📘 Lesson: Data Collection
1. Introduction
Data collection is the systematic process of gathering information to answer research questions,
test hypotheses, or evaluate outcomes. It is an essential first step in statistics because the
accuracy and reliability of conclusions depend on the quality of the data collected.
Proper data collection ensures:
Valid conclusions
Accurate statistical results
Minimal bias
Useful insights for decision-making
2. Types of Data
A. Qualitative (Categorical) Data
Describes qualities or categories.
Examples: gender, color, type of school
B. Quantitative Data
Numerical values that can be measured.
1. Discrete – countable
o Example: number of students
2. Continuous – measurable across intervals
o Example: height, weight, temperature
3. Data Collection Process
Step 1: Identify the Purpose
What problem are you solving?
What question do you want to answer?
Step 2: Determine the Type of Data Needed
Qualitative or quantitative?
Primary or secondary data?
Step 3: Choose a Data Collection Method
(Discussed below)
Step 4: Design Instruments
Survey form
Interview guide
Observation checklist
Step 5: Collect the Data
Follow a clear procedure to avoid bias.
Step 6: Check for Accuracy
Remove inconsistencies and errors.
4. Methods of Data Collection
A. Primary Data Collection
Collected directly from the source.
1. Surveys / Questionnaires
o Uses structured questions
o Good for large groups
2. Interviews
o Personal, in-depth information
o May be structured or unstructured
3. Observations
o Collects data by watching behaviors or events
o Can be naturalistic or controlled
4. Experiments
o Researchers manipulate variables
o Used in scientific and statistical testing
B. Secondary Data Collection
Data taken from existing sources.
Books
Journals
Government records
Databases
Previous research
Advantages:
Low cost
Saves time
Disadvantages:
May be outdated
May not perfectly match the research objective
5. Factors Affecting Quality of Data
1. Accuracy – How close data is to the true value
2. Reliability – Consistency of results
3. Validity – Measures what it is supposed to measure
4. Bias – Systematic errors that distort results
5. Sampling Method – Determines representativeness
6. Examples
Example 1:
A researcher wants to know the average daily screen time of students.
Best method: Survey or digital monitoring tool.
Example 2:
A store wants to know what products customers buy most frequently.
Best method: Observation or point-of-sale (POS) data.
Example 3:
A health department wants to track the number of dengue cases.
Best method: Secondary data from hospitals and public health records.
Example 4:
A scientist wants to know if fertilizer affects plant growth.
Best method: Controlled experiment.
Example 5:
A teacher wants to understand why students struggle in math.
Best method: Interviews or focus groups.
7. Summary
Data collection is the foundation of any statistical investigation.
Good data leads to good conclusions.
Choosing the right method depends on:
The purpose
The type of data needed
Available resources