Chapter Four

Data Collecting , Data Analysis Research

Data and Interpretation

1
Session Objectives

• To understand source of data and type of data

• To understand how to collect and present data
• To understand how to analyze and interpret data

2
Source of Data

3
Qualitative or Numerical Data
Discrete Data
• Only certain values are possible (there are gaps between the possible
values)
Continuous Data
• Theoretically, any value within an interval is possible with a
fine enough measuring device

4
Data sources

5
Data sources

6
Types of Data
• Primary data: data observed and recorded or collected
directly from respondents. Allow us to collect first hand information,
but time consuming and costly.

• Secondary data: data complied both inside and outside the

organization for some purpose other than the current
investigation. This approach is convenient from the time aspect, but
need critical evaluation of the accuracy, relevance and sources of
information.

7
Primary Data collection Techniques
• Interview
• Questioner
• Observation :
• Survey
• Experimentation

8
Interviews Different Techniques:-
1. Structured (closed) interviews
• Stakeholders answer a predefined set of questions
• Easy to analyze (+)
• Well-formed questions generate well-formed answers (+)
• Knowledge about what and how to ask (-)
2. Non-structured (open) interviews
• No predefined agenda
• Generating new ideas (experimental, brain storming) (+),
sometimes hard to handle (dynamics of discussion) (-)
3. In practice: mixed interview types are normal.

9
Survey
Advantages of using survey…
• Collect information from a large number of users simultaneously.
• If designed correctly, it can be quick & easy to analyze the data.
• Relatively cheap.

Disadvantages of using survey…

• Rich data collection is not possible
• Does not provide the holistic view of a system

10
Questionnaires

Advantages of Questionnaires…

• Questionnaires provide an efficient way to collect information from

multiple stakeholders quickly.

• Generally questionnaires are considered

• more useful as informal checklists to ensure fundamental elements are
addressed early on

11
Cont.

Disadvantages of Questionnaires…

• Questionnaires lack the opportunity to investigate further on a topic,

or expand on new ideas.

• In the same way, questionnaires provide no mechanism for the

participants to request clarification or correct misunderstandings.

12
Data Analysis
Data analysis is the systematic process of examining,
organizing, cleaning, and modeling data with the goal of
discovering useful information, drawing conclusions, and
supporting decision-making.
Purpose of Data Analysis:
• To summarize large volumes of data.
• To find patterns, relationships, and trends.
• To test hypotheses and answer research questions.
• To make evidence-based decisions.
•

13
Types of Data Analysis
A. Quantitative Data Analysis
• Involves numerical data.
• Focuses on quantifying patterns and relationships.
• Common in scientific, economic, and social research.

Common Techniques:
• Descriptive statistics: Mean, median, mode, standard
deviation.
• Inferential statistics: Hypothesis testing, correlation,
regression analysis, ANOVA.
• Visualization: Histograms, scatter plots, line graphs.
•

14
 •.

Types of Data Analysis

B. Qualitative Data Analysis
• Involves non-numerical data (e.g., words, images,
observations).
• Focuses on understanding meanings, experiences, and ideas

Common Techniques:
• Thematic analysis: Identifying recurring themes and ideas.
• Content analysis: Quantifying the presence of words, themes,
or concepts.
• Narrative analysis: Exploring the stories people tell.
• Discourse analysis: Studying communication patterns and
meanings.

15
Steps in the Data Analysis Process
Step 1: Data Preparation
• Data Cleaning: Remove or correct errors, missing values, duplicates, or inconsistencies.
• Data Organization: Categorize and arrange data systematically (e.g., spreadsheets,
databases).
Step 2: Exploratory Data Analysis (EDA)
• Summarize data: Use tables, charts, and summary statistics.
• Detect patterns: Identify trends, anomalies, or relationships visually and statistically.

Step 3: Statistical Analysis or Thematic Coding

• Apply statistical tests (for quantitative data).
• Develop codes and categories (for qualitative data).
• Compare groups or test relationships.

16
Steps in the Data Analysis Process
Step 4: Interpretation of Results
• What do the patterns or statistical outputs mean?
• Relate findings back to research objectives.

Step 5: Presentation of Results

• Use graphs, charts, tables, and textual explanations.
• Highlight key findings in a clear and understandable
manner.

17
Challenges in Data Analysis
üPoor data quality: Missing, wrong, or inconsistent data.
üOverfitting or underfitting (in predictive modeling).
üBiases: Data collection and interpretation biases.
üMisinterpretation of statistical results.
üLarge volume of data: Difficulty in managing "Big Data."

18
Statistical Analysis
Statistical analysis is a process used to collect, summarize,
interpret, and present data in a meaningful way.
• Descriptive Statistics
• Inferential Statistics

19
Descriptive Statistical Analysis
Descriptive statistics are methods of organizing,
summarizing, and presenting data in an informative way.
They describe the basic features of the data collected
without making predictions or generalizations.

Purpose:
• To summarize large amounts of data into simple forms.
• To provide a snapshot or overview of the data.
• To make raw data easier to understand.

20
Descriptive Statistical Analysis
Common Techniques
Purpose:
• To summarize large amounts of data into simple forms.
• To provide a snapshot or overview of the data.
• To make raw data easier to understand.
Mean (average), Median (middle value),
Measures of Central Tendency
Mode (most frequent value).

Range, Variance, Standard Deviation (how

Measures of Dispersion
spread out the data is).

Frequency Distributions Counts of how often values occur.

Bar charts, Pie charts, Histograms, Box
Data Visualization
plots.

21
 •.

Inferential Statistical Analysis

Inferential statistics involve making predictions, decisions,
or generalizations about a population based on a sample of
data.
Purpose:
• To draw conclusions beyond the data at hand.
• To infer characteristics of a large group (population) from a
smaller group (sample).
• To test hypotheses and estimate parameters.

22
•.

Inferential Statistical Analysis

Inferential statistics involve making predictions, decisions, or
generalizations about a population based on a sample of data.
Purpose:
• To draw conclusions beyond the data at hand.
• To infer characteristics of a large group (population) from a
smaller group (sample).
• To test hypotheses and estimate parameters.
Common Techniques
Hypothesis Testing: Testing assumptions about a population (e.g.,
t-test, chi-square test).
Confidence Intervals: Estimating the range within which a
population parameter lies
Regression Analysis: Predicting relationships between variables.
Analysis of Variance (ANOVA): Comparing means across multiple
groups.
23
•.
Statistical Analysis

24
•.

Data Interpretation
Data interpretation is the process of analyzing, evaluating,
and explaining the meaning of data after it has been
collected and analyzed. It involves making logical
conclusions and drawing insights from the processed data.

Purpose:
• To answer research questions.
• To confirm or reject hypotheses.
• To provide meaning to the raw data.
• To guide decision-making based on research findings.

25
•.

Steps in Data Interpretation

Step 1: Understand the Analyzed Data
• Review tables, charts, statistical results, and thematic
findings.
• Understand what the numbers, trends, or themes are
showing.
Step 2: Identify Patterns and Relationships
• Look for regularities, correlations, differences, and trends.
• Example: Sales increase during the holiday season.
Step 3: Relate Findings to Research Objectives
• Align your interpretations with the questions or
hypotheses you originally set out to address.
26
•.

Steps in Data Interpretation

Step 4: Explain the Results
• Why did these patterns emerge?
• What external or internal factors might have influenced
the results?
Step 5: Draw Conclusions and Make Recommendations
• Summarize key insights.
• Suggest actions, further research, or policy changes based
on findings.

27
•.

Types of Data Interpretation

A. Quantitative Data Interpretation
• Based on numerical data.
• Uses statistical tools like mean, median, standard deviation,
correlation, regression.
• Example: Interpreting survey results, experiment data,
census figures.

• Example:
If the average customer satisfaction score increased from
3.2 to 4.5, the interpretation could be that a new service
improvement initiative was effective

28
•.

Types of Data Interpretation

B. Qualitative Data Interpretation
• Based on non-numerical data like interviews, focus groups,
observations.
• Uses thematic analysis, content analysis, narrative analysis.
• Looks for meanings, emotions, experiences.
Example:
If multiple interview participants express frustration about a
system's complexity, the interpretation could suggest the
need for a user-friendly redesign.

29
•.

Factors to Consider During Interpretation

• Context: Always interpret data considering the social,

economic, and environmental context.
• Sample Size: A small or biased sample can mislead
interpretation.
• Bias: Be aware of personal bias and avoid seeing only what
you expect.
• Limitations: Acknowledge weaknesses in data collection
and analysis.
• External Influences: Consider other variables that might
have affected the results.
30
•.
Common Challenges in Data Interpretation
• Overgeneralization: Drawing broad conclusions from
limited data.
• Misinterpretation: Wrongly attributing causes without
enough evidence.
• Ignoring Confounding Variables: Overlooking other factors
that impact results.
• Cherry-picking Data: Focusing only on results that fit the
desired outcome.

31
 •.
Simple Example of Data Interpretation

A school conducted a survey and found that 80% of students

preferred online classes over face-to-face classes..
Interpretation:
• Online classes might offer more flexibility and convenience
for students.
• The school may need to invest more in online learning
platforms.
• However, further investigation is needed to see if learning
outcomes are also better online.

32