Upload
vuque
View
218
Download
0
Embed Size (px)
Citation preview
Statistics for Engineers
ChE 4C3 and 6C3
© Kevin Dunn, 2016
http://learnche.mcmaster.ca/4C3
Overall revision number: 155 (January 2016)
1
Copyright, sharing, and attribution notice
This work is licensed under the Creative Commons Attribution-ShareAlike 3.0
Unported License. To view a copy of this license, please visit
http://creativecommons.org/licenses/by-sa/3.0/
This license allows you:
I to share - to copy, distribute and transmit the work, includingprint it
I to adapt - but you must distribute the new result under thesame or similar license to this one
I commercialize - you are allowed to use this work forcommercial purposes
I attribution - but you must attribute the work as follows:I “Portions of this work are the copyright of Kevin Dunn”, orI “This work is the copyright of Kevin Dunn”
(when used without modification)
2
We appreciate:
I if you let us know about any errors in the slides
I any suggestions to improve the notes
All of the above can be done by writing to
or anonymous messages can be sent to Kevin Dunn at
http://learnche.mcmaster.ca/feedback-questions
If reporting errors/updates, please quote the current revision number: 155
Please note that all material is provided “as-is” and no liability willbe accepted for your usage of the material.
3
Data visualization section
I Data ink
I Clear, concise plots are critical to help you with the message
4
Univariate section
I Histograms
I Normal distribution and q-q plot
I Central limit theorem
I External vs internal methods to test for differences
5
Least squares
I ANOVA table interpretation
I Standard errors
I Confidence intervals
6
Least squares
Model
y = b1x1 + b2x2
7
Least squares
I Example of integer and continuous variables
8
Design and analysis of experimentsI Doing it wrong:
9
Design and analysis of experimentsI Factorial model: is a local approximation
10
Design and analysis of experiments
I DOE models are just least squares models:
11
Design and analysis of experimentsI Use the trade-off table: please bring copy to the final exam
12
Design and analysis of experiments
Model is only valid in alocal region
13
Process monitoring
I Shewhart charts
I CUSUM charts
I EWMA charts
I Cpk: width of process operation
14
University education is changing in different ways
You are thefirst group atMcMaster toexperiencethis style ofonlinecourse.
15
This course is also evolving: differences each year
I 2010: Response surface methods competition
I 2011: Take-home tests
I 2012: Electronic assignment/project submissions
I 2013: Electronic tests/quizzes
I 2014: Peer evaluation of the course project
I 2015: Online/video learning
I appreciate your comments and feedback.Please fill in your course evaluations: https://evals.mcmaster.ca
An extra course evaluation will be available for 4C3/6C3specifically about the online components.
16
Final exam
I Friday, 24 April, 09:00, IWC-1 (please confirm)
I 3 hours
I Covers all topics taught throughout the semester
I Counts 40% of the course grade
17
Final exam: how to do well
I This is a course that gives you a set of tools
I Think about the question’s objective; choose the mostappropriate tool
I Think about the results: what do they mean?I Do not just plug in values into equations
I Check if they are reasonable.
18
Final exam: some strategies
I Do the hardest and highest weighted questions first
I Short quick questions at the end
I Don’t repeat the question back to me
I Use bullet points, where appropriate
I Answer length should be appropriate to number of marks
I Read the questions carefully: “[2] Calculate and interpret..”
19
Final exam: more strategies
Copies of previous exam questions are on the course site
I 2010, 2011, 2012, 2013, and 2014 final exams available onwebsite
I Solutions to most questions are in PID textbook, or in theassignments
http://yint.org/practice-problems
20
Finally ...
I If you have any corrections to the notes (grammar, spelling,etc) - please don’t hesitate to email me
I Any suggestions to improve the notes gratefully accepted
I The course website will be permanently available
http://learnche.mcmaster.ca/4C3
Process Improvement using Data
http://learnche.mcmaster.ca/pid
21
Finally ...
I I’d like to hear about your successes with these methods
I Also any issues and problems in using these tools
I Feel free to email meI Stay in contact:
I http://ca.linkedin.com/in/kgdunn
I Thanks for your interest, your questions, your DoE projects,and enthusiasm with tackling an online delivered course.
22