Diploma in Statistics Design and Analysis of Experiments Lecture 2.11 Design and Analysis of Experiments Lecture 2.1 1.Review of Lecture 1.2 2.Randomised.

Slides:



Advertisements
Similar presentations
BPS - 5th Ed. Chapter 241 One-Way Analysis of Variance: Comparing Several Means.
Advertisements

Analysis of Variance Outlines: Designing Engineering Experiments
i) Two way ANOVA without replication
STT 511-STT411: DESIGN OF EXPERIMENTS AND ANALYSIS OF VARIANCE Dr. Cuixian Chen Chapter 14: Nested and Split-Plot Designs Design & Analysis of Experiments.
Model Adequacy Checking in the ANOVA Text reference, Section 3-4, pg
Simple Linear Regression. Start by exploring the data Construct a scatterplot  Does a linear relationship between variables exist?  Is the relationship.
STAT 2120 Tim Keaton. ANalysis Of VAriance (ANOVA) ANOVA is a generalization of the comparison of two population means In ANOVA, we compare k population.
Objectives (BPS chapter 24)
Design and Analysis of Experiments Dr. Tai-Yue Wang Department of Industrial and Information Management National Cheng Kung University Tainan, TAIWAN,
The Two Factor ANOVA © 2010 Pearson Prentice Hall. All rights reserved.
© 2010 Pearson Prentice Hall. All rights reserved The Complete Randomized Block Design.
Every achievement originates from the seed of determination. 1Random Effect.
Chapter 3 Experiments with a Single Factor: The Analysis of Variance
Basic Business Statistics, 11e © 2009 Prentice-Hall, Inc. Chap 14-1 Chapter 14 Introduction to Multiple Regression Basic Business Statistics 11 th Edition.
Hypothesis Testing. Introduction Always about a population parameter Attempt to prove (or disprove) some assumption Setup: alternate hypothesis: What.
13-1 Designing Engineering Experiments Every experiment involves a sequence of activities: Conjecture – the original hypothesis that motivates the.
Simple Linear Regression Analysis
Center for Biofilm Engineering Marty Hamilton Professor Emeritus of Statistics Montana State University Statistical design & analysis for assessing the.
Slide 1 Larger is better case (Golf Ball) Linear Model Analysis: SN ratios versus Material, Diameter, Dimples, Thickness Estimated Model Coefficients for.
13 Design and Analysis of Single-Factor Experiments:
Statistics for Managers Using Microsoft Excel, 4e © 2004 Prentice-Hall, Inc. Chap 13-1 Chapter 13 Introduction to Multiple Regression Statistics for Managers.
Inference for regression - Simple linear regression
5-1 Introduction 5-2 Inference on the Means of Two Populations, Variances Known Assumptions.
Diploma in Statistics Design and Analysis of Experiments Lecture 4.11 Design and Analysis of Experiments Lecture 4.1 Review of Lecture 3.1 Homework
QNT 531 Advanced Problems in Statistics and Research Methods
Copyright © 2013, 2010 and 2007 Pearson Education, Inc. Chapter Comparing Three or More Means 13.
Lecture 2.11 © 2015 Michael Stuart Design and Analysis of Experiments Lecture Review –Minute tests 1.2 –Homework –Randomized Blocks Design 2.Randomised.
Diploma in Statistics Introduction to Regression Lecture 2.21 Introduction to Regression Lecture Review of Lecture 2.1 –Homework –Multiple regression.
Diploma in Statistics Design and Analysis of Experiments Lecture 5.11 © 2010 Michael Stuart Lecture 5.1 Part 1 "Split Plot" experiments 1.Review of –randomised.
M23- Residuals & Minitab 1  Department of ISM, University of Alabama, ResidualsResiduals A continuation of regression analysis.
1 Design of Engineering Experiments Part 10 – Nested and Split-Plot Designs Text reference, Chapter 14, Pg. 525 These are multifactor experiments that.
23-1 Analysis of Covariance (Chapter 16) A procedure for comparing treatment means that incorporates information on a quantitative explanatory variable,
Design and Analysis of Experiments Dr. Tai-Yue Wang Department of Industrial and Information Management National Cheng Kung University Tainan, TAIWAN,
Diploma in Statistics Design and Analysis of Experiments Lecture 4.21 Design and Analysis of Experiments Lecture 4.2 Part 1: Components of Variation –identifying.
Business Statistics: A First Course, 5e © 2009 Prentice-Hall, Inc. Chap 12-1 Correlation and Regression.
Introduction to Probability and Statistics Thirteenth Edition Chapter 12 Linear Regression and Correlation.
Chapter 10: Analyzing Experimental Data Inferential statistics are used to determine whether the independent variable had an effect on the dependent variance.
Chap 14-1 Copyright ©2012 Pearson Education, Inc. publishing as Prentice Hall Chap 14-1 Chapter 14 Introduction to Multiple Regression Basic Business Statistics.
Lecture 8 Simple Linear Regression (cont.). Section Objectives: Statistical model for linear regression Data for simple linear regression Estimation.
Inference for Regression Simple Linear Regression IPS Chapter 10.1 © 2009 W.H. Freeman and Company.
Chapter 19 Analysis of Variance (ANOVA). ANOVA How to test a null hypothesis that the means of more than two populations are equal. H 0 :  1 =  2 =
Lecture 3.11 © 2014 Michael Stuart Design and Analysis of Experiments Lecture Review of Lecture 2.2 –2-level factors –Homework A 2 3 experiment.
ANALYSIS OF VARIANCE (ANOVA) BCT 2053 CHAPTER 5. CONTENT 5.1 Introduction to ANOVA 5.2 One-Way ANOVA 5.3 Two-Way ANOVA.
Lack of Fit (LOF) Test A formal F test for checking whether a specific type of regression function adequately fits the data.
Multiple regression. Example: Brain and body size predictive of intelligence? Sample of n = 38 college students Response (Y): intelligence based on the.
1 Always be contented, be grateful, be understanding and be compassionate.
Lecture 10 Chapter 23. Inference for regression. Objectives (PSLS Chapter 23) Inference for regression (NHST Regression Inference Award)[B level award]
ETM U 1 Analysis of Variance (ANOVA) Suppose we want to compare more than two means? For example, suppose a manufacturer of paper used for grocery.
Chapter 13 Design of Experiments. Introduction “Listening” or passive statistical tools: control charts. “Conversational” or active tools: Experimental.
Chapter 11: The ANalysis Of Variance (ANOVA)
Copyright © 2016, 2013, 2010 Pearson Education, Inc. Chapter 10, Slide 1 Two-Sample Tests and One-Way ANOVA Chapter 10.
732G21/732G28/732A35 Lecture 4. Variance-covariance matrix for the regression coefficients 2.
Lecture 2.11 © 2016 Michael Stuart Design and Analysis of Experiments Lecture Review –Minute tests 1.2 –Homework –Experimental factors with several.
Lecture 2.21  2016 Michael Stuart Design and Analysis of Experiments Lecture Review Lecture 2.1 –Minute test –Why block? –Deleted residuals 2.Interaction.
Statistics for Managers Using Microsoft Excel, 5e © 2008 Prentice-Hall, Inc.Chap 14-1 Statistics for Managers Using Microsoft® Excel 5th Edition Chapter.
Design and Analysis of Experiments (7) Response Surface Methods and Designs (2) Kyung-Ho Park.
Designs for Experiments with More Than One Factor When the experimenter is interested in the effect of multiple factors on a response a factorial design.
McGraw-Hill/IrwinCopyright © 2009 by The McGraw-Hill Companies, Inc. All Rights Reserved. Experimental Design and Analysis of Variance Chapter 11.
1 Statistical Analysis Professor Lynne Stokes Department of Statistical Science Lecture #10 Testing the Statistical Significance of Factor Effects.
Slide 1 DESIGN OF EXPERIMENT (DOE) OVERVIEW Dedy Sugiarto.
Diploma in Statistics Design and Analysis of Experiments Lecture 2.21 © 2010 Michael Stuart Design and Analysis of Experiments Lecture Review of.
Diploma in Statistics Design and Analysis of Experiments Lecture 4.11 © 2010 Michael Stuart Design and Analysis of Experiments Lecture Review of.
General Full Factorial Design
Inference for Least Squares Lines
i) Two way ANOVA without replication
Comparing Three or More Means
Chapter 10: Analysis of Variance: Comparing More Than Two Means
Chapter 11: The ANalysis Of Variance (ANOVA)
Essentials of Statistics for Business and Economics (8e)
Design and Analysis of Experiments
Presentation transcript:

Diploma in Statistics Design and Analysis of Experiments Lecture 2.11 Design and Analysis of Experiments Lecture Review of Lecture Randomised Block Design and Analysis –Illustration –Explaining ANOVA –Interaction? –Effect of Blocking –Matched pairs as Randomised blocks 3.Introduction to 2-level factorial designs –A 2 2 experiment –Set up –Analysis –Application

Diploma in Statistics Design and Analysis of Experiments Lecture 2.12 Minute Test - How Much

Diploma in Statistics Design and Analysis of Experiments Lecture 2.13 Minute Test - How Fast

Diploma in Statistics Design and Analysis of Experiments Lecture 2.14 Was the blocking effective?

Diploma in Statistics Design and Analysis of Experiments Lecture 2.15 Comparing several means Membrane A:standard Membrane B:alternative using new material Membrane C:other manufacturer Membrane D:other manufacturer Burst strength (kPa) of 10 samples of each of four filter membrane types

Diploma in Statistics Design and Analysis of Experiments Lecture 2.16 Comparing several means Tukey 95% Simultaneous Confidence Intervals All Pairwise Comparisons among Levels of Membrane Membrane = A subtracted from: Membrane Lower Center Upper B (---*----) C (----*---) D (----*----) Membrane = B subtracted from: Membrane Lower Center Upper C (----*---) D (----*----) Membrane = C subtracted from: Membrane Lower Center Upper D (---*----)

Diploma in Statistics Design and Analysis of Experiments Lecture 2.17 Comparing several means Membrane B mean is significantly bigger than Membranes C and D means and close to significantly bigger than Membrane A mean. Membrane C mean is significantly smaller than the other three means. Membranes A and D means are not significantly different.

Diploma in Statistics Design and Analysis of Experiments Lecture 2.18 Comparing several means; Conclusions Membrane C can be eliminated from our inquiries. Membrane D shows no sign of being an improvement on the existing Membrane A and so need not be considered further. Membrane B shows some improvement on Membrane A but not enough to recommend a change. It may be worth while carrying out further comparisons between Membranes A and B.

Diploma in Statistics Design and Analysis of Experiments Lecture 2.19 Characteristics of an experiment Experimental units: entities on which observations are made Experimental Factor: controllable input variable Factor Levels / Treatments: values of the factor Response: output variable measured on the units

Diploma in Statistics Design and Analysis of Experiments Lecture Randomised blocks Illustration Manufacture of an organic chemical using a filtration process Three step process: –input chemical blended from different stocks –chemical reaction results in end product suspended in an intermediate liquid product –liquid filtered to recover end product.

Diploma in Statistics Design and Analysis of Experiments Lecture Randomised blocks Illustration Problem:yield loss at filtration stage Proposal:adjust initial blend to reduce yield loss Plan: –prepare five different blends –use each blend in successive process runs, in random order –repeat at later times (blocks)

Diploma in Statistics Design and Analysis of Experiments Lecture Results

Diploma in Statistics Design and Analysis of Experiments Lecture Exercise What were the experimental units factor factor levels response blocks randomisation procedure

Diploma in Statistics Design and Analysis of Experiments Lecture Minitab Analysis General Linear Model ANOVA General Linear Model: Loss, per cent versus Blend, Block Analysis of Variance for Loss,%, using Adjusted SS for Tests Source DF Seq SS Adj SS Adj MS F P Blend Block Error Total S = R-Sq = 65.38% R-Sq(adj) = 39.41% Unusual Observations for Loss, per cent Loss, per Obs cent Fit SE Fit Residual St Resid R

Diploma in Statistics Design and Analysis of Experiments Lecture 2.115

Diploma in Statistics Design and Analysis of Experiments Lecture Conclusions (prelim.) F(Blends) is almost statistically significant, p = 0.07 F(Blocks) is not statistically significant, p = 0.4 Prediction standard deviation:S = 0.93

Diploma in Statistics Design and Analysis of Experiments Lecture Deleted diagnostics

Diploma in Statistics Design and Analysis of Experiments Lecture Iterated analysis: delete Case 12 General Linear Model: Loss versus Blend, Block Analysis of Variance for Loss Source DF Seq SS Adj SS Adj MS F P Blend Block Error Total S =

Diploma in Statistics Design and Analysis of Experiments Lecture Deleted diagnostics

Diploma in Statistics Design and Analysis of Experiments Lecture Conclusions (prelim.) F(Blends) is highly statistically significant, p = 0.01 F(Blocks) is not statistically significant, p = 0.65 Prediction standard deviation:S = 0.67

Diploma in Statistics Design and Analysis of Experiments Lecture Explaining ANOVA ANOVA depends on a decompostion of "Total variation" into components: Total Variation = Blend effect + Block effect + chance variation;

Diploma in Statistics Design and Analysis of Experiments Lecture Decomposition of results

Diploma in Statistics Design and Analysis of Experiments Lecture Decomposition of results

Diploma in Statistics Design and Analysis of Experiments Lecture Decomposition of results

Diploma in Statistics Design and Analysis of Experiments Lecture Decomposition of results

Diploma in Statistics Design and Analysis of Experiments Lecture Decomposition of results

Diploma in Statistics Design and Analysis of Experiments Lecture Decomposition of results

Diploma in Statistics Design and Analysis of Experiments Lecture Decomposition of results

Diploma in Statistics Design and Analysis of Experiments Lecture Interaction? Blend x Block interaction?

Diploma in Statistics Design and Analysis of Experiments Lecture Interaction? Blend x Block interaction?

Diploma in Statistics Design and Analysis of Experiments Lecture Exercise Calculate fitted values: Overall Mean + Blend Deviation + Block deviation

Diploma in Statistics Design and Analysis of Experiments Lecture Exercise (cont'd) Make a Block profile plot

Diploma in Statistics Design and Analysis of Experiments Lecture Fitted values; NO INTERACTION

Diploma in Statistics Design and Analysis of Experiments Lecture Actual plot: Interaction? Blend effects (the contributions of each blend to Loss) are similar for Blocks 1 and 2 but quite different for Block 3.

Diploma in Statistics Design and Analysis of Experiments Lecture Effect of Blocking Analysis of Variance for Loss (one run deleted) Source DF Seq SS Adj SS Adj MS F P Blend Block Error Total Analysis of Variance for Loss (one run deleted) unblocked Source DF Seq SS Adj SS Adj MS F P Blend Error Total

Diploma in Statistics Design and Analysis of Experiments Lecture Matched pairs as Randomised blocks Wear of shoe soles made of two materials, A and B, worn on opposite feet by each of 10 boys

Diploma in Statistics Design and Analysis of Experiments Lecture Pairing equals Blocking Paired T for Material B - Material A T-Test of mean difference = 0 (vs not = 0): T-Value = 3.35 P-Value = Two-way ANOVA: Wear versus Material, Boy Source DF SS MS F P Material Boy Error Total

Diploma in Statistics Design and Analysis of Experiments Lecture t and F

Diploma in Statistics Design and Analysis of Experiments Lecture t and F

Diploma in Statistics Design and Analysis of Experiments Lecture More on t

Diploma in Statistics Design and Analysis of Experiments Lecture More on F

Diploma in Statistics Design and Analysis of Experiments Lecture Paired Comparison: Effect of Pairing / Blocking Paired T for Material B - Material A T-Test of mean difference = 0 (vs not = 0): T-Value = 3.35 P-Value = Two-sample T for Material B vs Material A T-Value = 0.37 P-Value = 0.716

Diploma in Statistics Design and Analysis of Experiments Lecture Paired Comparison: Effect of Pairing / Blocking Two-way ANOVA: Wear versus Material, Boy Source DF SS MS F P Material Boy Error Total One-way ANOVA: Wear versus Material Source DF SS MS F P Material Error Total

Diploma in Statistics Design and Analysis of Experiments Lecture Introduction to 2-level factorial designs A 2 2 experiment Project: optimisation of a chemical process yield Factors (with levels): operating temperature (Low, High) catalyst (C1, C2) Design: Process run at all four possible combinations of factor levels, in duplicate, in random order.

Diploma in Statistics Design and Analysis of Experiments Lecture Exercise What were the experimental units factors factor levels response blocks randomisation procedure

Diploma in Statistics Design and Analysis of Experiments Lecture Set up

Diploma in Statistics Design and Analysis of Experiments Lecture Set up: Randomisation

Diploma in Statistics Design and Analysis of Experiments Lecture Set up: Run order

Diploma in Statistics Design and Analysis of Experiments Lecture Results (run order)

Diploma in Statistics Design and Analysis of Experiments Lecture Results (standard order)

Diploma in Statistics Design and Analysis of Experiments Lecture Analysis (Minitab) Main effects and Interaction plots Pareto plot of effects ANOVA results –with diagnostics Calculation of t-statistic

Diploma in Statistics Design and Analysis of Experiments Lecture Main Effects and Interactions

Diploma in Statistics Design and Analysis of Experiments Lecture Pareto plot of effects Bar height = t value (see slide 31) Reference line is at critical t value (4 df)

Diploma in Statistics Design and Analysis of Experiments Lecture Minitab DOE Analyze Factorial Design Estimated Effects and Coefficients for Yield (coded units) Term Effect Coef SE Coef T P Constant Temperature Catalyst Temperature*Catalyst S = R-Sq = 95.83% R-Sq(adj) = 92.69% Analysis of Variance for Yield (coded units) Source DF Seq SS Adj SS Adj MS F P Main Effects Way Interactions Residual Error Pure Error Total

Diploma in Statistics Design and Analysis of Experiments Lecture 2.155

Diploma in Statistics Design and Analysis of Experiments Lecture Minitab DOE Analyze Factorial Design Estimated Effects and Coefficients for Yield (coded units) Term Effect Coef SE Coef T P Constant Temperature Catalyst Temperature*Catalyst S = R-Sq = 95.83% R-Sq(adj) = 92.69% Analysis of Variance for Yield (coded units) Source DF Seq SS Adj SS Adj MS F P Main Effects Way Interactions Residual Error Pure Error Total

Diploma in Statistics Design and Analysis of Experiments Lecture ANOVA results ANOVA superfluous for 2 k experiments "There is nothing to justify this complexity other than a misplaced belief in the universal value of an ANOVA table". BHH (2nd ed.), Section 5.10 "a convenient method of arranging the arithmetic" R.A. Fisher

Diploma in Statistics Design and Analysis of Experiments Lecture Diagnostic Plots

Diploma in Statistics Design and Analysis of Experiments Lecture Calculation of t-statistic Results (Temperature order)

Diploma in Statistics Design and Analysis of Experiments Lecture Exercise Calculate a confidence interval for the Temperature effect. All effects may be estimated and tested in this way. Homework Test the statistical significance of and calculate confidence intervals for the Catalyst effect and the Temperature × Catalyst interaction.

Diploma in Statistics Design and Analysis of Experiments Lecture Application Finding the optimum More Minitab results Least Squares Means for Yield Mean SE Mean Temperature Low High Catalyst Temperature*Catalyst Low High Low High

Diploma in Statistics Design and Analysis of Experiments Lecture 

Diploma in Statistics Design and Analysis of Experiments Lecture Optimum operating conditions Highest yield achieved with Catalyst 2 at High temperature. Estimated yield: 81.5% 95% confidence interval: 81.5 ± 2.78 × 2.622, i.e., 81.5 ± 7.3, i.e., ( 74.2, 88.8 )

Diploma in Statistics Design and Analysis of Experiments Lecture Homework As part of a project to develop a GC method for analysing trace compounds in wine without the need for prior extraction of the compounds, a synthetic mixture of aroma compounds in ethanol- water was prepared. The effects of two factors, Injection volume and Solvent flow rate, on GC measured peak areas given by the mixture were assessed using a 2 2 factorial design with 3 replicate measurements at each design point. The results are shown in the table that follows. What conclusions can be drawn from these data? Display results numerically and graphically. Check model assumptions by using appropriate residual plots.

Diploma in Statistics Design and Analysis of Experiments Lecture Peak areas for GC study (EM, Exercise 5.2)

Diploma in Statistics Design and Analysis of Experiments Lecture Reading EM §5.3, §7.4.2 DCM §§4-1, 5-1, 5-2, 6-1, 6-2