OBTAINING DATA

Engineering Data Analysis (ES209)

Introduction

This module will help you understand how to

obtain data by following the methods, planning,
and conducting.
What is Statistics?

Definition: Statistics is the science that deals with...

● Collection
● Organization
● Presentation
● Analysis
● Interpretation of data
Purpose: To aid decision-making.
Main Divisions of Statistics

● Descriptive Statistics:
Definition: Summarizes and describes quantitative
data.
● Inferential Statistics:
Definition: Draws conclusions about a population
based on a sample.
Main Divisions of Statistics

● Descriptive Statistics:
Focus: Organizing and summarizing data.
Purpose: Describing data.
Methods: Histograms, charts, measures of
central tendency, etc.
Main Divisions of Statistics

● Inferential Statistics
Focus: Making judgments or conclusions about
populations.
Method: Using findings from a sample to make
inferences.
Importance: Decision-making support.
Conclusion

● Statistics as a science of data.

● Two main divisions: Descriptive and
Inferential.
● Importance: Vital for decision-making
in engineering.
LEARNING OBJECTIVES

At the end of this module, you are expected to:

● Demonstrate understanding of the different
methods of obtaining data.
● Explain the procedures for planning and
conducting surveys and experiment.
Understanding Data in
Statistics
OBTAINING DATA
What is DATA?

● Data are values of qualitative or quantitative

variables, belonging to a set of items.
● Data can be qualitative or quantitative.
● Data belongs to a set of items, often referred
to as the population.
What is DATA?

Population: The set of objects you are interested in.

❖ A population in statistics refers to the complete set of
individuals, items, data points, or events that share a
common characteristic and are the subject of a statistical
study.
❖ It is the entire group we want to understand, but it may not
always be feasible or practical to study every member of the
population. This is where sampling comes into play.
What is DATA?

Population: Key Characteristics

❖ Comprehensiveness: The population includes every
possible member that fits the defined criteria.
❖ Parameter Estimation: Population parameters are the
characteristics or values that describe the entire
population.
❖ Precision: Analyzing the entire population allows for the
most precise and accurate statistical conclusions.
What is DATA?

● Variables: A measurement or characteristic of

an item.
● Variables are fundamental components in the
field of statistics and data analysis. They serve
as the building blocks for understanding and
quantifying various aspects of the items or
entities within a population.
What is DATA?

● Qualitative Variables Variables that are not

numerical; they describe data that fits into
categories.
What is DATA?

● Here are some examples of qualitative

variables:
○ Eye Colors:
■ Blue
■ Green
■ Brown
■ Hazel
What is DATA?

● Here are some examples of qualitative

variables:
○ States:
■ Florida
■ New Jersey
■ Washington
What is DATA?

● Here are some examples of qualitative

variables:
○ Dog Breeds:
■ Alaskan Malamute
■ German Shepherd
■ Siberian Husky
■ Shih Tzu
What is DATA?

● Quantitative Variables Variables that involve

numerical measurements or values.
What is DATA?

● Here are some examples of quantitative

variables:
○ Counts:
■ The number of students in a classroom.
■ The total sales revenue of a company in a fiscal
year.
■ The quantity of products manufactured in a
factory in a day.
What is DATA?

● Here are some examples of quantitative

variables:
○ Percentages:
■ The percentage of students who passed a test.
■ The percentage of votes received by a political
candidate in an election.
■ The percentage increase in the price of a
commodity.
What is DATA?

● Here are some examples of quantitative

variables:
○ Numerical Values:
■ The temperature in degrees Celsius or
Fahrenheit.
■ The age of individuals in years.
■ The weight of products in kilograms or
pounds.
What is DATA?

● Here are some examples of quantitative

variables:
○ Scores and Ratings:
■ Test scores on a scale from 0 to 100.
■ Customer satisfaction ratings on a scale
from 1 to 5.
■ Credit scores, such as FICO scores.
What is DATA?

● Here are some examples of quantitative

variables:
○ Time:
■ The duration of a race in seconds.
■ The time of day in hours and minutes.
■ The age of a historical event in years.
What is DATA?

● Summary key points:

○ Data can be qualitative or quantitative.
○ The population represents the set of
objects of interest.
○ Variables are measurements or
characteristics of items.
Conclusion

Understanding data types in statistics is

foundational for effective data analysis, guiding
appropriate statistical methods, ensuring valid
conclusions, and preventing common errors
across all stages of the analytical process.
ACTIVITY TIME!!!
Determine whether the following is a qualitative or a quantitative variable. Write
QLV if qualitative variable and QTV if quantitative variable.

1. High school Grade Point Average (e.g. 4.0, 3.2, 2.1).

2. Number of pets owned (e.g. 1, 2, 4).
3. How many cousins you have (e.g. 0, 12, 22).
4. Your race (e.g. Asian, Latino, black).
5. Party affiliation (e.g. Republican, Democrat,
Independent).
ACTIVITY TIME!!!
Determine whether the following is a qualitative or a quantitative variable. Write
QLV if qualitative variable and QTV if quantitative variable.

1. High school Grade Point Average (e.g. 4.0, 3.2, 2.1). QTV
2. Number of pets owned (e.g. 1, 2, 4). QTV
3. How many cousins you have (e.g. 0, 12, 22). QTV
4. Your race (e.g. Asian, Latino, black). QLV
5. Party affiliation (e.g. Republican, Democrat,
Independent). QLV
REMEMBER

The general rule of thumb: if you

can add it, it is quantitative, if you
cannot add something, then it is
qualitative.
5 MINUTES BREAK
 WHAT DO DATA
LOOK LIKE?
OBTAINING DATA
ACTIVITY TIME!!!

Give five (5) example of data you use in daily life.

WHAT DO DATA LOOK LIKE?

● Tabular Data
● Numerical Data
● Categorical Data
● Time Series Data
● Geospatial Data
WHAT DO DATA LOOK LIKE?

● Images and Videos

WHAT DO DATA LOOK LIKE?

● Graph Data
WHAT DO DATA LOOK LIKE?

● Audio Data
CONCLUSION

1. Data is Everywhere
2. Diverse Types of Data
3. Data Informs Decision-Making
4. Data Personalization
5. Tracking Progress
6. Safety and Well-being
7. Efficiency and Convenience
8. Continuous Learning
 METHODS OF DATA
COLLECTION
OBTAINING DATA
Methods of Data Collection

Definition: Data collection is the process of

gathering and measuring information on
variables of interest.
Purpose: Enables research, hypothesis testing,
and outcome evaluation.
Methods of Data Collection

Types of Data
1. Primary Data
2. Secondary Data
Methods of Data Collection

Types of Data | Primary Data

Definition: Data collected fresh and for the first time; original
in character.
Characteristics:
● Originality
● Specific to Research
Examples: Surveys, Observations, Experiments
Methods of Data Collection

Types of Data | Secondary Data

Definition: Data collected by someone else and have been
through the statistical process.
Characteristics:
● Not Original
● Collected for Other Purposes
Sources: Databases, Published Reports, Government Records
Methods of Data Collection

Methods of Data Collection | Primary Data

● Observations
● Interviews
● Questionnaires
● Case Studies
● Surveys
Methods of Data Collection

Primary Data | Observations

Definition: Gathering data directly from the field through
observation.
Methods: Observer's presence or visits to the field.
Advantages: Subjective bias eliminated, current information.
Disadvantages: Time-consuming, limited information,
unforeseen factors.
Methods of Data Collection

Primary Data | Observations | Types of Observation

● Structured Observation
● Unstructured Observation
● Participant Observation
● Non-participant Observation
● Uncontrolled Observation
● Controlled Observation
Methods of Data Collection

Primary Data | Observations | Types of Observation

● Structured Observation
○ Definition: Observation with standardized
conditions, recorded styles, and defined units.
○ Example: Inventory analysis in a store by an
auditor.
Methods of Data Collection

Primary Data | Observations | Types of Observation

● Unstructured Observation
○ Definition: Observation without prior
planning.
○ Example: Observing children playing with new
toys
Methods of Data Collection

Primary Data | Observations | Types of Observation

● Participant Observation
○ Definition: Observer is a member of the
observed group.
○ Advantages: Natural behavior, better
understanding, closeness to the group.
Methods of Data Collection

Primary Data | Observations | Types of Observation

● Non-participant Observation
○ Definition: Observer observes without
interaction.
○ Advantages: Objectivity, neutrality, respondent
willingness.
Methods of Data Collection

Primary Data | Observations | Types of Observation

● Uncontrolled Observation
○ Definition: Observation in natural conditions
for spontaneous data.
○ Purpose: Capturing life and behaviors as they
occur.
Methods of Data Collection

Primary Data | Observations | Types of Observation

● Controlled Observation
○ Definition: Observation with pre-arranged
plans and experimental procedures.
○ Context: Often conducted in a laboratory
under controlled conditions.
Methods of Data Collection

Primary Data | Observations | Considerations in

Observation
● Factors:
○ Setting and context
○ Observer's role
○ Ethical considerations
○ Data recording methods
Methods of Data Collection

Primary Data | Observations | Advantages and

Disadvantages of Observation
● Advantages:
○ Subjective bias elimination
○ Real-time data
○ Independence from respondent variables
Methods of Data Collection

Primary Data | Observations | Advantages and

Disadvantages of Observation
● Disadvantages:
○ Time-consuming
○ Limited information
○ Influence of unforeseen factors
Methods of Data Collection

Primary Data | Observations | Conclusion

● Observation is a valuable method for primary
data collection.
● Various types of observation suit different
research needs.
● Consider context and ethical considerations
when using observation.
Methods of Data Collection

Primary Data | Interviews

Definition: The interview method involves
oral-verbal communication to gather
information.
Methods of Data Collection

Primary Data | Interviews | Types of Interviews

● Personal Interviews
● Structured Interviews
● Unstructured Interviews
● Focused Interviews
● Clinical Interviews
Methods of Data Collection

Primary Data | Interviews | Types of Interviews

● Personal Interviews
○ Definition: Face-to-face communication
with the interviewer and respondent.
○ Use: In-depth information gathering,
rapport building.
Methods of Data Collection

Primary Data | Interviews | Types of Interviews

● Structured Interviews
○ Definition: Pre-determined set of
questions.
○ Use: Consistency in data collection, easy
analysis.
Methods of Data Collection

Primary Data | Interviews | Types of Interviews

● Unstructured Interviews
○ Definition: No set questions; flexible
conversation.
○ Use: Exploratory research, open-ended
responses.
Methods of Data Collection

Primary Data | Interviews | Types of Interviews

● Focused Interviews
○ Definition: Emphasis on a specific
experience and its effects.
○ Use: Understanding specific aspects deeply.
Methods of Data Collection

Primary Data | Interviews | Types of Interviews

● Clinical Interviews
○ Definition: Explores broad feelings,
motivations, or life experiences.
○ Use: Psychological or therapeutic contexts.
Methods of Data Collection

Primary Data | Interviews | Types of Interviews

● Group Interviews
○ Definition: Interviews with 6 to 8
individuals simultaneously.
○ Use: Collecting diverse perspectives, group
dynamics.
Methods of Data Collection

Primary Data | Interviews | Types of Interviews

● Qualitative and Quantitative Interviews
○ Definition: Based on subject matter
(qualitative vs. quantitative).
○ Use: Depending on research objectives and
data type.
Methods of Data Collection

Primary Data | Interviews | Types of Interviews

● Individual Interviews
○ Definition: One-on-one interviews with a
single person.
○ Use: In-depth exploration of an individual's
experiences or opinions.
Methods of Data Collection

Primary Data | Interviews | Types of Interviews

● Selection Interviews
○ Definition: Interviews for job recruitment
or candidate selection.
○ Use: Assessing qualifications and suitability
for a position.
Methods of Data Collection

Primary Data | Interviews | Types of Interviews

● Depth Interviews
○ Definition: Aims to elicit unconscious and
personality-related material.
○ Use: Psychological research, personality
analysis.
Methods of Data Collection

Primary Data | Interviews | Types of Interviews

● Telephonic Interviews
○ Definition: Conducted over the phone.
○ Use: Cost-effective data collection, remote
interviews.
Methods of Data Collection

Primary Data | Interviews | Considerations in

Interviews
● Factors:
○ Interviewer skills
○ Respondent comfort
○ Ethical considerations
○ Data recording methods
Methods of Data Collection

Primary Data | Interviews | Advantages and

Disadvantages of Interviews
● Advantages:
○ In-depth data
○ Clarification of responses
○ Rapport building
Methods of Data Collection

Primary Data | Interviews | Advantages and

Disadvantages of Interviews
● Disadvantages:
○ Time-consuming
○ Potential for interviewer bias
○ Limited to available respondents
Methods of Data Collection

Primary Data | Interviews | Conclusion

● Interviews are a versatile data collection method.
● Different types of interviews suit different
research needs.
● Consider context, objectives, and ethical
considerations when conducting interviews.
Methods of Data Collection

Primary Data | Questionnaires

Definition: The questionnaire method involves
sending a set of questions to respondents, who
are expected to answer in writing.
Methods of Data Collection

Primary Data | Questionnaires

Use of Questionnaires:
● Popularity in big surveys
● Written responses from respondents
● Independent response generation
Methods of Data Collection

Primary Data | Questionnaires

Advantages of Questionnaires
● Cost-effectiveness for large geographic areas
● Answers in respondents' words, reducing bias
● Adequate time for thoughtful responses
● Ability to reach non-approachable
respondents
Methods of Data Collection

Primary Data | Questionnaires

Disadvantages of Questionnaires
● Low return rate of completed questionnaires
● Slow data collection process
● Difficulty in verifying respondent identity
● Potential for incomplete or inaccurate
responses
Methods of Data Collection

Primary Data | Questionnaires

Additional Advantages
● Large sample sizes for increased reliability
● Ease of anonymity for sensitive topics
● Flexibility in questionnaire design
Methods of Data Collection

Primary Data | Questionnaires

Types of Questions
● Open-ended questions
● Closed-ended questions
● Multiple-choice questions
● Likert scale questions
Methods of Data Collection

Primary Data | Questionnaires

Questionnaire Design
● Factors:
○ Clarity of questions
○ Question sequence
○ Language and tone
○ Length of the questionnaire
Methods of Data Collection

Primary Data | Questionnaires | Conclusion

● Questionnaires are a cost-effective method for data collection.
● They offer advantages such as anonymity and thoughtful
responses.
● Disadvantages include low return rates and slow data collection.
● Careful questionnaire design and ethical considerations are
crucial.
Methods of Data Collection

Primary Data | Questionnaires | Conclusion

● Questionnaires are a cost-effective method for data collection.
● They offer advantages such as anonymity and thoughtful
responses.
● Disadvantages include low return rates and slow data collection.
● Careful questionnaire design and ethical considerations are
crucial.
Methods of Data Collection

Primary Data | Case Studies

Definition: A case study is an intensive
investigation of a particular unit or subject
under study.
Purpose: Explore the use, advantages, and
disadvantages of case studies in research.
Methods of Data Collection

Primary Data | Case Studies

Use of Case Studies
● In-depth investigation
● Applicable in various fields (e.g., psychology,
medicine, business)
● Ideal for complex or unique scenarios
Methods of Data Collection

Primary Data | Case Studies

Advantages:
● Cost-effective and less time-consuming
● Suitable for hard-to-obtain exposure data
● Effective for studying dynamic populations
● Rich qualitative data
Methods of Data Collection

Primary Data | Case Studies

Disadvantages:
● Subject to selection bias
● Limited ability to calculate incidence (absolute
risk)
● Findings may not be generalizable
● Time and resource-intensive for data collection
Methods of Data Collection

Primary Data | Case Studies

Ethical Considerations
Factors:
● Informed consent
● Privacy and confidentiality
● Respect for participants
Methods of Data Collection

Primary Data | Case Studies | Conclusion

● Case studies offer rich qualitative data for in-depth
investigations.
● They are cost-effective but subject to selection bias.
● Ideal for dynamic populations but may not allow for
incidence calculations.
● Careful planning and ethical considerations are
essential in case study research.
Methods of Data Collection

Primary Data | Surveys

Definition: Surveys are common methods for
diagnosing and addressing social problems.
Purpose: Explore the use, advantages, and
disadvantages of surveys in research.
Methods of Data Collection

Primary Data | Surveys

Use of Surveys
● Wide applicability in social research
● Ideal for collecting data from diverse populations
● Versatility in question types (e.g., closed-ended,
open-ended)
Methods of Data Collection

Primary Data | Surveys

Advantages
● Easy administration
● Relatively quick development time
● Cost-effectiveness (depending on survey
mode)
Methods of Data Collection

Primary Data | Surveys

Disadvantages
● Potential for respondent bias
● Accuracy and honesty of responses may vary
● Validity concerns with closed-ended questions
● Data errors due to non-responses
● Wide-reaching data collection
Methods of Data Collection

Primary Data | Surveys

Ethical Considerations
● Informed consent
● Privacy and data protection
● Ensuring respondent well-being
Methods of Data Collection

Primary Data | Surveys | Conclusion

● Surveys are versatile data collection methods.
● They offer advantages in ease of administration,
speed, and cost-effectiveness.
● However, concerns about respondent bias and
question validity require careful planning.
Methods of Data Collection

Secondary Data
Definition: Secondary data is data collected by
someone else for another purpose but used for a
different research objective.
Purpose: Explore the use, sources, and factors
to consider when using secondary data.
Methods of Data Collection

Sources of Secondary Data

● Government publications
● Technical and trade journals
● Books, magazines, newspapers
● Reports from industry, banks, stock exchanges
● Academic research reports
● Public records
Methods of Data Collection

Sources of Secondary Data

Government publications
● Examples: Census data, economic reports,
health statistics
● Use: Comprehensive and reliable data from
government sources.
Methods of Data Collection

Sources of Secondary Data

Technical and Trade Journals
● Examples: Industry-specific data, research
findings
● Use: Valuable for industry analysis and
specialized research.
Methods of Data Collection

Sources of Secondary Data

Books, Magazines, Newspapers
● Examples: Historical data, public opinions
● Use: Historical context and public sentiment
analysis.
Methods of Data Collection

Sources of Secondary Data

Reports from Industry
● Examples: Annual reports, market research
studies
● Use: Business analysis and market trends.
Methods of Data Collection

Sources of Secondary Data

Academic Research Reports
● Examples: Theses, dissertations, research
papers
● Use: Scholarly insights and findings.
Methods of Data Collection

Sources of Secondary Data

Public Records
● Examples: Birth records, property records,
legal documents
● Use: Legal and historical data.
Methods of Data Collection

Sources of Secondary Data | Conclusion

● Secondary data offers valuable resources for
research.
● Multiple sources provide a wide range of data
types.
● Careful consideration of data reliability,
suitability, and adequacy is essential.
Methods of Data Collection

Factors to Consider When Choosing Data

Collection Methods
● Nature, Scope, and Object of Inquiry
● Availability of Funds
● Time Factor
● Precision Required
Methods of Data Collection

Factors to Consider When Choosing Data Collection

Methods
● Nature, Scope, and Object of Inquiry
Considerations:
○ The research's focus, goals, and objectives
○ Suitability of the method for the research's nature
and scope
Methods of Data Collection

Factors to Consider When Choosing Data Collection

Methods
● Availability of Funds
Considerations
○ Funding limitations may impact method choice
○ Balancing cost-effectiveness with method
efficiency
Methods of Data Collection

Factors to Consider When Choosing Data Collection

Methods
● Time Factor
Considerations
○ Research timelines and deadlines
○ Data collection methods' time requirements
Methods of Data Collection

Factors to Consider When Choosing Data Collection

Methods
● Precision Required
Considerations:
○ The level of accuracy and detail needed
○ Whether the data collection method allows for the
desired precision
 Planning and
Conducting Surveys
OBTAINING DATA
Designing a Survey

Definition: Surveys gather data through a series

of questions.
Purpose: Explore the steps involved in designing
an effective survey.
Designing a Survey

Steps in Designing a Survey

1. Determine the goal
2. Identify the sample population
3. Choose an interviewing method
4. Decide on question order and phrasing
5. Conduct the interview and collect data
6. Analyze results
Designing a Survey

Steps in Designing a Survey

1. Determine the goal
Clearly define the research question or
objective.
Designing a Survey

Steps in Designing a Survey

2. Identify the sample population
Define the target group for your survey.
Designing a Survey

Steps in Designing a Survey

3. Choose an Interviewing Method
Select the most appropriate method for data
collection.
Options: Face-to-face, phone,
self-administered, online.
Designing a Survey

Steps in Designing a Survey

4. Decide on Question Order and Phrasing
Plan the sequence and wording of questions
carefully.
Example: Create concise and unbiased
questions.
Designing a Survey

Steps in Designing a Survey

5. Conduct the Interview and Collect Data
Execute the survey and record responses.
Considerations: Non-response bias, data
recording.
Designing a Survey

Steps in Designing a Survey

6. Analyze Results
Use data analysis techniques to draw
conclusions.
Methods: Charts, graphs, statistical analysis.
Designing a Survey

Steps in Designing a Survey | EXAMPLE

Martha wants to construct a survey that
shows which sports students at her school
like to play the most.
Designing a Survey

Steps in Designing a Survey | EXAMPLE

1. Goal:
"Which sports do students at Martha's
school like to play the most?"
Designing a Survey

Steps in Designing a Survey | EXAMPLE

2. Population: Random sample of Martha's
school students.
Designing a Survey

Steps in Designing a Survey | EXAMPLE

3. Method: Face-to-face interviews at an
all-school assembly.
Designing a Survey

Steps in Designing a Survey | EXAMPLE

4. Question order and phrasing: You may asked
open/ close ended questions.
Designing a Survey

Steps in Designing a Survey | EXAMPLE

5. Data Collection Sheet: Include space for
recording student responses.
Designing a Survey

Steps in Designing a Survey | EXAMPLE

6. Analysis and Conclusion
Emphasis: The importance of analyzing
collected data and drawing meaningful
conclusions.
 The Scientific Method

OBTAINING DATA
What is The Scientific Method?

Definition: A systematic approach to answering

questions and solving problems.
Steps: Observation, hypothesis,
experimentation, data collection, analysis,
conclusion.
Steps of the Scientific Method

1. Decide what phenomenon to investigate.

2. Specify how to manipulate the factor and
control other conditions.
3. Measure the response variable at different
factor settings.
4. Establish cause-and-effect relationships.
Number of Factors in an Experiment

1. Independent variables are factors that researchers

intentionally manipulate to observe their effect on the
dependent variable. In comparative experiments, there is
usually at least one independent variable.
2. Extraneous variables are other factors that may
unintentionally affect the dependent variable but are not
the primary focus of the study. Researchers aim to control
or account for extraneous variables to ensure that the
observed effects are due to the independent variable(s).
Number of Factors in an Experiment
Example: Baking a Cake
● Oven Preheating
● Baking Time
● Ingredients
● Moisture
● Temperature
● Recipe Variations
● Leavening Agents
● Mixing Technique
● Pan Selection and Preparation
● Cooling
Number of Factors in an Experiment
Controlling factors in experiments is like making sure you understand why
something happens. There are two main ways to do this:

● Isolate One Thing: Imagine you want to know if a new medicine works.
You would only change the medicine (keep everything else the same) to
see if it's the medicine that helps, not other factors like diet or lifestyle.
● Change Several Things Together: Sometimes, you need to study how
many things work together, like how water, sunlight, and soil affect plant
growth. It's more complex, but it helps in understanding real-world
situations.

Both approaches are important in science. The key is to be careful and

organized when doing experiments, so you can trust the results.
What is Design of Experiments (DOE)?
Definition: A structured approach to
experimentation for optimizing processes and
solving problems.
Purpose: Enhance the efficiency and
effectiveness of experiments.
What is Design of Experiments (DOE)?
Key Concepts in DOE
● Factorial experiments
● Control factors
● Interaction effects
● Response surface methodology
What is Design of Experiments (DOE)?
Benefits of DOE
Advantages: Improved process understanding,
optimized results, reduced experimentation
time and cost.
Conclusion
● The scientific method guides experimental
inquiry.
● Controlling factors is crucial for accurate
results.
● Introduction to DOE enhances
experimentation efficiency.
Engineering Experiments and
Experimental Design
OBTAINING DATA
Purposes of Engineering Experiments
● Reduce time to develop new products and
processes.
● Enhance the performance of existing
processes.
● Improve product reliability and performance.
● Achieve product and process robustness.
● Evaluate materials, design alternatives,
tolerances, etc.
Competitive Drive in Engineering
Competitiveness in engineering drives a
continuous cycle of experimentation,
innovation, and quality improvement. To
succeed in global markets, engineering teams
must leverage experiments to develop products
that excel in terms of quality, efficiency, and
customer satisfaction.
Robustness in Engineering Experiments
In engineering, robustness is crucial for
ensuring that products, processes, and systems
maintain their performance and reliability under
real-world conditions.
Factors and Inputs
Controlled Factors: These are the variables researchers
manipulate deliberately to isolate their effects on the outcome.
They are also known as independent variables.
Uncontrolled Factors: These are external variables that can
influence the outcome but are not deliberately controlled by
the researcher. They are also called extraneous variables.
Inputs: Inputs encompass all variables and elements in the
experiment, including both controlled and uncontrolled
factors.
Controllable vs. Uncontrollable Factors
In engineering experiments, distinguishing between controllable
(independent) and uncontrollable (extraneous) factors is essential for
consistency and predictability.

● Controllable Factors: Researchers manipulate these deliberately, like

temperature levels in a material strength test, ensuring consistent and
predictable outcomes.
● Uncontrollable Factors: These external influences, such as
environmental conditions, can't be controlled but are minimized for
reliable results.

This distinction is crucial for establishing cause-and-effect relationships and

achieving reproducible, predictable outcomes in engineering experiments.
Output and Response
In engineering experiments, output or response
variables are the measurements used to assess
the effects of controlled factors (independent
variables). These variables, such as cake texture,
height, size, or flavor in a cake experiment, are
crucial for quantifying the impact of changes in
factors on a system's characteristics.
Experimental Design

Definition: The systematic approach to planning

and conducting experiments.
Components: Control groups, treatment groups,
randomization, replication.
Key Concepts in Experimental Design
● Control groups and baseline measurements
● Treatment variables and conditions
● Randomization to reduce bias
● Replication for result reliability
Conclusion
● Engineering experiments serve multiple
purposes.
● Robustness and control are vital in
experimental design.
● Understanding factors, inputs, and responses
is crucial.
Basic Principles of Design of
Experiments (DOE)
OBTAINING DATA
Randomization
Definition: Random assignment of treatments to
experimental units.
Importance: Eliminating biases and ensuring the
validity of comparative experiments.
Replication
Definition: The practice of repeating
experimental conditions to assess the
consistency of results.
Significance: Enhancing the reliability and
robustness of experiment outcomes.
Blocking
Definition: Incorporating additional factors
(blocking factors) to control undesirable
variation.
Application: Controlling sources of noise in
experiments, such as age and gender in human
studies.
Multi-factor Designs
Definition: Experiments involving multiple
factors or variables.
Benefits: Studying interactions and main effects
simultaneously for comprehensive insights.
Confounding
Definition: The intermingling of two or more
effects in an experiment.
Examples: Avoiding confounding in comparative
studies; strategic confounding in complex
experiments.
Practical Applications
● Manufacturing process optimization
● Drug development studies
● Agricultural field trials
● Product quality improvement
● Environmental impact assessments
Conclusion
● Randomization, replication, and blocking
enhance experimental validity.
● Multi-factor designs provide comprehensive
insights.
● Confounding is typically avoided but can be
strategically used in complex experiments.
 Steps for Planning,
Conducting, and Analyzing an
Experiment
OBTAINING DATA
Steps for Experimentation
● Recognition and statement of the problem
● Choice of factors, levels, and ranges
● Selection of the response variable(s)
● Choice of design
● Conducting the experiment
● Statistical analysis
● Drawing conclusions and making
recommendations
Recognition and Statement of the Problem
Identifying the goal and problem statement for
the experiment.
Setting a clear direction for the research.
Choice of Factors, Levels, and Ranges
Selecting treatment factors, specifying levels,
and defining the range of variation.
Determining what will be manipulated and
observed.
Selection of the Response Variable(s)
Defining the outcome or variables to be
measured.

Considerations: Relevance to the research

question and feasibility of measurement.
Choice of Design
Selecting the appropriate experimental design.

Options: Randomized controlled trials, factorial

designs, etc.
Conducting the Experiment
The practical implementation of the experiment,
including data collection.

Considerations: Control of variables,

randomization, and replication.
Statistical Analysis
Applying statistical methods to analyze collected
data.

Methods: Descriptive statistics, hypothesis

testing, regression analysis.
Drawing Conclusions and Making Recommendations
Interpreting the results and providing insights
or recommendations.

Implications: Practical applications and future

research directions.
Factors in Experimentation
treatment factors - main variables of interest
nuisance factors - secondary variables to control
experimental factors- manipulated
classification factors - categorization criteria
Quantitative vs. Qualitative: Factors can be numerical
(quantitative) or categorical (qualitative), influencing the
choice of statistical analysis methods.
Conclusion
Recap:
The systematic steps in experimental design.
The significance of factor selection and
experimental design.
Understanding different types of factors in
experimentation.
 Thank You

NEXT >> PROBABILITY