzed according to sex?

[email protected]
• Independent Sample T- Test

• Independent Sample T- Test- s an inferential statistical test

that determines whether there is a statistically significant
difference between the means in two groups

• A t-test for independent means test two distinct

groups of participants, each group is tested once

[email protected]
Teaching Performance

Male Female
90 91
89 87
91 89
90 90
87 85
90 98

[email protected]
The paired sample t-test
• The paired sample t-test, sometimes called the
dependent sample t-test, is a statistical
procedure used to determine whether the mean
difference between two.
• Example:
• Is there a significant difference between the result in
the Reading Enhancement program of the pre and
post tests of control and experimental groups?
[email protected]
Result of the REP for both Groups

Experimental group Control group

Pre Test Post test Pre Test Post test
12 20 12 15
12 18 11 10
11 17 11 11
9 13 8 6
7 11 7 6
4 10 4 5
[email protected]
One – Way ANOVA

• One-Way ANOVA ("analysis of

variance") compares the means of two or
more independent groups in order to
determine whether there is statistical
evidence that the associated population
means are significantly different.

[email protected]
• Example
Is there a significant difference
between the teachers’ teaching
performance when data are analyzed
according to educational attainment?

[email protected]
Bachelors Master’s Doctorate
Degree Degree Degree
93 95 94
90 94 95
91 92 96
87 92 96
85 93 95
89 95 94
87 92
[email protected] 96
Regression
• Correlation is a term that is a measure of the
strength of a linear relationship between two
quantitative variables (e.g., height, weight). ...
• For example, positive correlation may be that the
more you exercise, the more calories you will
burn

[email protected]
• Example
• Is there a significant relationship between the
teachers teaching performance and their mental
health?
• Does Teacher’s Teaching performance influence by
student’s academic achievement?

[email protected]
• Example
• Is there a significant relationship between the
teachers psychological perspectives such as social,
emotional and behavioral and their mental health?
• DoTeacher’s Teaching performance influence by
student’s academic achievement?

[email protected]
Statistical Treatment of Data
IV – Level of DV- Level of Purpose Treatment
Measurement Measurement
Continuous Continuous Association Pearson-r
1 Continuous IV Continuous Prediction/impact Simple Regression
/effect
2 or more Continuous Continuous Prediction/impact Multiple Regression
IV /effect

Categorical (2 Groups) Continuous Difference T-test

Categorical (3 or more Continuous Difference ANOVA
groups)
[email protected]
[email protected]
[email protected]
Identify the appropriate Statistical Treatment

1. The impact of peace of mind on Academic performance

2. The influence of happiness and flourishing on physical
health
3. The relationship of burnout and job satisfaction
4. Awareness of Employees on Health Anxiety amidst
COVID outbreak in terms of gender
5. Measuring Hope across the various regions in the
country
[email protected]
[email protected]