Professional Documents
Culture Documents
Lecture
on
Design and Analysis of Experiments
Aim
Contents to describe and explain the variation of
Introduction information under conditions that are
Defining research problem hypothesized to reflect the variation
Selection of the Responses
Statistical Analysis
Design of Experiment is a problem-solving tool
Introduction to Design of Experiment (DOE)
Research design is a set of advance decisions that make up the master plan
specifying the methods and procedures for collecting and analyzing the needed
information.
a. Sampling Design: deals with the method of selecting items to be observed for
the given study.
b. observational design: relates to the conditions under which the observations
are to be made.
c. Statistical Design: concerns with the question of how many items are to be
observed and how the information and data gathered are to be analyzed.
d. Operational Design: deals with the techniques by w/c the procedures specified
in the sampling, statistical and observational designs can be carried out.
DOE is a body of knowledge and techniques that assist the experimenter to:
conduct experiment economically,
from the analysis and the original
analyze the data, and
objectives of the investigation.
make connections between the conclusions
Secondary factor Factors that impact the performance but whose impact we are not
interested in quantifying
Interaction Two factors A and B interact if the effect of one depends upon the level
of the other
Treatment One set of levels of all factors employed in a given experimental trial
Answer A A A
Careful observations lead to questions that
• From where ???????
arise…
– Curiosity
Screen: Which are the biggest – Information Gaps
factors?
– Controversy
Characterize: What is the relationship between – Replication
responses and factors?
– Literature Review
Optimize: What is the best setting of – Other People
the factors? – ...???
Verify: Are the results repeatable?
• Time-lines of the Problem: some problems take little time for its solution while others
take more time. So, it depends on the time in which we have
to complete his research work
• Data Availability: If the desired data is available to the researcher, then the
problem would be selected
• Urgency: Urgent problem must be given priority because the immediate solution
can benefit the people
• Feasibility:
The researcher qualification, training and experience should match
• Area Culture: the problem
The culture of the area for which a researcher conducts his research is
also responsible for the selection of research problem
www.studylecturenotes.com
VS.
• The CONTROL is the group or condition that is used as the basis for
comparison for the results of the changes in the independent variable
OR
QUANTITATIVE
• This is a NUMBER or “quantity”
• an objective measure or
observation
• measured numerically
Examples: Distance, mass,
QUALITATIVE volume, density
• This is a WORD or “quality”
• a subjective measure other than an
number
• categorical in nature
Examples: An odor, color, texture,
taste, etc.
4. Calculations are
generally to the right
3. Y Axis – DV columns - after stated
data
2. X Axis – IV
• Unbiased
– Randomization • Wide range of applicability
– Blinding – Deliberate variation
• High precision – Factorial designs
– Uniform material • Able to estimate uncertainty
– Replication – Replication
– Stratification – Randomization
• Simple
– Protect against
mistakes
30
Thank you
01/20/2022 31
Quiz (10%) TA: 15 minutes
1. Explain the project proposal with its content, mention basic elements of
introduction sequentially.
2. Describe the need of literature review and enumerate the sources of
literature review.
3. What is the goal and outcomes of this course?
4. Why the experiment is important in engineering?
5. What are the basic principles of the design of experiments?