GOOD
MORNING
CLASS!
ANALYZING
THE DATA
ANALYSIS
a detailed examination of anything
complex in order to understand its nature
or to determine its essential features : a
thorough study.
ANALYSIS
In simpler terms, analysis means "breaking
down" concepts from whole to part.
DATA ANALYSIS
Data analysis in research refers to the
process of inspecting, cleaning, transforming,
and modeling data to discover useful
information, support decision-making, and
validate research hypotheses.
OBJECTIVES:
1. Describe data – Summarize key
characteristics (e.g., mean, frequency
distributions).
2. Identify patterns & Relationships –
Detect trends, correlations, and anomalies.
3. Test hypotheses – Use statistical
methods to confirm or reject research
assumptions.
4. Make predictions – Apply predictive
modeling to forecast future trends.
5. Support decision-making – Provide
empirical evidence for policy, business, or
scientific conclusions.
3 TYPES OF
DATA
ANALYSIS
IN
RESEARCH
1. QUANTITATIVE
DATA ANALYSIS
Involves numerical data analyzed using statistical
methods.
Common techniques:
- Descriptive statistics (mean, median, standard deviation)
- Inferential statistics (t-tests, ANOVA, regression analysis)
- Factor analysis & principal component analysis (PCA)
2. QUALITATIVE
DATA ANALYSIS
Focuses on non-numerical data (text, audio, video) to
identify themes and patterns.
Common techniques:
- Thematic analysis
- Content analysis
- Grounded theory
- Discourse analysis
3. MIXED-METHODS
ANALYSIS
Combines both quantitative and qualitative approaches
for a comprehensive understanding.
Common techniques:
Triangulation (cross-validating findings from different methods)
Embedded design (one method supports the other)
Example: A study using surveys (quantitative) and focus groups
(qualitative) to assess employee satisfaction.
DATA
ANALYSIS
METHODS IN
RESEARCH
1. DESCRIPTIVE
STATISTICS
Descriptive statistics help you
understand what your data looks
like. They don’t test hypotheses or
make predictions—they simply
summarize data in a meaningful way.
At the start of any research to
describe your sample.
EXAMPLE
A researcher surveys 300 university students.
Mean age = 21.4 years
60% female, 40% male
Standard deviation of GPA = 0.45
This gives readers a clear picture of who participated
in the study.
2. INFERENTIAL
STATISTICS
Inferential statistics allow
researchers to draw conclusions
about a population based on
sample data and test
hypotheses.
When you want to test
assumptions, differences, or
relationships.
EXAMPLE
A study compares exam scores between:
Group A: Traditional teaching
Group B: Online teaching
A t-test shows Group B scores significantly higher (p
< 0.05), suggesting the new method is more
effective.
3. CONTENT ANALYSIS
(QUALITATIVE)
Content analysis systematically
examines communication
content (text, images, videos) by
categorizing it into meaningful
units.
When analyzing documents,
media, interviews, or speeches.
EXAMPLE
A study compares exam scores between:
Group A: Traditional teaching
Group B: Online teaching
A t-test shows Group B scores significantly higher (p
< 0.05), suggesting the new method is more
effective.
4. THEMATIC ANALYSIS
(QUALITATIVE)
Thematic analysis focuses
on identifying patterns of
meaning (themes) across
qualitative data.
To understand experiences,
perceptions, or perspectives.
EXAMPLE
Researchers interview patients with chronic pain:
[Link]: Reading transcripts repeatedly
[Link]: Highlighting phrases like “feeling ignored”
[Link]: “Lack of medical validation”
[Link]: Ensuring themes fit the data
[Link]: Final themes clearly defined
5. FACTOR ANALYSIS
(QUANTITATIVE)
Factor analysis reduces a large number
of variables into smaller underlying
factors.
When working with questionnaires or
scales with many items.
EXAMPLE
Researchers survey 300 college students about study habits using a 20-item
questionnaire:
Data Collection: Students rate statements such as “I study regularly,” “I
manage my time well,” and “I procrastinate”
Correlation Analysis: Identifying items that are highly related to each other
Factor Extraction: Grouping related items into factors
Factors Identified: (Time Management, Study Motivation, Procrastination)
Rotation & Interpretation: Clarifying factor structure for better
interpretation
Naming Factors: Final factors are labeled based on the items they represent
6. META-ANALYSIS
(QUANTITATIVE)
Meta-analysis statistically
combines findings from multiple
studies to produce a more
reliable overall conclusion.
In evidence-based medicine,
education, psychology, and
policy research.
EXAMPLE
A researcher reviews 25 clinical trials on a drug:
Calculates effect sizes from each study
Combines them statistically
Finds the drug has a moderate overall
benefit
7. GROUNDED THEORY
(QUALITATIVE)
Grounded theory
develops a new theory
directly from data, rather
than testing existing
theories.
When little theory exists
about a phenomenon.
EXAMPLE
Researchers study leadership in startups:
Interview founders
Identify recurring patterns like “adaptive
decision-making”
Develop a new theory explaining leadership
under uncertainty