Republic of the Philippines

NUEVA ECIJA UNIVERSITY OF SCIENCE AND TECHNOLOGY

Cabanatuan City, Nueva Ecija

College of Engineering – Mechanical Engineering Department

Math 243 – Module for Course Outcome 1

1.1 Methods of Data Collection

• Definition of Data Collection
• Types of Data Collection Methods:
o Primary Data Collection:
▪ Surveys
▪ Interviews
▪ Observations
▪ Focus Groups
▪ Experiments
o Secondary Data Collection:
▪ Government Reports
▪ Academic Papers
▪ Online Databases
• Advantages and Disadvantages of Each Method
• Choosing the Right Data Collection Method
1.2 Planning and Conducting Surveys and Experiments
• Understanding the Purpose of Surveys and Experiments
• Steps in Survey Planning:
o Defining Objectives
o Identifying Target Population
o Choosing Data Collection Mode (Online, Paper, Phone, Face-to-Face)
o Designing Questions
o Pretesting the Survey
o Collecting and Analyzing Data
• Planning and Conducting Experiments:
o Hypothesis Development
o Experimental Design (Control vs. Experimental Group)
o Data Collection and Observation Techniques
o Analyzing Experimental Results
• Ethical Considerations in Data Collection
 Republic of the Philippines
NUEVA ECIJA UNIVERSITY OF SCIENCE AND TECHNOLOGY
Cabanatuan City, Nueva Ecija

College of Engineering – Mechanical Engineering Department

1.3 Questionnaire Design in Planning/Surveys

• Purpose of a Questionnaire
• Characteristics of a Good Questionnaire:
o Clear and Concise Questions
o Avoiding Bias and Leading Questions
o Using Open-ended vs. Close-ended Questions
o Logical Flow of Questions
• Steps in Developing a Questionnaire:
o Identifying Key Information to Collect
o Structuring and Formatting Questions
o Pretesting the Questionnaire
o Finalizing and Deploying
• Common Pitfalls and How to Avoid Them
1.4 Sampling Plans/ Sampling Techniques
• Introduction to Sampling
o Importance of Sampling in Research
o Sampling vs. Census
• Types of Sampling Techniques:
o Probability Sampling:
▪ Simple Random Sampling
▪ Stratified Sampling
▪ Cluster Sampling
▪ Systematic Sampling
o Non-Probability Sampling:
▪ Convenience Sampling
▪ Purposive Sampling
▪ Snowball Sampling
▪ Quota Sampling
• Determining Sample Size
• Reducing Sampling Errors
 Republic of the Philippines
NUEVA ECIJA UNIVERSITY OF SCIENCE AND TECHNOLOGY
Cabanatuan City, Nueva Ecija

College of Engineering – Mechanical Engineering Department

1.1 Methods of Data Collection

Data collection is the systematic process of gathering and measuring information from various
sources to obtain accurate and reliable data for research, decision-making, or analysis. This process
ensures that collected data is relevant, unbiased, and useful for drawing meaningful conclusions.

Types of Data Collection Methods

Data collection methods are categorized into primary and secondary methods, depending on
whether the data is collected directly from sources or obtained from existing records.
Primary Data Collection
Primary data collection involves gathering first-hand data directly from respondents or sources. It
is often used for specific research purposes and requires direct interaction.
1. Surveys – A method of collecting data from a predefined group using questionnaires or
structured interviews. Surveys can be conducted online, via phone, or in person.
2. Interviews – A face-to-face, phone, or virtual conversation where an interviewer asks
open-ended or structured questions to gather in-depth information.
3. Observations – A method where researchers record behaviors, activities, or phenomena
without direct interaction. It is useful in behavioral studies.
4. Focus Groups – A discussion-based method where a small group of individuals share
opinions and experiences on a specific topic under the guidance of a facilitator.
5. Experiments – A controlled method of data collection used in scientific and social
research, where variables are manipulated to study their effects on an outcome.
Secondary Data Collection
Secondary data collection involves using previously gathered data from various sources. It is a
cost-effective way to obtain information that already exists.
1. Government Reports – Official data published by government agencies, including census
data, economic reports, and policy documents.
2. Academic Papers – Research articles, theses, and conference papers that provide peer-
reviewed information from previous studies.
3. Online Databases – Digital repositories containing datasets, reports, and statistical
information from various disciplines (e.g., Google Scholar, PubMed, World Bank
databases).
 Republic of the Philippines
NUEVA ECIJA UNIVERSITY OF SCIENCE AND TECHNOLOGY
Cabanatuan City, Nueva Ecija

College of Engineering – Mechanical Engineering Department

Advantages and Disadvantages of Each Method

Method Advantages Disadvantages

Surveys Collect data from large samples, Responses may be biased,
cost-effective, easy to analyze limited depth of responses
Interviews Provides detailed insights, allowsTime-consuming, interviewer
for clarification bias may affect responses
Observations Captures natural behavior, Observer bias, difficult to
useful for non-verbal data generalize findings
Focus Groups Interactive discussions, rich Small sample size, potential for
qualitative data dominant voices influencing
opinions
Experiments Establishes cause-and-effect Can be expensive, ethical
relationships, highly controlled concerns in some cases
Government Reports Reliable and comprehensive, May be outdated or lack
covers broad demographics specificity
Academic Papers Peer-reviewed and credible, Access may be restricted, may
builds on existing research require interpretation
Online Databases Large amounts of readily Quality and reliability may vary
available data, useful for trend
analysis

Choosing the Right Data Collection Method

Selecting the appropriate data collection method depends on:
• Research Objectives: If the goal is to understand behaviors, observations may be best. If
numerical trends are needed, surveys may be preferable.
• Resources & Budget: Experiments and interviews may require more time and funding,
whereas secondary data is often more cost-effective.
• Data Accuracy & Reliability: Primary data ensures specificity and relevance, but
secondary data may be more comprehensive.
• Ethical Considerations: Some methods (e.g., experiments, interviews) may involve
privacy concerns or ethical constraints.
 Republic of the Philippines
NUEVA ECIJA UNIVERSITY OF SCIENCE AND TECHNOLOGY
Cabanatuan City, Nueva Ecija

College of Engineering – Mechanical Engineering Department

1.2 Planning and Conducting Surveys and Experiments

Definition
Planning and conducting surveys and experiments involves systematically designing a research
process to collect accurate and meaningful data. Surveys are structured methods used to gather
information from a specific group, while experiments involve controlled conditions to test
hypotheses and analyze cause-and-effect relationships.

Understanding the Purpose of Surveys and Experiments

• Surveys aim to collect data about opinions, behaviors, or characteristics of a specific
population. They are widely used in social sciences, marketing, health studies, and business
research.
• Experiments are used to test hypotheses by manipulating variables and observing
outcomes in controlled settings. They help researchers determine causal relationships
between different factors.
Both approaches ensure that data is collected systematically to make informed decisions and draw
valid conclusions.
Steps in Survey Planning
1. Defining Objectives
o Clearly outline the purpose of the survey.
o Identify what information needs to be collected.
o Example: A company conducting a customer satisfaction survey may aim to assess
user experience and areas for improvement.
2. Identifying Target Population
o Determine who will participate in the survey.
o Consider demographic factors such as age, gender, location, and profession.
o Example: A university survey on student engagement will target enrolled students
rather than faculty or staff.
3. Choosing Data Collection Mode
o Online Surveys: Conducted via Google Forms, SurveyMonkey, or email links
(cost-effective and scalable).
o Paper Surveys: Printed questionnaires distributed physically (useful for areas with
limited internet access).
o Phone Surveys: Conducted via telephone interviews (useful for detailed responses
but time-consuming).
 Republic of the Philippines
NUEVA ECIJA UNIVERSITY OF SCIENCE AND TECHNOLOGY
Cabanatuan City, Nueva Ecija

College of Engineering – Mechanical Engineering Department

o Face-to-Face Surveys: Conducted in person (ideal for complex questions but

costly and time-intensive).
4. Designing Questions
o Use clear, concise, and unbiased language.
o Include both closed-ended (yes/no, multiple choice) and open-ended (descriptive
answers) questions.
o Avoid leading or confusing questions.
o Example: Instead of asking, “Do you agree that our product is the best?” ask, “How
satisfied are you with our product?”
5. Pretesting the Survey
o Conduct a trial run with a small group before full distribution.
o Identify unclear or misleading questions and refine them.
o Example: If respondents find a question too complex, simplify its wording.
6. Collecting and Analyzing Data
o Distribute the survey using the selected method.
o Collect responses and check for completeness and accuracy.
o Use statistical tools (Excel, SPSS, or Python) to analyze patterns, trends, and
insights.
o Example: A survey on employee satisfaction may reveal that 80% of respondents
value flexible working hours.

Planning and Conducting Experiments

1. Hypothesis Development
o Formulate a testable statement predicting the relationship between variables.
o Example: Increasing daily exercise will improve students' concentration levels.
2. Experimental Design (Control vs. Experimental Group)
o Control Group: A group that does not receive the experimental treatment (used for
comparison).
o Experimental Group: A group that experiences the intervention or change.
o Example: In a study on sleep and productivity, one group maintains regular sleep
patterns while another follows a reduced sleep schedule.
3. Data Collection and Observation Techniques
o Use structured methods such as direct observations, lab experiments, or field
studies.
 Republic of the Philippines
NUEVA ECIJA UNIVERSITY OF SCIENCE AND TECHNOLOGY
Cabanatuan City, Nueva Ecija

College of Engineering – Mechanical Engineering Department

o Measure variables consistently using validated tools (e.g., surveys, physiological

measurements, time tracking).
o Example: In a drug efficacy study, researchers monitor patients' symptoms and side
effects over time.
4. Analyzing Experimental Results
o Use statistical analysis to determine if observed differences are significant.
o Common methods include t-tests, ANOVA, and regression analysis.
o Example: If students who exercise score 15% higher on concentration tests,
researchers analyze if this difference is statistically meaningful.
5. Ethical Considerations in Data Collection
o Informed Consent: Participants must voluntarily agree to participate,
understanding the risks and purpose.
o Confidentiality: Personal data should be protected and anonymized when
necessary.
o Minimizing Harm: Research should not cause physical, emotional, or
psychological distress.
o Honesty in Reporting Data: Results should be reported accurately, avoiding bias
or manipulation.
o Example: A psychological study ensures that participants are aware of potential
emotional triggers before participating.
 Republic of the Philippines
NUEVA ECIJA UNIVERSITY OF SCIENCE AND TECHNOLOGY
Cabanatuan City, Nueva Ecija

College of Engineering – Mechanical Engineering Department

1.3 Questionnaire Design in Planning/Surveys

Questionnaire design is the process of creating a structured set of questions used to gather
information from respondents in a survey or research study. A well-designed questionnaire
ensures clarity, accuracy, and effectiveness in collecting meaningful and reliable data.
Purpose of a Questionnaire
A questionnaire serves as a tool for systematically collecting data from individuals. The
key purposes of a questionnaire include:
1. Data Collection – Gathering quantitative and qualitative data from a target population.
2. Standardization – Ensuring consistency in the way questions are presented to different
respondents.
3. Efficiency – Collecting large volumes of data quickly and cost-effectively.
4. Comparability – Allowing responses to be analyzed, compared, and interpreted for
decision-making.
5. Minimizing Bias – Providing a structured format that reduces researcher influence on
responses.

Characteristics of a Good Questionnaire

1. Clear and Concise Questions
• Questions should be easy to understand and free from unnecessary complexity.
• Avoid jargon or technical terms that respondents might not comprehend.
• Example: Instead of “What is your perception of the current economic climate?”
use “How do you feel about the current state of the economy?”
2. Avoiding Bias and Leading Questions
• Questions should not be framed in a way that influences respondents toward a
particular answer.
• Leading questions can skew results and compromise data integrity.
• Example of a biased question:
o Bad: “Don’t you think the new policy has improved public health?”
o Good: “How has the new policy impacted public health?”
3. Using Open-ended vs. Close-ended Questions
• Open-ended questions allow respondents to provide their own answers, leading to
more detailed insights. Example: “What factors influence your purchase
decisions?”
 Republic of the Philippines
NUEVA ECIJA UNIVERSITY OF SCIENCE AND TECHNOLOGY
Cabanatuan City, Nueva Ecija

College of Engineering – Mechanical Engineering Department

• Close-ended questions provide a set of predefined answer choices, making

analysis easier. Example: “How often do you shop online?
(Daily/Weekly/Monthly/Never)”
• A combination of both types can improve data richness and accuracy.
4. Logical Flow of Questions
• The sequence of questions should be logical and natural.
• Start with general questions before moving to more specific ones.
• Avoid abrupt topic shifts to keep respondents engaged.
• Example structure:
o Introduction: General demographic questions
o Middle: Main research-related questions
o End: Sensitive or optional questions

Steps in Developing a Questionnaire

1. Identifying Key Information to Collect
• Clearly define the objectives of the questionnaire.
• Identify the type of data required (e.g., demographic, behavioral, opinion-based).
• Example: If researching customer satisfaction, key information may include service
quality, pricing, and customer support.
2. Structuring and Formatting Questions
• Group similar questions together to improve readability.
• Use headings or sections for different topics.
• Keep response options clear and exhaustive (e.g., include “Other” or “Not
Applicable” if needed).
3. Pretesting the Questionnaire
• Conduct a pilot test with a small sample group.
• Identify ambiguities, confusing wording, or redundant questions.
• Make necessary modifications based on feedback.
4. Finalizing and Deploying
• Revise the questionnaire based on pretest results.
• Choose a distribution method (online, paper-based, telephone, or face-to-face).
• Ensure ethical considerations, such as anonymity and informed consent.
 Republic of the Philippines
NUEVA ECIJA UNIVERSITY OF SCIENCE AND TECHNOLOGY
Cabanatuan City, Nueva Ecija

College of Engineering – Mechanical Engineering Department

Introduction to Sampling
Sampling is the process of selecting a subset of individuals or observations from a larger
population to make inferences about the whole group. Since studying an entire population
is often impractical, sampling provides a cost-effective and time-efficient way to gather
data.

Importance of Sampling in Research

Sampling is crucial for research because:
1. Efficiency: Studying a sample is quicker and more affordable than analyzing an entire
population.
2. Accuracy: If done correctly, a well-chosen sample can provide reliable insights about the
population.
3. Feasibility: Some populations are too large or inaccessible, making sampling the only
viable option.
4. Quality Control: Proper sampling techniques help reduce bias and improve data
reliability.

Sampling vs. Census

Criteria Sampling Census

Definition Selection of a subset from theCollection of data from the
population entire population
Time Required Less time-consuming More time-consuming
Cost Less expensive More expensive
Accuracy High accuracy if done Very high accuracy but can
properly suffer from errors due to
large-scale data handling
Usage Used when population is large Used when population is
small or a complete count is
necessary

When to Use Sampling vs. Census?

Use a census when accuracy is critical (e.g., national population count).
Use sampling when studying a large or inaccessible population (e.g., consumer behavior
surveys).
 Republic of the Philippines
NUEVA ECIJA UNIVERSITY OF SCIENCE AND TECHNOLOGY
Cabanatuan City, Nueva Ecija

College of Engineering – Mechanical Engineering Department

Types of Sampling Techniques

Sampling methods are categorized into Probability Sampling and Non-Probability
Sampling techniques.
1. Probability Sampling
Probability sampling ensures that every individual in the population has a known, non-zero
chance of being selected. It allows for unbiased and statistically valid results.
a. Simple Random Sampling
• Every individual has an equal chance of being selected.
• Selection is often done using random number generators or lottery methods.
• Example: Drawing names from a hat for a class representative.
b. Stratified Sampling
• The population is divided into subgroups (strata) based on a specific characteristic
(e.g., age, gender).
• A sample is randomly selected from each stratum to ensure representation.
• Example: Selecting equal numbers of men and women from a workforce for a
survey.
c. Cluster Sampling
• The population is divided into groups (clusters), and entire clusters are randomly
selected for study.
• Used when populations are naturally divided (e.g., schools, cities).
• Example: Selecting 5 schools randomly from a district and surveying all students
in those schools.
d. Systematic Sampling
• Every nth individual from a list is selected.
• Ensures even distribution across the population.
• Example: Selecting every 10th customer from a list of supermarket shoppers.

2. Non-Probability Sampling
Non-probability sampling does not give every individual an equal chance of being selected. It is
useful for exploratory research but may introduce bias.
a. Convenience Sampling
• Selecting individuals based on ease of access.
• Quick and inexpensive but prone to bias.
• Example: Surveying students in a cafeteria rather than the whole campus.
 Republic of the Philippines
NUEVA ECIJA UNIVERSITY OF SCIENCE AND TECHNOLOGY
Cabanatuan City, Nueva Ecija

College of Engineering – Mechanical Engineering Department

b. Purposive Sampling
• Researchers choose participants who meet specific criteria relevant to the study.
• Often used in qualitative research.
• Example: Interviewing only experts in artificial intelligence for a study on AI ethics.
c. Snowball Sampling
• Existing participants recruit new participants, forming a growing chain.
• Useful for studying hard-to-reach populations.
• Example: Studying drug users by having each participant refer another user.
d. Quota Sampling
• Selecting a sample to reflect certain characteristics in a population.
• Similar to stratified sampling but non-random.
• Example: Ensuring 50% of respondents in a market survey are women.

Determining Sample Size

The sample size affects the reliability of research findings. It is determined by:
1. Population Size: Larger populations require larger samples.
2. Margin of Error: A lower margin of error requires a larger sample.
3. Confidence Level: Higher confidence levels require more data points.
4. Variability in Population: More diverse populations require larger samples.

Formula for Sample Size (for large populations):

 Republic of the Philippines
NUEVA ECIJA UNIVERSITY OF SCIENCE AND TECHNOLOGY
Cabanatuan City, Nueva Ecija

College of Engineering – Mechanical Engineering Department

Reducing Sampling Errors

Sampling errors occur when the selected sample does not represent the whole population.
They can be minimized by:
1. Using Probability Sampling – Ensuring every member has a fair chance of selection.
2. Increasing Sample Size – Larger samples reduce variability.
3. Ensuring Proper Stratification – Grouping similar units before sampling.
4. Avoiding Selection Bias – Making sure every individual has an equal chance of being
included.
5. Conducting Pilot Studies – Testing sampling methods before full-scale research.