Experimental design. Matti Hotokka Department of Physical Chemistry Åbo Akademi University

Size: px
Start display at page:

Download "Experimental design. Matti Hotokka Department of Physical Chemistry Åbo Akademi University"

Transcription

1 Experimental design Matti Hotokka Department of Physical Chemistry Åbo Akademi University

2 Contents Elementary concepts Regression Validation Design of Experiments Definitions Random sampling Factorial designs Response surface designs Robust parameter design [1] Otto, Chemometrics, Wiley, [2] Wu, Hamada, Experiments, Wiley, [3] Snedecor & Cochran: Statistical Methods, Iowa State Univ. Press [4] Cochran, Experimental designs, Wiley, 1966.

3 Definitions Analytical function Signal y: to be modeled or optimized. E.g., yield, measuring time, figure-of-merit, deviation from a model etc. y x

4 Definitions Factors Factor, or feature: ph, concentration, temperature,... A huge number of factors govern every measurement. The chemist must know which are important and must be tested. The others are kept as constant as possible.

5 Definitions Replications Every measurement is repeated from start a number of times so that a mean, a standard error and a confidence limit can be determined. Observation: mean of a set of parallel measurements. Blank: reference observation with default value of all the important factors, y B.

6 Definitions Replications vs. Repetitions Repetition: Repeated reading of the meter. Replication: New measurement from start. Repetitions test your ability to read a digital meter. Replications test the experimental errors in the measuring procedure.

7 Definitions Calibration parameters Sensitivity Detection limit Precision and trueness Specificity and selectivity

8 Definitions Calibration curve Sensitivity = slope Signal, y y = b0 + b1 x x y y b1 = x b 0 Intercept b 0 can be ignored if the sample is obtained against a blank (reference). Concentration, x

9 Definitions Analytical range Dynamic range: The valid range of x where the signal y depends functionally on x. Analytical range: the interval of x where the signal y can be determined accurately.

10 Definitions Signal, y DL Dynamic range Analytical range LoD Concentration, x

11 Definitions Detection limit Detection limit: lowest value of x where the signal can still be separated from noise. Noise is measured as the variance of the blank. y = y + 3 s x DL B B DL = y DL b b 0 1

12 Definitions Limit of determination Limit of determination: lowest value of x (concentration) where y can be determined with a useful accuracy.

13 Definitions Bias Error e in variable x (say, concentration) e = x x true x

14 Definitions Bias Error e in variable x (say, concentration) ( ) ( ) e = x x = x x + x x true Random error true Bias Random error x true x x Systematic error

15 Definitions Precision and trueness Precision = repeatability s = ( x x) n i 1 2 Trueness = deviation from true value x RR(%) = 100 x true

16 Definitions Selectivity Selectivity: possibility to measure in presence of interfering components. Specificity: sensitivity for a given analyte. Analytical resolution: N = x/ x. x x

17

18 Random sampling Why randomization All experiments must be made in random order. Response Response Systematic True slope Drift Random True slope Concentration Concentration

19 Random sampling Random number lists The random sequences are obtained from tables of random numbers. Nowadays random number generators of pocket calculators may be used. Normally, you get the same sequence every time. This is OK. If you want truly random numbers you should use a random seed.

20 Random sampling Always randomize Assume that four different concentrations are to be tested. Name them A, B, C, D. Make four parallel measurements for each: A 1, A 2, A 3, A 4 etc.

21 Random sampling Always randomize First run: Measure A 1, B 1, C 1, D 1. Second run: Start from scratch and do A 2, B 2, etc. A 1, B 1, C 1, D 1 A 2, B 2, C 2, D 2 A 3, B 3, C 3, D 3 Wrong! Systematic errors will not be found. A 4, B 4, C 4, D 4

22 Random sampling Always randomize Randomize the order of concentrations in the runs. A 1, B 1, C 1, D 1 C 2, D 2, A 2, B 2 D 3, A 3, B 3, C 3 B 4, C 4, D 4, A 4

23 Random sampling Always randomize Use linear (or non-linear) regression to analyse the results. Specifically, plot the residues to see whether some effects were not captured.

24 Random sampling Analysis y A B C D Conc.

25 Random sampling Residues Residues A 1, B 1, C 1, D 1 C 2, D 2, A 2, B 2 D 3, A 3, B 3, C 3 B 4, C 4, D 4, A 4 Drift! A B C D Conc.

26 Random sampling Types of factors Controlled factors Varied systematically or kept constant Known factors that cannot be controlled E.g., drift of instrument Unknown factors that can be anticipated E.g., impurities of the chemicals Truly unknown effects

27 Random sampling Blocking Some constant factors cannot be kept fixed but vary from batch to batch, day to day,... Make a series of measurements varying one factor and keeping the other conditions as constant as possible => A 1, B 1, C 1, D 1. This is a block. Then measure A 2, B 2, C 2, D 2 keeping the conditions constant but not necessarily the same as in block 1 if this is not possible.

28 Random sampling Latin square designs Randomize the blocking experiment. Run Sample A B D C 2 D C A B 3 B D C A 4 C A B D Observe the good balance.

29

30 Factorial designs What? Typically two-level experiments A low level and a high level for each factor. Typically for screening Study which of the presumed factors really show a significant effect.

31 Factorial designs Two levels Each factor is tested at a low and a high level. Designate the levels symbolically -1 and +1. Rate of p-phenylenediamine (PPD) oxidation at constant enzyme level of 13.6 mg L -1 is studied using spectrophotometry: Factor Level T, C ph [PPD], mm

32 Factorial designs Experiment plan Run Factors T PPD ph y 1 - y 4 y s but like this, randomized.

33 Factorial designs 2 k design Run Coded factor levels Main effects Interaction effects T PPD ph TxPPD TxpH PPDxpH y Experimental accuracy? Four parallel determinations => s = D.f.=3. Compute the differences high level - low level: D T =(y 1 +y 2 +y 3 +y 4 )/4 - (y 5 +y 6 +y 7 +y 8 )/4

34 Factorial designs 2 k design D T = 0.53 D PPD = 5.73 D ph = 2.19 D TxPPD = D TxpH = D PPDxpH = Statistically significant effects at 95 % confidence: D >Student t s = 0.18, 3 degrees of freedom => t = 3.18 D > = D PPD, D ph and D PPDxpH are significant. s

35 Factorial designs Another analysis method Consider the normal distribution. P y 1 y 1 0 x 0 0 Most statistical quantities are normally distributed. x y

36 Factorial designs Half-normal quantiles Given the integrated normal distribution in a y vs y plot, calculate what is the x that gives your y value. i Φ N In the example there are six effects, N = 6. What is x if y is *(1-0.5)/6 = 0.542? Answer: This you obtain from the tables of normal distribution.

37 Factorial designs Half-normal quantiles Six effects: N = 6. Numbered 1,2,3,...,6 in ascending order. Therefore i y = *(i-0.5)/8 x

38 Factorial designs Half-normal quantiles Sort the D values in ascending order x y TxpH TxPPD T PPDxpH ph PPD TxpH PPD ph T PPDxpH TxPPD 1 2

39 Factorial designs Orthogonal arrays The 2 k design gives 64 combinations for k = 8. Too many degrees of freedom! Choose half of the combinations, 2 k-1. However, you cannot choose any set of combinations. The arrays must be orthogonal.

40 Factorial designs Orthogonal arrays There are many ways of choosing orthogonal arrays. Plackett and Burmann, and Hall, and Taguchi, have published large selections based on Hadamard matrices.

41 Taguchi table L4 (2 3 ) Taguchi table L4 (2 3 ) Full set of experiments Eight experiments

42 Taguchi table L4 (2 3 ) Taguchi table L4 (2 3 ) Taguchi design Four experiments

43 Factorial designs Orthogonal arrays What you loose when using orthogonal arrays is (some of) the interaction effects.

44 Factorial designs More reduction Designs of size 2 k-p, p>1, also have been proposed.

45 Factorial designs Three-level designs +1 x x 1

46 Factorial designs Three-level designs Response -1 0 Factor +1

47 Factorial designs Central composite design y y y y y y y y 8 9 -a 0 0 y a 0 0 y a 0 y a 0 y a y a y 14 15, 16, y 15, y 16, y 17

48 Factorial designs Box-Behnken design

49 Factorial designs Lattice design

50 Factorial designs Analysis Use multivariate regression.

51

52 Response surfaces Optimization tasks Biggest is best Find a set of factor values that give maximal response (e.g., yield) Smallest is best Find minimum Nominal is best Minimize the difference (measured - nominal)

53 Response surfaces The response ph PPD

54 Response surfaces Optimization techniques Any optimization strategy can be used Single factor at a time (the engineering method) may miss the optimum Fixed-size simplex algorithm may work better

55 Response surfaces Engineering method ph Max Measure at the indicated points. PPD

56 Response surfaces Simplex method Code the factor values to the range (0,1). Generate the initial simplex. Measure at the indicated points. ph If there are N factors (here N=2) the simplex has N+1 points. Here the points are 0,0;1,0; 0.5, PPD Unknown surface

57 Response surfaces Simplex method ph 1 0 w 0 p 1 Remove the worst point. Calculate the centroid of the remaining points. PPD p = 1 N N + 1 v j + 1 j = 1 j w

58 Response surfaces Simplex method Measure at the indicated point. ph 1 0 w 0 p r 1 Generate a new point. PPD r = p + ( p w)

59 Response surfaces Simplex method Measure at the indicated points. ph 1 0 w 0 1 PPD

60

61 Robust parameters Factor categories Control factors Can be kept fixed once chosen Noise factors Cannot be controlled Create the variations in the quality of the product

62 Robust parameters Typical procedure Usually, the quality of the product is improved by reducing the noise. Unfortunately the noise factors are difficult (=expensive) to reduce.

63 Robust parameters 2 k design, a reminder Run Coded factor levels Main effects Interaction effects T PPD ph TxPPD TxpH PPDxpH y

64 Robust parameters Control of noise Main effects: All control and noise factors. Interaction effects between control factors and noise factors may be quite large. If this is the case, then variations in the product quality may be reduced by adjusting the control factors so that the effect of noise is reduced.

65 Robust parameters An example Consider the dependence of y (signal level) on x (voltage over detector = control factor). y Width of noise A B x

Experimental design. Matti Hotokka Department of Physical Chemistry Åbo Akademi University

Experimental design. Matti Hotokka Department of Physical Chemistry Åbo Akademi University Experimental design Matti Hotokka Department of Physical Chemistry Åbo Akademi University Contents Elementary concepts Regression Validation Hypotesis testing ANOVA PCA, PCR, PLS Clusters, SIMCA Design

More information

Chemometrics. Matti Hotokka Physical chemistry Åbo Akademi University

Chemometrics. Matti Hotokka Physical chemistry Åbo Akademi University Chemometrics Matti Hotokka Physical chemistry Åbo Akademi University Hypothesis testing Inference method Confidence levels Descriptive statistics Hypotesis testing Predictive statistics Hypothesis testing

More information

Chemometrics. Matti Hotokka Physical chemistry Åbo Akademi University

Chemometrics. Matti Hotokka Physical chemistry Åbo Akademi University Chemometrics Matti Hotokka Physical chemistry Åbo Akademi University Linear regression Experiment Consider spectrophotometry as an example Beer-Lamberts law: A = cå Experiment Make three known references

More information

-However, this definition can be expanded to include: biology (biometrics), environmental science (environmetrics), economics (econometrics).

-However, this definition can be expanded to include: biology (biometrics), environmental science (environmetrics), economics (econometrics). Chemometrics Application of mathematical, statistical, graphical or symbolic methods to maximize chemical information. -However, this definition can be expanded to include: biology (biometrics), environmental

More information

Application of mathematical, statistical, graphical or symbolic methods to maximize chemical information.

Application of mathematical, statistical, graphical or symbolic methods to maximize chemical information. Application of mathematical, statistical, graphical or symbolic methods to maximize chemical information. -However, this definition can be expanded to include: biology (biometrics), environmental science

More information

Experimental Design and Optimization

Experimental Design and Optimization . Experimental Design Stages a) Identifying the factors which may affect the results of an experiment; b) Designing the experiment so that the effects of uncontrolled factors are minimized; c) Using statistical

More information

Response Surface Methodology

Response Surface Methodology Response Surface Methodology Process and Product Optimization Using Designed Experiments Second Edition RAYMOND H. MYERS Virginia Polytechnic Institute and State University DOUGLAS C. MONTGOMERY Arizona

More information

Response Surface Methodology:

Response Surface Methodology: Response Surface Methodology: Process and Product Optimization Using Designed Experiments RAYMOND H. MYERS Virginia Polytechnic Institute and State University DOUGLAS C. MONTGOMERY Arizona State University

More information

Taguchi Method and Robust Design: Tutorial and Guideline

Taguchi Method and Robust Design: Tutorial and Guideline Taguchi Method and Robust Design: Tutorial and Guideline CONTENT 1. Introduction 2. Microsoft Excel: graphing 3. Microsoft Excel: Regression 4. Microsoft Excel: Variance analysis 5. Robust Design: An Example

More information

Practical Statistics for the Analytical Scientist Table of Contents

Practical Statistics for the Analytical Scientist Table of Contents Practical Statistics for the Analytical Scientist Table of Contents Chapter 1 Introduction - Choosing the Correct Statistics 1.1 Introduction 1.2 Choosing the Right Statistical Procedures 1.2.1 Planning

More information

Basic Statistics. 1. Gross error analyst makes a gross mistake (misread balance or entered wrong value into calculation).

Basic Statistics. 1. Gross error analyst makes a gross mistake (misread balance or entered wrong value into calculation). Basic Statistics There are three types of error: 1. Gross error analyst makes a gross mistake (misread balance or entered wrong value into calculation). 2. Systematic error - always too high or too low

More information

Preface Introduction to Statistics and Data Analysis Overview: Statistical Inference, Samples, Populations, and Experimental Design The Role of

Preface Introduction to Statistics and Data Analysis Overview: Statistical Inference, Samples, Populations, and Experimental Design The Role of Preface Introduction to Statistics and Data Analysis Overview: Statistical Inference, Samples, Populations, and Experimental Design The Role of Probability Sampling Procedures Collection of Data Measures

More information

Response Surface Methodology: Process and Product Optimization Using Designed Experiments, 3rd Edition

Response Surface Methodology: Process and Product Optimization Using Designed Experiments, 3rd Edition Brochure More information from http://www.researchandmarkets.com/reports/705963/ Response Surface Methodology: Process and Product Optimization Using Designed Experiments, 3rd Edition Description: Identifying

More information

Validation of an Analytical Method

Validation of an Analytical Method Validation of an Analytical Method Refer to: ICH Guideline Q2(R1), Validation of Analytical Procedures: Teaxt andmethodology. Introduction All major laboratories eg. in the industry operates with clearly

More information

RESPONSE SURFACE MODELLING, RSM

RESPONSE SURFACE MODELLING, RSM CHEM-E3205 BIOPROCESS OPTIMIZATION AND SIMULATION LECTURE 3 RESPONSE SURFACE MODELLING, RSM Tool for process optimization HISTORY Statistical experimental design pioneering work R.A. Fisher in 1925: Statistical

More information

Introduction to the Design and Analysis of Experiments

Introduction to the Design and Analysis of Experiments Introduction to the Design and Analysis of Experiments Geoffrey M. Clarke, MA,Dip.stats.,c.stat. Honorary Reader in Applied Statistics, University of Kent at Canterbury and Consultant to the Applied Statistics

More information

Experimental Design Matrix of Realizations for Optimal Sensitivity Analysis

Experimental Design Matrix of Realizations for Optimal Sensitivity Analysis Experimental Design Matrix of Realizations for Optimal Sensitivity Analysis Oy Leuangthong (oy@ualberta.ca) and Clayton V. Deutsch (cdeutsch@ualberta.ca) Department of Civil and Environmental Engineering

More information

MATH602: APPLIED STATISTICS

MATH602: APPLIED STATISTICS MATH602: APPLIED STATISTICS Dr. Srinivas R. Chakravarthy Department of Science and Mathematics KETTERING UNIVERSITY Flint, MI 48504-4898 Lecture 10 1 FRACTIONAL FACTORIAL DESIGNS Complete factorial designs

More information

ASEAN GUIDELINES FOR VALIDATION OF ANALYTICAL PROCEDURES

ASEAN GUIDELINES FOR VALIDATION OF ANALYTICAL PROCEDURES ASEAN GUIDELINES FOR VALIDATION OF ANALYTICAL PROCEDURES Adopted from ICH Guidelines ICH Q2A: Validation of Analytical Methods: Definitions and Terminology, 27 October 1994. ICH Q2B: Validation of Analytical

More information

TWO-LEVEL FACTORIAL EXPERIMENTS: IRREGULAR FRACTIONS

TWO-LEVEL FACTORIAL EXPERIMENTS: IRREGULAR FRACTIONS STAT 512 2-Level Factorial Experiments: Irregular Fractions 1 TWO-LEVEL FACTORIAL EXPERIMENTS: IRREGULAR FRACTIONS A major practical weakness of regular fractional factorial designs is that N must be a

More information

ON REPLICATION IN DESIGN OF EXPERIMENTS

ON REPLICATION IN DESIGN OF EXPERIMENTS ON REPLICATION IN DESIGN OF EXPERIMENTS Bianca FAGARAS 1), Ingrid KOVACS 1), Anamaria OROS 1), Monica RAFAILA 2), Marina Dana TOPA 1), Manuel HARRANT 2) 1) Technical University of Cluj-Napoca, Str. Baritiu

More information

8 RESPONSE SURFACE DESIGNS

8 RESPONSE SURFACE DESIGNS 8 RESPONSE SURFACE DESIGNS Desirable Properties of a Response Surface Design 1. It should generate a satisfactory distribution of information throughout the design region. 2. It should ensure that the

More information

Stat 5303 (Oehlert): Tukey One Degree of Freedom 1

Stat 5303 (Oehlert): Tukey One Degree of Freedom 1 Stat 5303 (Oehlert): Tukey One Degree of Freedom 1 > catch

More information

OF ANALYSIS FOR DETERMINATION OF PESTICIDES RESIDUES IN FOOD (CX/PR 15/47/10) European Union Competence European Union Vote

OF ANALYSIS FOR DETERMINATION OF PESTICIDES RESIDUES IN FOOD (CX/PR 15/47/10) European Union Competence European Union Vote 1 April 2015 European Union s CODEX COMMITTEE ON PESTICIDE RESIDUES 47 th Session Beijing, China, 13 18 April 2015 AGENDA ITEM 8 PROPOSED DRAFT GUIDELINES ON PERFORMANCE CRITERIA SPECIFIC FOR METHODS OF

More information

SIX SIGMA IMPROVE

SIX SIGMA IMPROVE SIX SIGMA IMPROVE 1. For a simplex-lattice design the following formula or equation determines: A. The canonical formula for linear coefficients B. The portion of each polynomial in the experimental model

More information

Detection and quantification capabilities

Detection and quantification capabilities 18.4.3.7 Detection and quantification capabilities Among the most important Performance Characteristics of the Chemical Measurement Process (CMP) are those that can serve as measures of the underlying

More information

Optimal Selection of Blocked Two-Level. Fractional Factorial Designs

Optimal Selection of Blocked Two-Level. Fractional Factorial Designs Applied Mathematical Sciences, Vol. 1, 2007, no. 22, 1069-1082 Optimal Selection of Blocked Two-Level Fractional Factorial Designs Weiming Ke Department of Mathematics and Statistics South Dakota State

More information

Robust Design: An introduction to Taguchi Methods

Robust Design: An introduction to Taguchi Methods Robust Design: An introduction to Taguchi Methods The theoretical foundations of Taguchi Methods were laid out by Genichi Taguchi, a Japanese engineer who began working for the telecommunications company,

More information

Analytical Performance & Method. Validation

Analytical Performance & Method. Validation Analytical Performance & Method Ahmad Aqel Ifseisi Assistant Professor of Analytical Chemistry College of Science, Department of Chemistry King Saud University P.O. Box 2455 Riyadh 11451 Saudi Arabia Building:

More information

Moment Aberration Projection for Nonregular Fractional Factorial Designs

Moment Aberration Projection for Nonregular Fractional Factorial Designs Moment Aberration Projection for Nonregular Fractional Factorial Designs Hongquan Xu Department of Statistics University of California Los Angeles, CA 90095-1554 (hqxu@stat.ucla.edu) Lih-Yuan Deng Department

More information

Module III Product Quality Improvement. Lecture 4 What is robust design?

Module III Product Quality Improvement. Lecture 4 What is robust design? Module III Product Quality Improvement Lecture 4 What is robust design? Dr. Genichi Taguchi, a mechanical engineer, who has won four times Deming Awards, introduced the loss function concept, which combines

More information

CHEM 3420 /7420G Instrumental Analysis

CHEM 3420 /7420G Instrumental Analysis CHEM 3420 /7420G Instrumental Analysis Prof. Brian Gibney 2411 Ingersoll bgibney@brooklyn.cuny.edu Course Introduction Prof. Brian R. Gibney B.S. Chemistry (ACS Certified) Ph.D. Chemistry Brooklyn College,

More information

Taguchi Design of Experiments

Taguchi Design of Experiments Taguchi Design of Experiments Many factors/inputs/variables must be taken into consideration when making a product especially a brand new one The Taguchi method is a structured approach for determining

More information

Test 3 Practice Test A. NOTE: Ignore Q10 (not covered)

Test 3 Practice Test A. NOTE: Ignore Q10 (not covered) Test 3 Practice Test A NOTE: Ignore Q10 (not covered) MA 180/418 Midterm Test 3, Version A Fall 2010 Student Name (PRINT):............................................. Student Signature:...................................................

More information

Calibration (The Good Curve) Greg Hudson EnviroCompliance Labs, Inc.

Calibration (The Good Curve) Greg Hudson EnviroCompliance Labs, Inc. Calibration (The Good Curve) Greg Hudson EnviroCompliance Labs, Inc. greghudson@envirocompliance.com www.envirocompliance.com Abstract It should come as no surprise that the correlation coefficient is

More information

Objective Experiments Glossary of Statistical Terms

Objective Experiments Glossary of Statistical Terms Objective Experiments Glossary of Statistical Terms This glossary is intended to provide friendly definitions for terms used commonly in engineering and science. It is not intended to be absolutely precise.

More information

CHAPTER 6 A STUDY ON DISC BRAKE SQUEAL USING DESIGN OF EXPERIMENTS

CHAPTER 6 A STUDY ON DISC BRAKE SQUEAL USING DESIGN OF EXPERIMENTS 134 CHAPTER 6 A STUDY ON DISC BRAKE SQUEAL USING DESIGN OF EXPERIMENTS 6.1 INTRODUCTION In spite of the large amount of research work that has been carried out to solve the squeal problem during the last

More information

R 2 and F -Tests and ANOVA

R 2 and F -Tests and ANOVA R 2 and F -Tests and ANOVA December 6, 2018 1 Partition of Sums of Squares The distance from any point y i in a collection of data, to the mean of the data ȳ, is the deviation, written as y i ȳ. Definition.

More information

Passing-Bablok Regression for Method Comparison

Passing-Bablok Regression for Method Comparison Chapter 313 Passing-Bablok Regression for Method Comparison Introduction Passing-Bablok regression for method comparison is a robust, nonparametric method for fitting a straight line to two-dimensional

More information

Harris: Quantitative Chemical Analysis, Eight Edition CHAPTER 03: EXPERIMENTAL ERROR

Harris: Quantitative Chemical Analysis, Eight Edition CHAPTER 03: EXPERIMENTAL ERROR Harris: Quantitative Chemical Analysis, Eight Edition CHAPTER 03: EXPERIMENTAL ERROR Chapter 3. Experimental Error -There is error associated with every measurement. -There is no way to measure the true

More information

DESIGN AND ANALYSIS OF EXPERIMENTS Third Edition

DESIGN AND ANALYSIS OF EXPERIMENTS Third Edition DESIGN AND ANALYSIS OF EXPERIMENTS Third Edition Douglas C. Montgomery ARIZONA STATE UNIVERSITY JOHN WILEY & SONS New York Chichester Brisbane Toronto Singapore Contents Chapter 1. Introduction 1-1 What

More information

Assignment 10 Design of Experiments (DOE)

Assignment 10 Design of Experiments (DOE) Instructions: Assignment 10 Design of Experiments (DOE) 1. Total No. of Questions: 25. Each question carries one point. 2. All questions are objective type. Only one answer is correct per numbered item.

More information

1 Mathematics and Statistics in Science

1 Mathematics and Statistics in Science 1 Mathematics and Statistics in Science Overview Science students encounter mathematics and statistics in three main areas: Understanding and using theory. Carrying out experiments and analysing results.

More information

Quantitative Analysis of Financial Markets. Summary of Part II. Key Concepts & Formulas. Christopher Ting. November 11, 2017

Quantitative Analysis of Financial Markets. Summary of Part II. Key Concepts & Formulas. Christopher Ting. November 11, 2017 Summary of Part II Key Concepts & Formulas Christopher Ting November 11, 2017 christopherting@smu.edu.sg http://www.mysmu.edu/faculty/christophert/ Christopher Ting 1 of 16 Why Regression Analysis? Understand

More information

Optimization of Muffler and Silencer

Optimization of Muffler and Silencer Chapter 5 Optimization of Muffler and Silencer In the earlier chapter though various numerical methods are presented, they are not meant to optimize the performance of muffler/silencer for space constraint

More information

Harris: Quantitative Chemical Analysis, Eight Edition CHAPTER 03: EXPERIMENTAL ERROR

Harris: Quantitative Chemical Analysis, Eight Edition CHAPTER 03: EXPERIMENTAL ERROR Harris: Quantitative Chemical Analysis, Eight Edition CHAPTER 03: EXPERIMENTAL ERROR Chapter 3. Experimental Error -There is error associated with every measurement. -There is no way to measure the true

More information

Method Validation. Role of Validation. Two levels. Flow of method validation. Method selection

Method Validation. Role of Validation. Two levels. Flow of method validation. Method selection Role of Validation Method Validation An overview Confirms the fitness for purpose of a particular analytical method. ISO definition: Conformation by examination and provision of objective evidence that

More information

SOME NEW THREE-LEVEL ORTHOGONAL MAIN EFFECTS PLANS ROBUST TO MODEL UNCERTAINTY

SOME NEW THREE-LEVEL ORTHOGONAL MAIN EFFECTS PLANS ROBUST TO MODEL UNCERTAINTY Statistica Sinica 14(2004), 1075-1084 SOME NEW THREE-LEVEL ORTHOGONAL MAIN EFFECTS PLANS ROBUST TO MODEL UNCERTAINTY Pi-Wen Tsai, Steven G. Gilmour and Roger Mead National Health Research Institutes, Queen

More information

CEM 333 Instrumental Analysis

CEM 333 Instrumental Analysis CEM 333 Instrumental Analysis Simon J. Garrett Room: CEM 234 Phone: 355 9715 ext 208 E-mail: garrett@cem.msu.edu Lectures: Tuesday, Thursday 9:00-9:50 am Room 136 Office Hours: Tuesdays 10:00-11:00 am

More information

LOOKING FOR RELATIONSHIPS

LOOKING FOR RELATIONSHIPS LOOKING FOR RELATIONSHIPS One of most common types of investigation we do is to look for relationships between variables. Variables may be nominal (categorical), for example looking at the effect of an

More information

Response Surface Methodology IV

Response Surface Methodology IV LECTURE 8 Response Surface Methodology IV 1. Bias and Variance If y x is the response of the system at the point x, or in short hand, y x = f (x), then we can write η x = E(y x ). This is the true, and

More information

Multidisciplinary System Design Optimization (MSDO)

Multidisciplinary System Design Optimization (MSDO) Multidisciplinary System Design Optimization (MSDO) Design Space Exploration Lecture 5 Karen Willcox 1 Today s Topics Design of Experiments Overview Full Factorial Design Parameter Study One at a Time

More information

The New MDL Procedure How To s. Presented by: Marcy Bolek - Alloway

The New MDL Procedure How To s. Presented by: Marcy Bolek - Alloway The New MDL Procedure How To s Presented by: Marcy Bolek - Alloway Proposed MDL Revision 2015 MUR How to obtain a copy of the proposed MDL revision? https://www.gpo.gov/fdsys/pkg/fr-2015-02-19/pdf/2015-02841.pdf

More information

Signal, Noise, and Detection Limits in Mass Spectrometry

Signal, Noise, and Detection Limits in Mass Spectrometry Signal, Noise, and Detection Limits in Mass Spectrometry Technical Note Chemical Analysis Group Authors Greg Wells, Harry Prest, and Charles William Russ IV, Agilent Technologies, Inc. 2850 Centerville

More information

Two-Level Designs to Estimate All Main Effects and Two-Factor Interactions

Two-Level Designs to Estimate All Main Effects and Two-Factor Interactions Technometrics ISSN: 0040-1706 (Print) 1537-2723 (Online) Journal homepage: http://www.tandfonline.com/loi/utch20 Two-Level Designs to Estimate All Main Effects and Two-Factor Interactions Pieter T. Eendebak

More information

DOE Wizard Screening Designs

DOE Wizard Screening Designs DOE Wizard Screening Designs Revised: 10/10/2017 Summary... 1 Example... 2 Design Creation... 3 Design Properties... 13 Saving the Design File... 16 Analyzing the Results... 17 Statistical Model... 18

More information

Data Analysis, Standard Error, and Confidence Limits E80 Spring 2015 Notes

Data Analysis, Standard Error, and Confidence Limits E80 Spring 2015 Notes Data Analysis Standard Error and Confidence Limits E80 Spring 05 otes We Believe in the Truth We frequently assume (believe) when making measurements of something (like the mass of a rocket motor) that

More information

Math 423/533: The Main Theoretical Topics

Math 423/533: The Main Theoretical Topics Math 423/533: The Main Theoretical Topics Notation sample size n, data index i number of predictors, p (p = 2 for simple linear regression) y i : response for individual i x i = (x i1,..., x ip ) (1 p)

More information

Stat 5303 (Oehlert): Models for Interaction 1

Stat 5303 (Oehlert): Models for Interaction 1 Stat 5303 (Oehlert): Models for Interaction 1 > names(emp08.10) Recall the amylase activity data from example 8.10 [1] "atemp" "gtemp" "variety" "amylase" > amylase.data

More information

Design of Screening Experiments with Partial Replication

Design of Screening Experiments with Partial Replication Design of Screening Experiments with Partial Replication David J. Edwards Department of Statistical Sciences & Operations Research Virginia Commonwealth University Robert D. Leonard Department of Information

More information

IE 361 Module 18. Reading: Section 2.5 Statistical Methods for Quality Assurance. ISU and Analytics Iowa LLC

IE 361 Module 18. Reading: Section 2.5 Statistical Methods for Quality Assurance. ISU and Analytics Iowa LLC IE 361 Module 18 Calibration Studies and Inference Based on Simple Linear Regression Reading: Section 2.5 Statistical Methods for Quality Assurance ISU and Analytics Iowa LLC (ISU and Analytics Iowa LLC)

More information

2 Analysis of Full Factorial Experiments

2 Analysis of Full Factorial Experiments 2 Analysis of Full Factorial Experiments This chapter details how to analyze 2 k factorial experiments and is organized as follows: Section 2.1. Analysis Strategy Overview Section 2.2. Analysis of Numerical

More information

Linear Regression Analysis for Survey Data. Professor Ron Fricker Naval Postgraduate School Monterey, California

Linear Regression Analysis for Survey Data. Professor Ron Fricker Naval Postgraduate School Monterey, California Linear Regression Analysis for Survey Data Professor Ron Fricker Naval Postgraduate School Monterey, California 1 Goals for this Lecture Linear regression How to think about it for Lickert scale dependent

More information

Mixture Designs Based On Hadamard Matrices

Mixture Designs Based On Hadamard Matrices Statistics and Applications {ISSN 2452-7395 (online)} Volume 16 Nos. 2, 2018 (New Series), pp 77-87 Mixture Designs Based On Hadamard Matrices Poonam Singh 1, Vandana Sarin 2 and Rashmi Goel 2 1 Department

More information

Data Analysis, Standard Error, and Confidence Limits E80 Spring 2012 Notes

Data Analysis, Standard Error, and Confidence Limits E80 Spring 2012 Notes Data Analysis Standard Error and Confidence Limits E80 Spring 0 otes We Believe in the Truth We frequently assume (believe) when making measurements of something (like the mass of a rocket motor) that

More information

The Theory of HPLC. Quantitative and Qualitative HPLC

The Theory of HPLC. Quantitative and Qualitative HPLC The Theory of HPLC Quantitative and Qualitative HPLC i Wherever you see this symbol, it is important to access the on-line course as there is interactive material that cannot be fully shown in this reference

More information

IE 361 EXAM #3 FALL 2013 Show your work: Partial credit can only be given for incorrect answers if there is enough information to clearly see what you were trying to do. There are two additional blank

More information

Data Analysis III. CU- Boulder CHEM-4181 Instrumental Analysis Laboratory. Prof. Jose-Luis Jimenez Spring 2007

Data Analysis III. CU- Boulder CHEM-4181 Instrumental Analysis Laboratory. Prof. Jose-Luis Jimenez Spring 2007 Data Analysis III CU- Boulder CHEM-48 Instrumental Analysis Laboratory Prof. Jose-Luis Jimenez Spring 007 Lecture will be posted on course web page based on lab manual, Skoog, web links 6 Linear Regression

More information

Performance characteristics of analytical tests

Performance characteristics of analytical tests Performance characteristics of analytical tests Jaap-Willem Hutter 31-3-2011 1 CONTENT Background Performance characteristics Bottlenecks Detection limits, definitions procedures in various countries Some

More information

Stat 5101 Lecture Notes

Stat 5101 Lecture Notes Stat 5101 Lecture Notes Charles J. Geyer Copyright 1998, 1999, 2000, 2001 by Charles J. Geyer May 7, 2001 ii Stat 5101 (Geyer) Course Notes Contents 1 Random Variables and Change of Variables 1 1.1 Random

More information

Simple Linear Regression for the Climate Data

Simple Linear Regression for the Climate Data Prediction Prediction Interval Temperature 0.2 0.0 0.2 0.4 0.6 0.8 320 340 360 380 CO 2 Simple Linear Regression for the Climate Data What do we do with the data? y i = Temperature of i th Year x i =CO

More information

Introduction to Design of Experiments

Introduction to Design of Experiments Introduction to Design of Experiments Jean-Marc Vincent and Arnaud Legrand Laboratory ID-IMAG MESCAL Project Universities of Grenoble {Jean-Marc.Vincent,Arnaud.Legrand}@imag.fr November 20, 2011 J.-M.

More information

Schedule. Draft Section of Lab Report Monday 6pm (Jan 27) Summary of Paper 2 Monday 2pm (Feb 3)

Schedule. Draft Section of Lab Report Monday 6pm (Jan 27) Summary of Paper 2 Monday 2pm (Feb 3) Schedule Assignment Due Date Draft Section of Lab Report Monday 6pm (Jan 27) Quiz for Lab 2 Peer Review of Draft Complete Lab Report 1 Tuesday 9:30am Wednesday 6pm Friday 6pm Summary of Paper 2 Monday

More information

Multiple Predictor Variables: ANOVA

Multiple Predictor Variables: ANOVA Multiple Predictor Variables: ANOVA 1/32 Linear Models with Many Predictors Multiple regression has many predictors BUT - so did 1-way ANOVA if treatments had 2 levels What if there are multiple treatment

More information

Objectives Simple linear regression. Statistical model for linear regression. Estimating the regression parameters

Objectives Simple linear regression. Statistical model for linear regression. Estimating the regression parameters Objectives 10.1 Simple linear regression Statistical model for linear regression Estimating the regression parameters Confidence interval for regression parameters Significance test for the slope Confidence

More information

Some Nonregular Designs From the Nordstrom and Robinson Code and Their Statistical Properties

Some Nonregular Designs From the Nordstrom and Robinson Code and Their Statistical Properties Some Nonregular Designs From the Nordstrom and Robinson Code and Their Statistical Properties HONGQUAN XU Department of Statistics, University of California, Los Angeles, CA 90095-1554, U.S.A. (hqxu@stat.ucla.edu)

More information

Investigating Models with Two or Three Categories

Investigating Models with Two or Three Categories Ronald H. Heck and Lynn N. Tabata 1 Investigating Models with Two or Three Categories For the past few weeks we have been working with discriminant analysis. Let s now see what the same sort of model might

More information

Instrumental methods of analysis

Instrumental methods of analysis Instrumental methods of analysis By Dr Hisham Ezzat Abdellatef Prof. of Analytical Chemistry Background: Analytical Chemistry: The Science of Chemical Measurements. Analyte: The compound or chemical species

More information

CS 5014: Research Methods in Computer Science

CS 5014: Research Methods in Computer Science Computer Science Clifford A. Shaffer Department of Computer Science Virginia Tech Blacksburg, Virginia Fall 2010 Copyright c 2010 by Clifford A. Shaffer Computer Science Fall 2010 1 / 254 Experimental

More information

TAGUCHI ANOVA ANALYSIS

TAGUCHI ANOVA ANALYSIS CHAPTER 10 TAGUCHI ANOVA ANALYSIS Studies by varying the fin Material, Size of Perforation and Heat Input using Taguchi ANOVA Analysis 10.1 Introduction The data used in this Taguchi analysis were obtained

More information

Process Robustness Studies

Process Robustness Studies Process Robustness Studies ST 435/535 Background When factors interact, the level of one can sometimes be chosen so that another has no effect on the response. If the second factor is controllable in a

More information

DEPARTMENT OF ENGINEERING MANAGEMENT. Two-level designs to estimate all main effects and two-factor interactions. Pieter T. Eendebak & Eric D.

DEPARTMENT OF ENGINEERING MANAGEMENT. Two-level designs to estimate all main effects and two-factor interactions. Pieter T. Eendebak & Eric D. DEPARTMENT OF ENGINEERING MANAGEMENT Two-level designs to estimate all main effects and two-factor interactions Pieter T. Eendebak & Eric D. Schoen UNIVERSITY OF ANTWERP Faculty of Applied Economics City

More information

" M A #M B. Standard deviation of the population (Greek lowercase letter sigma) σ 2

 M A #M B. Standard deviation of the population (Greek lowercase letter sigma) σ 2 Notation and Equations for Final Exam Symbol Definition X The variable we measure in a scientific study n The size of the sample N The size of the population M The mean of the sample µ The mean of the

More information

Review of Statistics 101

Review of Statistics 101 Review of Statistics 101 We review some important themes from the course 1. Introduction Statistics- Set of methods for collecting/analyzing data (the art and science of learning from data). Provides methods

More information

EPAs New MDL Procedure What it Means, Why it Works, and How to Comply

EPAs New MDL Procedure What it Means, Why it Works, and How to Comply EPAs New MDL Procedure What it Means, Why it Works, and How to Comply Richard Burrows TestAmerica Inc. 1 A Revision to the Method Detection Limit EPA published a revision to the 40 CFR Part 136 MDL procedure

More information

Battery Life. Factory

Battery Life. Factory Statistics 354 (Fall 2018) Analysis of Variance: Comparing Several Means Remark. These notes are from an elementary statistics class and introduce the Analysis of Variance technique for comparing several

More information

Linear Models 1. Isfahan University of Technology Fall Semester, 2014

Linear Models 1. Isfahan University of Technology Fall Semester, 2014 Linear Models 1 Isfahan University of Technology Fall Semester, 2014 References: [1] G. A. F., Seber and A. J. Lee (2003). Linear Regression Analysis (2nd ed.). Hoboken, NJ: Wiley. [2] A. C. Rencher and

More information

Chapter 5 EXPERIMENTAL DESIGN AND ANALYSIS

Chapter 5 EXPERIMENTAL DESIGN AND ANALYSIS Chapter 5 EXPERIMENTAL DESIGN AND ANALYSIS This chapter contains description of the Taguchi experimental design and analysis procedure with an introduction to Taguchi OA experimentation and the data analysis

More information

Rule of Thumb Think beyond simple ANOVA when a factor is time or dose think ANCOVA.

Rule of Thumb Think beyond simple ANOVA when a factor is time or dose think ANCOVA. May 003: Think beyond simple ANOVA when a factor is time or dose think ANCOVA. Case B: Factorial ANOVA (New Rule, 6.3). A few corrections have been inserted in blue. [At times I encounter information that

More information

LAB 5 INSTRUCTIONS LINEAR REGRESSION AND CORRELATION

LAB 5 INSTRUCTIONS LINEAR REGRESSION AND CORRELATION LAB 5 INSTRUCTIONS LINEAR REGRESSION AND CORRELATION In this lab you will learn how to use Excel to display the relationship between two quantitative variables, measure the strength and direction of the

More information

Chemometrics Unit 4 Response Surface Methodology

Chemometrics Unit 4 Response Surface Methodology Chemometrics Unit 4 Response Surface Methodology Chemometrics Unit 4. Response Surface Methodology In Unit 3 the first two phases of experimental design - definition and screening - were discussed. In

More information

Analysis of Variance and Co-variance. By Manza Ramesh

Analysis of Variance and Co-variance. By Manza Ramesh Analysis of Variance and Co-variance By Manza Ramesh Contents Analysis of Variance (ANOVA) What is ANOVA? The Basic Principle of ANOVA ANOVA Technique Setting up Analysis of Variance Table Short-cut Method

More information

How To: Analyze a Split-Plot Design Using STATGRAPHICS Centurion

How To: Analyze a Split-Plot Design Using STATGRAPHICS Centurion How To: Analyze a SplitPlot Design Using STATGRAPHICS Centurion by Dr. Neil W. Polhemus August 13, 2005 Introduction When performing an experiment involving several factors, it is best to randomize the

More information

Problems of Forensic Sciences, vol. XLIII, 2000, Received 9 September 1999; accepted 16 May 2000

Problems of Forensic Sciences, vol. XLIII, 2000, Received 9 September 1999; accepted 16 May 2000 COMPARISON OF AN ENZYMATIC ALCOHOL DEHYDROGENASE ASSAY AND ALCOHOL HEADSPACE GC-FID METHOD USING STATISTICAL ANALYSIS ON REAL FORENSIC BLOOD AND URINE SAMPLES Katrien M. ARYS, Jan F. VAN BOCXLAER, Willy

More information

Step 2: Select Analyze, Mixed Models, and Linear.

Step 2: Select Analyze, Mixed Models, and Linear. Example 1a. 20 employees were given a mood questionnaire on Monday, Wednesday and again on Friday. The data will be first be analyzed using a Covariance Pattern model. Step 1: Copy Example1.sav data file

More information

DOE module: Practice problem solutions

DOE module: Practice problem solutions DOE module: Practice problem solutions Part 1. 1) People with dysphagia can have difficulty swallowing liquids with too low a viscosity. To avoid this, thickening agents can be added to drinks to increase

More information

Cost optimisation by using DoE

Cost optimisation by using DoE Cost optimisation by using DoE The work of a paint formulator is strongly dependent of personal experience, since most properties cannot be predicted from mathematical equations The use of a Design of

More information

Statistical Analysis of Engineering Data The Bare Bones Edition. Precision, Bias, Accuracy, Measures of Precision, Propagation of Error

Statistical Analysis of Engineering Data The Bare Bones Edition. Precision, Bias, Accuracy, Measures of Precision, Propagation of Error Statistical Analysis of Engineering Data The Bare Bones Edition (I) Precision, Bias, Accuracy, Measures of Precision, Propagation of Error PRIOR TO DATA ACQUISITION ONE SHOULD CONSIDER: 1. The accuracy

More information

y ˆ i = ˆ " T u i ( i th fitted value or i th fit)

y ˆ i = ˆ  T u i ( i th fitted value or i th fit) 1 2 INFERENCE FOR MULTIPLE LINEAR REGRESSION Recall Terminology: p predictors x 1, x 2,, x p Some might be indicator variables for categorical variables) k-1 non-constant terms u 1, u 2,, u k-1 Each u

More information

Kumaun University Nainital

Kumaun University Nainital Kumaun University Nainital Department of Statistics B. Sc. Semester system course structure: 1. The course work shall be divided into six semesters with three papers in each semester. 2. Each paper in

More information