12/03/2024

Chapter 1. Introduction

CERE 107 1.1 Definition of Experimental Design

Experimental Design
DESIGN AND ANALYSIS OF EXPERIMENTS IN  The design of experiments (DOE), also known as experiment design or experimental
design, is the design of any task that aims to describe and explain the variation of
CERAMIC ENGINEERING information under conditions that are hypothesized to reflect the variation.

 Experimental design is a concept used to organize, conduct, and interpret results of

experiments in an efficient way, making sure that as much useful information as
possible is obtained by performing a small number of trials.

 An experimental design is a detailed plan for collecting and using data to identify causal
relationships. Through careful planning, the design of experiments allows your data
collection efforts to have a reasonable chance of detecting effects and testing
hypotheses that answer your research questions.
Prepared and Compiled by:
EMIE SALAMANGKIT MIRASOL, CerE, MSMSE, PhD  Design of experiments is an organized way of conducting and analyzing controlled tests
Associate Professor II to determine the influence of inputs and their interactions on the output response.

Chapter 1. Introduction
1.1 Definition of Experimental Design
Topics:
The three basic principles of experimental design are randomization, replication, and
Chapter 1. Introduction blocking. Sometimes we add the factorial principle to these three.
1.1 Definition of Experimental Design
1.2 Benefits of using Statistical Experimental Designs Randomization is the cornerstone underlying the use of statistical methods in
1.3 Applications of Statistical Experimental Designs experimental design. By randomization we mean that both the allocation of the
1.3a. Variable Screening Experiments experimental material and the order in which the individual runs of the experiment are
to be performed are randomly determined. Statistical methods require that the
1.3b. Optimization Studies
observations (or errors) be independently distributed random variables. Randomization
1.3c. Mechanistic Studies usually makes this assumption valid. By properly randomizing the experiment,
we also assist in “averaging out” the effects of extraneous factors that may be present.
By the end of the chapter, the students must have: For example, suppose that the specimens in the hardness experiment are of slightly
1. define experimental design; different thicknesses and that the effectiveness of the quenching medium may be
2. determine benefits of using statistical experimental designs; and affected by specimen thickness. If all the specimens subjected to the oil quench are
3. apply statistical experimental designs. thicker than those subjected to the saltwater quench, we may be introducing
systematic bias into the experimental results. This bias handicaps one of the quenching
media and consequently invalidates our results.
 12/03/2024

Chapter 1. Introduction Chapter 1. Introduction

1.1 Definition of Experimental Design 1.2 Benefits of using Statistical Experimental Designs
The three basic principles of experimental design are randomization, replication, and The important goals in ceramic research are to reduce the cost and to improve the specific
blocking. Sometimes we add the factorial principle to these three. properties of products. Statistical experimental design and analysis are effective tools to
assist ceramists to reach their stated forward looking goals.
By replication we mean an independent repeat run of each factor combination.
Thus, if five specimens are treated in each quenching medium, we say that five Statistical design of experiments is the process of planning the experiment so that
replicates have been obtained. Each of the 10 observations should be run in random appropriate data will be collected and statistically analyzed.
order. These methods not only help ceramists to plan and conduct experiments but also assist
Replication has two important properties. them in analysis of the resulting data. With good experimental design and analysis, the
1. it allows the experimenter to obtain an estimate of the experimental error. This maximum amount of information can be obtained from a minimum amount of collected
estimate of error becomes a basic unit of measurement for determining whether data.
observed differences in the data are really statistically different.
2. if the sample mean ( y bar) is used to estimate the true mean response for one of As an example of such an experiment, suppose that a ceramist is interested in studying the effects of time
(x1) and firing temperature (x2), as well as chemical composition (x3), on water absorption (y1) and
the factor levels in the experiment, replication permits the experimenter to obtain a
modulus of rupture (y2) of light weight concrete. The factors that will be controlled and varied in his study
more precise estimate of this parameter. are inputs (x1, x2, and x3) and the properties which will be measured or calculated are outputs (y1 and y2).
In general, there are always some uncontrollable factors (z1, z2, …zi) in every experiment.

Chapter 1. Introduction Chapter 1. Introduction

1.1 Definition of Experimental Design 1.2 Benefits of using Statistical Experimental Designs
The three basic principles of experimental design are randomization, replication, and As an example of such an experiment, suppose that a ceramist is interested in studying
blocking. Sometimes we add the factorial principle to these three. the effects of time (x1) and firing temperature (x2), as well as chemical composition (x3),
on water absorption (y1) and modulus of rupture (y2) of light weight concrete. The factors
Blocking is a design technique used to improve the precision with which comparisons that will be controlled and varied in his study are inputs (x1, x2, and x3) and the properties
among the factors of interest are made. Often blocking is used to reduce or eliminate which will be measured or calculated are outputs (y1 and y2). In general, there are always
the variability transmitted from nuisance factors—that is, factors that may influence some uncontrollable factors (z1, z2, …zi) in every experiment.
the experimental response but in which we are not directly interested.
Design of experiments is an organized way of conducting and analyzing controlled tests to
For example, an experiment in a chemical process may require two batches of raw determine the influence of inputs and their interactions on the output response. Since the
material to make all the required runs. inputs are varied and simultaneously tested, causal predictive models can be evaluated.
Experiments conducted without design have several disadvantages and can only establish
correlation but not causality.

An experiment is a data collection procedure that occurs in controlled conditions to

identify and understand causal relationships between variables.
 12/03/2024

Chapter 1. Introduction Chapter 1. Introduction

1.3 Applications of Statistical Experimental Designs 1.3 Applications of Statistical Experimental Designs
Experimental design methods have found broad application in many disciplines. we may Guidelines for Designing Experiments
view experimentation as part of the scientific process and as one of the ways by which
we learn about how systems or processes work. Generally, we learn through a series of
activities in which we make conjectures about a process, perform experiments to
generate data from the process, and then use the information from the experiment to
establish new conjectures, which lead to new experiments, and so on.

Experimental design is a critically important tool in the scientific and engineering world
for improving the product realization process. Critical components of these activities are
in new manufacturing process design and development, and process management. The
application of experimental design techniques early in process development can result in
1. Improved process yields
2. Reduced variability and closer conformance to nominal or target requirements
3. Reduced development time
4. Reduced overall costs.

Chapter 1. Introduction Chapter 1. Introduction

1.3 Applications of Statistical Experimental Designs 1.3 Applications of Statistical Experimental Designs
Experimental design methods are also of fundamental importance in engineering design 1.3a. Variable Screening Experiments or Characterizing Experiments
activities, where new products are developed and existing ones improved. Some
applications of experimental design in engineering design include When a system or process is new, it is usually important to learn which factors have the
1. Evaluation and comparison of basic design configurations most influence on the response(s) of interest.
2. Evaluation of material alternatives
3. Selection of design parameters so that the product will work well under a wide variety Often there are a lot of factors. This usually indicates that the experimenters do not know
of field conditions, that is, so that the product is robust much about the system so screening is essential if we are to efficiently get the desired
4. Determination of key product design parameters that impact product performance performance from the system.
5. Formulation of new products.
Screening experiments are extremely important when working with new systems or
The use of experimental design in product realization can result in products that are technologies so that valuable resources will not be wasted using best guess and one-factor
easier to manufacture and that have enhanced field performance and reliability, lower at a time (OFAT) approaches.
product cost, and shorter product design and development time. Designed experiments
also have extensive applications in marketing, market research, transactional and service Sometimes we call an experiment such as this a screening experiment. Typically,
operations, and general business operations. screening or characterization experiments involve using fractional factorial designs.
 12/03/2024

Chapter 1. Introduction Chapter 1. Introduction

1.3 Applications of Statistical Experimental Designs 1.3 Applications of Statistical Experimental Designs
1.3a. Variable Screening Experiments or Characterizing Experiments 1.3a. Variable Screening Experiments or Characterizing Experiments

The information from this screening or characterization experiment will be used to In the situation mentioned in earlier example,
identify the critical process factors and to determine the direction of adjustment for these - Engineers are interested in characterizing or investigating the fabrication of NBC
factors to reduce further the number of defects per unit. ceramic membranes; that is, they want to determine which factors (both controllable
and uncontrollable) affect the fabrication.
The experiment may also provide information about which factors should be more
carefully controlled during routine manufacturing to prevent high defect levels and erratic - To accomplish this, they can design an experiment that will enable them to estimate
process performance. the magnitude and direction of the factor effects; that is,
- how much does the response variable (porosity and mechanical strength) change
Thus, one result of the experiment could be the application of techniques such as control when each factor is changed, and does changing the factors together produce
charts to one or more process variables (such as sintering temperature), in addition to different results than are obtained from individual factor adjustments
control charts on process output. Over time, if the process is improved enough, it may be - do the factors interact?
possible to base most of the process control plan on controlling process input variables
instead of control charting the output.

Chapter 1. Introduction Chapter 1. Introduction

1.3 Applications of Statistical Experimental Designs 1.3 Applications of Statistical Experimental Designs
1.3a. Variable Screening Experiments or Characterizing Experiments 1.3b. Optimization Studies

A screening design is used to assess a large number of process or design parameters to After the system has been characterized and we are reasonably certain that the important
identify the most influential factors that affect the process performance. factors have been identified, the next objective is usually optimization, that is, find the
settings or levels of the important factors that result in desirable values of the response.
Example: A study investigates factors affecting the fabrication of natural ball clay (NBC)
ceramic membranes using the 24 full factorial design (FFD) with two replications at each For example, if a screening experiment on a chemical process results in the identification
point. The factors studied were: particle size of the sawdust, percentage of sawdust, of time and temperature as the two most important factors, the optimization experiment
amount of binder, and sintering temperature. The FFD study results indicated that the may have as its objective finding the levels of time and temperature that maximize yield,
sawdust particle size and the percentage of sawdust had a positive impact on the porosity or perhaps maximize yield while keeping some product property that is critical to the
and mechanical strength of the NBC ceramic membrane. This demonstrates the customer within specifications.
importance of performing a screening experiment prior to an extensive investigation of
certain factors such as in the optimization studies. An optimization experiment is usually a follow-up to a screening experiment. It would be
(https://onlinelibrary.wiley.com/doi/10.1002/ceat.202200093?af=R) very unusual for a screening experiment to produce the optimal settings of the important
factors.
 12/03/2024

Chapter 1. Introduction
1.3 Applications of Statistical Experimental Designs
1.3c. Mechanistic Studies

Experimentation is a vital part of the scientific (or engineering) method. Now there are
certainly situations where the scientific phenomena are so well understood that useful
results including mathematical models can be developed directly by applying these well-
understood principles. The models of such phenomena that follow directly from the
physical mechanism are usually called mechanistic models.

A simple example is the familiar equation for current flow in an electrical circuit, Ohm’s
law, E IR.
However, most problems in science and engineering require observation of the system at
work and experimentation to elucidate information about why and how it works. Well-
designed experiments can often lead to a model of system performance; such
experimentally determined models are called empirical models. These empirical models
can be manipulated by a scientist or an engineer just as a mechanistic model can.

Assignment:
1.1. Suppose that you want to design an experiment to study the proportion of unpopped
kernels of popcorn. Complete steps 1–3 of the guidelines for designing experiments in
Section 1.4. Are there any major sources of variation that would be difficult to control?

References:
Montgomery, D. C. (2013). Design and Analysis of Experiments Eight Edition. John Wiley & Sons, Inc. (QA279.M66 2013)
Refereed Journals, Bulletins and e-book from the Internet