0% found this document useful (0 votes)
79 views32 pages

Fundamentals of Design Experiments Part 1

The document discusses the key components of experimental design including defining the problem, developing a hypothesis, designing an experiment to test the hypothesis, collecting and analyzing data, and interpreting results. It provides examples of single-factor and multi-factor experimental designs and discusses important concepts such as independent and dependent variables, repeated trials, and qualitative and quantitative observations.

Uploaded by

ali
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
79 views32 pages

Fundamentals of Design Experiments Part 1

The document discusses the key components of experimental design including defining the problem, developing a hypothesis, designing an experiment to test the hypothesis, collecting and analyzing data, and interpreting results. It provides examples of single-factor and multi-factor experimental designs and discusses important concepts such as independent and dependent variables, repeated trials, and qualitative and quantitative observations.

Uploaded by

ali
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Majd Shhadi, PhD

First Semester 2018/2019


1
EXPERIMENTAL DESIGN
27

Science answers questions with experiments


Prof. Amer EL-Hamouz
Define The Problem
28

Begin by asking a question about your topic

What is a good question for an experiment?

One that is testable with the materials at hand

Prof. Amer EL-Hamouz


Hypothesis
29

Now we need a hypothesis to guide our investigation

What is a hypothesis?

Your best thinking about how the change you make might affect
another factor.

Tentative or trial solution to the question.


An if ………… then ………… statement.
Prof. Amer EL-Hamouz
Design an Experiment
30

 Must design an experiment that will test your hypothesis.

 This experiment will allow you to change some conditions or


variables to test your hypothesis.

Prof. Amer EL-Hamouz


Introduction to Design of Experiments
31

Variables: All the factors, their levels and all the measured traits
(responses) are variables (Variables are things that change).

Independent or class variables: Factors applied to the experimental


units are independent variables. Is the variable that is purposely
changed. It is the manipulated variable.

Response or dependent variables: Measured or observed traits in


the experiment. Changes in response to the independent variable.

The strength of the paper measured after ‘treated’ with starch is a


response (or dependent) variable
Majd Shhadi, PhD
Categorical vs. Quantitative Variables
32

Variables can be classified as categorical (qualitative) or


quantitative (numerical).

 Categorical variables take on values that are names or labels. The


color of a ball (e.g., red, green, blue).

 Quantitative variables are numerical. They represent a


measurable quantity. For example, when we speak of the
population of a city.

Majd Shhadi, PhD


Categorical Variable Characteristics
33

 Recorded usually with words.


 Records which of several groups an individual belongs to.
 Count data in each group, but you logically should not average it.
 Includes all yes/no questions
 Categorical variables that have only two possible outcomes (e.g.,
"yes" vs. "no" or "success" vs. "failure") are known as binary
variables (or Bernoulli variables).
 Graphing: best illustrated with a pie chart (but could also be a bar
graph)

Majd Shhadi, PhD


Quantitative Variable Characteristics
34

 Possible responses are numerical in nature


 Includes values for which it makes sense to do operations like
adding, totaling and averaging
 Includes answers to how much/how many questions
 Always includes ‘units’
 Graphing: best illustrated with a bar chart

Majd Shhadi, PhD


Discrete vs. Continuous Variables
35

 Quantitative variables can be further


classified as discrete or continuous. Categorical
(Qualitative)
 If a variable can take on any value
between two specified values, it is
called a continuous variable (i.e., it’s Variables Discrete
a number & it can be any value)
Usually a variable that can be Quantitative
‘measured’. (Numerical)

 If the variable is a sets of isolated Continuous


points on the number line, it is called a
discrete (i.e., it’s a number but it only
comes in certain values) Usually a
variable that can be ‘counted’.
Majd Shhadi, PhD
Categorical or Quantitative
36

If Categorical, one possible category?


If Quantitative, Continuous or Discrete? Units?

1. Subject of a book?
2. Number of pages in the book?
3. Area of each page of book?
4. Number of letters on a page?

Majd Shhadi, PhD


Introduction to Design of Experiments
37

Factor
 A factor of an experiment is a controlled independent variable
whose levels are set by the experimenter.
➢ The effect of additive on paper strength (additive is a factor).

❑ Constants or Controlled Variables: Factors that are kept the same


and not allowed to change.
❑ It is important to control all but one variable at a time to be able
to interpret data.

Treatment
A treatment is a level (amount) of factor applied to the experimental
units.
Majd Shhadi, PhD
Single-factor Design
38

Example I
Response variable :Yield from a chemical process (conversion of the
raw materials to final product)
Begin with experiments involving a single factor
Amount of catalyst used in the process

Majd Shhadi, PhD


Introduction to Design of Experiments
39

Example I
Response variable
 Yield from a chemical process (conversion of the raw materials to
final product)

Factors
 Factor A: Temperature at which process is run
 Factor B: Amount of catalyst used in the process

Majd Shhadi, PhD


Two-factor Design
40

In this experiment
Factor A (temperature) is at three levels, 20, 30, and 45oC
Factor B (mass of catalyst) is at two levels, 100 and 150 kg

Note that for each


combination of
treatment levels,
we have 2
observations of the
response variable
(duplicate)

Majd Shhadi, PhD


Four-factor Design
41

Example II
Response: conversion
Factor A: Temperature (50, 100, 150, 200 oC)
Factor B: Pressure (5, 10, 15 MPa)
Factor C: Mass of Catalyst (100, 200, 300 g)
Factor D: degree of agitation (500, 1000 rpm)

The importance of designing experiments really kicks in for multi-


factor experiments

Majd Shhadi, PhD


Materials and Procedures
42

A description of what you will use for your experiment, and how you
will do it.

Be sure to include:

 Listing of the Variables

 Repeated Trials

 Drawing of Apparatus (if applicable)

Prof. Amer EL-Hamouz


How will you vary the Independent
Variable?
43

How many different values of the independent variable should we


test?
3 ? 5? 10? The more the better?

Repeated Trials
What are repeated trials?
The number of times that a value of the independent variable is
tested.

Why are repeated trials necessary?


They reduce the possibility of chance errors affecting the results.
Prof. Amer EL-Hamouz
Drawing of Experiment
44

Include Labels to clearly identify the important parts of the


experimental setup

Level of solution

Angle of refraction

Beaker filled with sugar solution

Prof. Amer EL-Hamouz


Qualitative Observations and Results
45

What are qualitative observations?


They are what you perceive that occurred during the course of your
experiment. They are identification of trends in the data.

What are quantitative observations?


Numbers in the form of raw data displayed in data tables and
graphs

Prof. Amer EL-Hamouz


Sample Data Table
46

Title: The Effect of the independent variable on the dependent


variable
Column for
Column for dependent Column for derived
independent
variable quantity
variable
Label – with units if necessary –
Label – with units if multiple trials included Label – with units if
necessary necessary. Example =
average of trials
1 2 3

Prof. Amer EL-Hamouz


Sample Data Table
47

Title: The Effect of the independent variable on the dependent


variable
Dependent Variable –
include units and an
appropriate scale

Independent Variable
Prof. Amer EL-Hamouz
Analysis and Interpretation of Results
48

 This is where you describe in words what is illustrated by your data


as shown in your table and graph.

 You also describe the meaning of the results.

Possible Experimental Errors

What factors in your materials or procedure might have had an


impact on your results?

Prof. Amer EL-Hamouz


Conclusion
49

 Why or why not your results supported or did not support the
hypothesis.

 Hypotheses are never “wrong”. They are either supported or not


supported.

 Include reasons for the hypothesis to be supported or unsupported.

Prof. Amer EL-Hamouz


Recommendations for Further Experimentation
50

 What are some practical applications of your results?

 What other questions that could be tested arise from your results?

Prof. Amer EL-Hamouz


What kind of question would you ask?
51

 Materials provided: sugar, stir sticks, access to warm and cold


water and ice, thermometers, beakers, object that floats partially
submerged in water, graph paper, jumbo paper clip, straws, rulers,
protractor

Come up with a question related to solutions

Prof. Amer EL-Hamouz


Possible Questions
52

 Effects of temperature on solubility


 Effects of concentration on depth object sinks in solution
 Effects of stirring on solubility
 Effects of concentration on height of solution rising in straw
 Effect of amount of sugar dissolved on temperature of solution
 Effect of temperature on how long a set amount of sugar required
to dissolve.

Prof. Amer EL-Hamouz


Possible Hypotheses
53

 If we raise the temperature then the solubility will ???

 If we increase the sugar concentration then the height of solution


rising in the straw will ???

 If we dissolve more sugar in the solution then the temperature


will ???

Prof. Amer EL-Hamouz


One-Variable-At-a-Time (OVAT) experiments
54

 Engineers and scientists often perform one-factor-at-a time (OFAT)


or One-Variable-At-a-Time (OVAT) experiments, which vary only
one factor or variable at a time while keeping others fixed.

 This approach depends upon guesswork, luck, experience and


intuition for its success.

 Moreover, this type of experimentation requires large resources to


obtain a limited amount of information about the process.

 OVAT experiments often are unreliable, inefficient, time consuming


and may yield false optimum condition for the process.

Majd Shhadi, PhD


One-Variable-At-a-Time (OVAT) experiments
55

 An engineer is interested in measuring the yield of a chemical


process, which is influenced by two key process variables (or control
factors).

 The engineer decides to perform an experiment to study the effects


of these two variables on the process yield.

 The engineer uses an OVAT approach to experimentation.

 The first step is to keep the temperature constant (T1) and vary the
pressure from P1 to P2.

 The next step is to keep the pressure constant (P1) and vary the
temperature from T1 to T2
Majd Shhadi, PhD
One-Variable-At-a-Time (OVAT) experiments
56

 The experiment is repeated twice and the results are illustrated in


the following Tables

Majd Shhadi, PhD


One-Variable-At-a-Time (OVAT) experiments
57

 The engineer has calculated the average yield values for only
three combinations of temperature and pressure: (T1, P1), (T1, P2)
and (T2, P1).

 The question then arises as to what should be the average yield


corresponding to the combination (T2, P2)?

 The engineer was unable to study this combination as well as the


interaction between temperature and pressure.

 The OVAT approach to experimentation can be misleading and


may lead to unsatisfactory experimental conclusions in real life
situations.
Majd Shhadi, PhD

You might also like