This preview shows pages 1–3. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: 1 INSE 6220  Week 10 Advanced Statistical Approaches to Quality Experimental Design Design of Experiments in Process Improvement Factorial Experiments Factorial Design Dr. A. Ben Hamza Concordia University Factor A Factor B 2 Linear Regression and Analysis of Variance 2 2 2 1 1 1 ( ) ( ) ( ) n n n i i i i i i i T R E y y y y y y SS SS SS The total sum of squares of the observed y values is a measure of the total variability in the response: And the sample correlation coefficient is given by: Analysis of Variance for Testing Significance of Regression Source of Variation Sum of Squares Degrees of Freedom Mean Square Regression Error or residual Total 1 xy xx T xx yy S S r SS S S 1 /2 1 R R R E E E T SS MS MS MS SS n MS SS n F 2 2 1 1 , ( ) , n xy R xy T yy i E T R i xx S SS S SS S y y SS SS SS S 3 Linear regression: MATLAB example We want to check if there is a linear relationship between y and x x = [0.1750 0.2200 0.2250 0.2260 0.2500 0.2765]'; y = [0.0480 0.0525 0.0540 0.0535 0.0570 0.0610]'; plot( x , y ,'o'); grid on; xlabel( ' x ' ); ylabel( ' y ' ); Now we want to use the regress function to estimate the model parameters and perform regression diagnostics. The regress function requires that the matrix of independent variables includes a column of ones so that the model contains a constant term, so we create a matrix X as: X = [ones(size(x)) x]; b = regress(y,X); betahat0 = b(1); betahat1 = b(2); yhat = betahat0 + betahat1*x; hold on; plot(x,yhat,'r'); 0.16 0.18 0.2 0.22 0.24 0.26 0.28 0.3 0.046 0.048 0.05 0.052 0.054 0.056 0.058 0.06 0.062 x y 1 i i y x Red curve: 4 Introduction to Design of Experiments An experiment is a test or a series of tests Experiments are used widely in the engineering world Process characterization & optimization Evaluation of material properties Product design & development Component & system tolerance determination All experiments are designed experiments, some are poorly designed, some are welldesigned Reduce time to design/develop new products & processes Improve performance of existing processes Improve reliability and performance of products Achieve product & process robustness Evaluation of materials, design alternatives, setting component & system tolerances, etc. 5 Experimental Design Objectives of an experiment may include: 1) Determining which variables are most influential on response y . 2) Determining where to set influential x s so that y is near nominal requirement. (which level?) 3) Determining where to set influential x s so that variability in y is small....
View
Full
Document
This note was uploaded on 09/07/2011 for the course INSE 6210 taught by Professor Benhamza during the Fall '10 term at Concordia Canada.
 Fall '10
 Benhamza

Click to edit the document details