MATH 224: ENGINEERING DATA ANALYSIS

CHAPTER 1: The Role of Statistics in Engineering

Professor: Engr. Danny Dave B. Fabiaña

OUTLINE

1-1 The Engineering Method and 4. Experiment: Design and run an

Statistical experiment to test the tentative
1-2 Collecting Engineering Data model.
1-3 Mechanistic and Empirical
5. Analysis: Analyze data collected
Models Thinking
in the experiment.
1-4 Probability and Probability
Models 6. Model modification: Refine the
tentative model.
1-1 The Engineering Method and 7. Model validation: Validate the
Statistical Thinking engineering model by a follow-up
experiment.
LEARNING GOALS:
8. Conclusion (recommendation): Draw
 Explain engineering problem conclusions or make recommendations
solving process. based on the analysis results.
 Describe the application of (Note) Some of these steps may be
statistics in the engineering iterated as necessary.
problem solving process.
 Distinguish between APPLICATION OF STATISTICS
enumerative and analytic
studies. Statistical methods are
applied to interpret data with
Engineering Problem Solving Process variability. Throughout the
engineering problem solving process,
Engineers develop practical engineers often encounter data
solutions and techniques for showing variability. Statistics
engineering problems by applying provides essential tools to deal
scientific principles and with the observed variability.
methodologies. Existing systems are Examples of the application of
improved and/or new systems are statistics in the engineering
introduced by the engineering problem solving process include, but
approach for better harmony between are not limited to, the following:
humans, systems, and environments
1. Summarizing and presenting data:
numerical summary and visualization
In general, the engineering in descriptive statistics (Chapter
problem solving process includes the 6).
following steps: 2. Inferring the characteristics
1. Problem definition: Describe the (mean, median, proportion, and
problem to solve. variance) of single/two populations:
z, t, x*, and F tests in parametric
2. Factor identification: Identify statistics (Chapters 7-10); signed,
primary factors which cause the signed-rank, and rank-sum tests in
problem. nonparametric statistics (Chapter
15).
3. Model (hypothesis) suggestion:
Propose a model (hypothesis) that
explains the relationship between
the problem and factors.
 MATH 224: ENGINEERING DATA ANALYSIS
CHAPTER 1: The Role of Statistics in Engineering
Professor: Engr. Danny Dave B. Fabiaña

3. Testing the relationship between

DATA COLLECTION METHOD
variables: correlation analysis
(Chapter 11); categorical data
analysis (Chapter 8).
Three methods are available for
4. Modeling the causal relationship data collection:
between the response and independent
1. Retrospective study: Use existing
variables: regression analysis
records of the population. Some
(Chapters 1 1-12); analysis of
crucial information may be
variance (Chapters 13-14).
unavailable and the validity of data
5. Identifying the sources of be questioned.
variability in response: analysis of
2. Observational study: Collect data
variance (Chapters 13-14).
by observing the population with as
6. Evaluating the relative minimal interference as possible.
importance of factors for the Information of the population for
response variable: regression some conditions of interest may be
analysis (Chapter 12); analysis of unavailable and some observations be
variance (Chapter 14). contaminated by extraneous
variables.
7. Designing an efficient, effective
experiment: design of experiment 3. Designed experiment: Collect data
(Chapters 13-14). by observing the population while
controlling conditions on the
These applications would lead to experiment plan. The findings would
development of general laws and obtain scientific rigorousness
principles such as Ohm's law and through deliberate control of
design guidelines. extraneous variables.
ENUMERATIVE VS. ANALYTIC
STUDIES
1-3 Mechanistic and Empirical
Two types of studies are Models
defined depending on the use of a
sample in statistical vs. inference: LEARNING GOALS:
1. Enumerative study: Makes an  Explain the difference between
inference to the well-defined mechanistic and empirical
population from Studies which the models.
MECHANISTIC VS. EMPIRICAL MODELS
sample is selected. (e.g.) defective
rate of products in a lot
Models (explaining the
2. Analytic study: Makes an
relationship between variables) can
inference to a future (conceptual)
be divided into two categories:
population. (e.g.) defective rate of
products at a production line 1. Mechanistic model: Established
based on the underlying
1-2 Collecting Engineering Data theory, principle, or law of a
physical mechanism.
LEARNING GOALS:
 Explain three methods of data
(e.g.)
collection: retrospective
study, Observational study,
and designed experiment.
 MATH 224: ENGINEERING DATA ANALYSIS
CHAPTER 1: The Role of Statistics in Engineering
Professor: Engr. Danny Dave B. Fabiaña

where: I = current, E = voltage, R=

resistance, and E = random error
2. Empirical model: Established
based on the experience,
observation, or experiment of
a system (population) under
study.
(e.g.)

Where: y = sitting height, x =

stature, and E = random error

1-4 Probability and Probability

Models
LEARNING GOALS:

 Describe the application of

probability in the engineering
problem solving process

APPLICATION OF PROBABILITY
Along with statistics, the
concepts and models of probability
are applied in the Probability
engineering problem solving process
for the following:
1. Modeling the stochastic behavior
of the system: discrete and
continuous probability
distributions.
2. Quantifying the risks involved in
statistical inference: error
probabilities in hypothesis testing.
3. Determining the sample size of an
experiment for a designated test
condition: sample size selection