SlideShare une entreprise Scribd logo
1  sur  34
Statistics and Design of Experiments:  Role in Research George A. Milliken, PhD Department of Statistics Kansas State University Manhattan, Kansas September 2000 Department of Statistics  Kansas State University
September 2000 Department of Statistics  Kansas State University Statistics:  A collection of procedures and processes to enable researchers in the unbiased pursuit of Knowledge Statistics is an important part of the Scientific Method State a Hypothesis Analyze the Data Design a Study and Collect Data Interpret the Results—Draw Conclusions
September 2000 Department of Statistics  Kansas State University State a Hypothesis:  The OBJECTIVE or OBJECTIVES of the Study A HYPOTHESIS OR SET OF HYPOTHESES should state exactly what you want to DO or LEARN or STUDY SHOULD ANSWER What are the factors to be studied and what relationships are to be investigated?  What is the experimental material? Etc.?
September 2000 Department of Statistics  Kansas State University The area of STATISTICS would not be needed if each time you measured an experimental unit you would obtain the same response or value BUT, THE RESPONSES ARE NOT THE SAME SINCE THERE IS VARIABILITY or NOISE IN THE SYSTEM STATISTICAL METHODS EXTRACT THE SIGNAL FROM THE NOISE TO PROVIDE INFORMATION One of the Statistician’s JOBS is to make sense from DATA in the presence of VARIABILITY or noise by using DATA ANALYSIS TOOLS
September 2000 Department of Statistics  Kansas State University DESIGN VS. ANALYSIS The PURPOSE OF DATA COLLECTION is to GAIN INFORMATION OR KNOWLEDGE!! Collecting Data does not guarantee that  information is obtained. INFORMATION  ≠ DATA At best: INFORMATION=DATA+ANALYSIS
September 2000 Department of Statistics  Kansas State University If data are collected such that they contain  NO information in the first place, then the analysis phase cannot find it!!! The best way to insure that appropriate information is contained in the collected data is to DESIGN (plan) and Carefully Control the DATA COLLECTION PROCESS The measured variables must relate to the stated OBJECTIVES of the study
September 2000 Department of Statistics  Kansas State University If you have a good design and process for data collection, it is quite often straight forward to construct an analysis that extracts all of the available information from the data The ROLE of a STATISTICIAN is to work with the REAEARCH TEAM (or researcher) from the START of the study
September 2000 Department of Statistics  Kansas State University A STATISTICIAN CAN HELP OBTAIN THE MAXIMUM AMOUNT INFORMATON FROM AVAILABLE RESOURCES The MOST IMPORTANT TIME for the statistician to become involved with a research study is in the very BEGINNING
September 2000 Department of Statistics  Kansas State University HOW??? HELP WITH THE DESIGN OF THE EXPERIMENT DETERMINE SAMPLE SIZE NEEDED DEVELOP PROCESS OF COLLECTING DATA DISCUSS VARIABLES TO BE MEASURED AND HOW THEY RELATE TO THE OBJECTIVES OF THE STUDY PROVIDE METHODS OF ANALYZING THE DATA HELP TRANSLATE STATISTICAL CONCLUSIONS INTO SUBJECT MATTER CONCLUSIONS
September 2000 Department of Statistics  Kansas State University THE CORE HELP FROM THE STATISTICIAN IS IN THE DESIGN OF THE EXPERIMENT Help with selecting conditions that relate to the objectives of the study Selecting the Experimental Units Deciding when REPLICATIONS exist Determining the ORDER in which the experiment is to be carried out THE DESIGN OF THE EXPERIMENT IS CRITICAL
September 2000 Department of Statistics  Kansas State University COMPONENTS OF DESIGNED EXPERIMENTS TREATMENT STRUCTURE: Factors or Populations or Treatments related to the objectives of the experiment: Brands of Product, Types of Uses of Product DESIGN STRUCTURE OR EXPERIMENTAL UNITS: Factors used in blocking the experimental units as well as characteristics of exp. Units Washing Machine, Person Using Machine, Products evaluated in Session by Taste Panelist
September 2000 Department of Statistics  Kansas State University Complete Designed Experiment Treatment Structure Design Structure RANDOMIZE  – randomization plan to assign Treatment of TS to Experimental Units in DS
September 2000 Department of Statistics  Kansas State University RANDOMIZATION IS THE INSURANCE POLICY AGAINST INTRODUCING BIAS INTO THE STUDY Selecting an appropriate Treatment Structure, necessary Design Structure, and  required Randomization Process provides the Statistician the information needed to construct an appropriate model  APPROPRIATE  MODEL = BEST ANALYSIS
September 2000 Department of Statistics  Kansas State University Key to the Design of the Experiment is the Concept of REPLICATION REPLICATON: The independent observation of a treatment An Experimental Unit Provides a Replication of the level of a Factor if the level is randomly assigned the the Experimental Unit and observed independently of the other Experimental Units Must make sure that Sub-samples are not considered to be Replications
September 2000 Department of Statistics  Kansas State University The Variability among Experimental Units treated independently alike provides the estimate of the variance (or Standard Error) to be used as the measuring stick for comparing the levels of treatments randomly assigned to those Experimental Units Between Sub-sample variance is generally much less than between Replication variance It is critical that the Replications are appropriately Identified Treatment Structure, Design Structure (with experimental units and replication) and Randomization describe the total Design
September 2000 Department of Statistics  Kansas State University ANALYZE THE DATA: Use the COMPLETED DESIGNED EXPERIMENT and the data type to construct an appropriate analysis Use Statistical Software – SAS, RS/1, JMP A software package you know will provide valid results
September 2000 Department of Statistics  Kansas State University The Statistician will provide the STATISTICAL interpretation of the results from the analyses – STATISTICAL ANALYSES CONCLUSIONS The Statistician will help the Researcher TRANSLATE the statistical analyses conclusions into subject matter conclusions Discuss how the statistical analyses provide results that relate to the STATED OBJECTIVES of the study.  The expected results should be written along with the objectives.  Results that are not expected should be looked at carefully
September 2000 Department of Statistics  Kansas State University Washing Machine Example: 4 brands or models --  one machine each 3 types of laundry – Whites, Wash/wear, Denim  3 persons to operate the Machines  For each person: Randomly assign the order of Brands For each Brand, randomly assign the order of Types
September 2000 Department of Statistics  Kansas State University Brand D Brand B Brand A Brand C Random Order of Brands for Person 1 White White White White W/W W/W W/W W/W Denim Denim Denim Denim Machine Random Order of Types within each Machine Re-Randomize for each Person
September 2000 Department of Statistics  Kansas State University Machines are Experimental Unit for Brands and Variance is computed by Person*Brand Persons are Blocks of Machines Compare BRANDS by using the variability among Machines Treated Alike
September 2000 Department of Statistics  Kansas State University The Machines within a Person are Blocks for Types – Three Loads per Machine The Loads within a machine are the Experimental Units for Type and Brand*Type Variability among Loads treated alike provides the measuring stick for comparing the levels of Type and Brand*Type This Design Involves Persons as Blocks and Two Sizes of Experimental Unit Machine and Load
September 2000 Department of Statistics  Kansas State University If you ignore that this design involves TWO sizes of Experimental Units and there are Two Error Terms, the resulting error term is a combination of these two error terms The combined error term is Too Large for making comparisons involving Type and Brand*Type – won’t find things that are there The Combined error term is Too Small for Making comparisons involving Brand – will declare things to be different when they are not Statistical Conclusions can be very misleading
September 2000 Department of Statistics  Kansas State University STATISTICIAN’S JOB – to figure out how the study is being ran and help identify the type of design that is being used which includes determining if more than one size of experimental unit is involved This is accomplished  BEST when the Statistician is involved at the Beginning of the Study
September 2000 Department of Statistics  Kansas State University SALSA TASTING EXPERIMENT NINE TYPES OR BRANDS OF SALSA A PERSON CAN TASTE ONLY THREE SALSAS DURING THE SESSION TWELVE PERSONS WILL BE USED IN THE STUDY
September 2000 Department of Statistics  Kansas State University ASSIGNMENT OF PRODUCTS TO PERSONS – with order Person Person Order 1  2  3   Order 1  2  3  1 C A B  7 F D E 2 H I G  8 A G D 3 E B H 9 C I F 4 G B F 10 D H C 5 I E A 11 F A H 6 C G E 12 B D I
September 2000 Department of Statistics  Kansas State University Each Product is Tasted 4 times – there are Four Replications of each product Since each person tastes only Three of the products, how do we compare the products? The Analysis obtains predicted values for each Product for each Person Want to compare the Products as if each Person had tasted all of the Products
September 2000 Department of Statistics  Kansas State University The Product Means of these Predicted Values are the “ADJUSTED MEANS” for each Product Called LEAST SQUARES MEANS by SAS ® The LSMEANS are the Predicted Means as if Each of the Persons has Tasted and evaluated all of the products
September 2000 Department of Statistics  Kansas State University Some times characteristics of experimental units are measured – to be used as possible covariates Study the effect of three types of Drugs on a persons heart rate Randomly Assign 12 persons to each of the Drugs  -- person is experimental unit Dose the person with the assigned drug and measure the heart rate after 15 minutes
September 2000 Department of Statistics  Kansas State University Persons do not have identical heart rates before being given the respective drug Measure the initial heart rate – heart rate before giving the drug We want to compare the Drugs as if all experimental units (persons) had the same initial heart rate
September 2000 Department of Statistics  Kansas State University Analysis of Covariance uses a regression model to obtain predicted after drug heart rate values as if all persons had initial heart rates of, say, 74 beats per minute The Drug Means of these predicted heart rates are used to compare the Drugs – These means of Predicted Values are called LSMEANS
September 2000 Department of Statistics  Kansas State University ,[object Object],[object Object],[object Object]
September 2000 Department of Statistics  Kansas State University Another Role of the Statistician is to provide appropriate models for the analysis of the data from a given study in order to take into account the Design Structure and covariates to provide estimates of the treatment effects as if all experimental units had observed all treatments or all experimental units had the same value of the covariate  -- provide appropriate LSMEANS
September 2000 Department of Statistics  Kansas State University ,[object Object],[object Object],[object Object],[object Object]
September 2000 Department of Statistics  Kansas State University THE   END THANK YOU FOR LISTENING

Contenu connexe

Tendances

Principles of design of experiments (doe)20 5-2014
Principles of  design of experiments (doe)20 5-2014Principles of  design of experiments (doe)20 5-2014
Principles of design of experiments (doe)20 5-2014
Awad Albalwi
 
factorial design.pptx
factorial design.pptxfactorial design.pptx
factorial design.pptx
SreeLatha98
 
design of experiments
design of experimentsdesign of experiments
design of experiments
sigma-tau
 

Tendances (20)

Sample and sample size
Sample and sample sizeSample and sample size
Sample and sample size
 
Design of experiments
Design of experiments Design of experiments
Design of experiments
 
Research Methodology (M. Pharm, IIIrd Sem.)_UNIT_IV_CPCSEA Guidelines for Lab...
Research Methodology (M. Pharm, IIIrd Sem.)_UNIT_IV_CPCSEA Guidelines for Lab...Research Methodology (M. Pharm, IIIrd Sem.)_UNIT_IV_CPCSEA Guidelines for Lab...
Research Methodology (M. Pharm, IIIrd Sem.)_UNIT_IV_CPCSEA Guidelines for Lab...
 
Cross over design, Placebo and blinding techniques
Cross over design, Placebo and blinding techniques Cross over design, Placebo and blinding techniques
Cross over design, Placebo and blinding techniques
 
T test
T testT test
T test
 
Principles of design of experiments (doe)20 5-2014
Principles of  design of experiments (doe)20 5-2014Principles of  design of experiments (doe)20 5-2014
Principles of design of experiments (doe)20 5-2014
 
Design of experiments-Box behnken design
Design of experiments-Box behnken designDesign of experiments-Box behnken design
Design of experiments-Box behnken design
 
Fractional factorial design tutorial
Fractional factorial design tutorialFractional factorial design tutorial
Fractional factorial design tutorial
 
Fractional Factorial Designs
Fractional Factorial DesignsFractional Factorial Designs
Fractional Factorial Designs
 
Biostatistics_Unit_II_Research Methodology & Biostatistics_M. Pharm (Pharmace...
Biostatistics_Unit_II_Research Methodology & Biostatistics_M. Pharm (Pharmace...Biostatistics_Unit_II_Research Methodology & Biostatistics_M. Pharm (Pharmace...
Biostatistics_Unit_II_Research Methodology & Biostatistics_M. Pharm (Pharmace...
 
factorial design.pptx
factorial design.pptxfactorial design.pptx
factorial design.pptx
 
Analysis of variance
Analysis of varianceAnalysis of variance
Analysis of variance
 
PPT on Sample Size, Importance of Sample Size,
PPT on Sample Size, Importance of Sample Size,PPT on Sample Size, Importance of Sample Size,
PPT on Sample Size, Importance of Sample Size,
 
(I) MEDICAL RESEARCH_ UNIT_III_RESEARCH METHODOLOGY & BIOSTATISTICS.pptx
(I) MEDICAL RESEARCH_ UNIT_III_RESEARCH METHODOLOGY & BIOSTATISTICS.pptx(I) MEDICAL RESEARCH_ UNIT_III_RESEARCH METHODOLOGY & BIOSTATISTICS.pptx
(I) MEDICAL RESEARCH_ UNIT_III_RESEARCH METHODOLOGY & BIOSTATISTICS.pptx
 
5 factorial design
5 factorial design5 factorial design
5 factorial design
 
introduction to design of experiments
introduction to design of experimentsintroduction to design of experiments
introduction to design of experiments
 
Wilcoxon Rank-Sum Test
Wilcoxon Rank-Sum TestWilcoxon Rank-Sum Test
Wilcoxon Rank-Sum Test
 
design of experiments
design of experimentsdesign of experiments
design of experiments
 
2^3 factorial design in SPSS
2^3 factorial design in SPSS2^3 factorial design in SPSS
2^3 factorial design in SPSS
 
Design of Experiments
Design of ExperimentsDesign of Experiments
Design of Experiments
 

En vedette

Optimal design of experiments
Optimal design of experimentsOptimal design of experiments
Optimal design of experiments
Michal Komorowski
 
Introduction to experimental design
Introduction to experimental designIntroduction to experimental design
Introduction to experimental design
relsayed
 
Solutions. Design and Analysis of Experiments. Montgomery
Solutions. Design and Analysis of Experiments. MontgomerySolutions. Design and Analysis of Experiments. Montgomery
Solutions. Design and Analysis of Experiments. Montgomery
Byron CZ
 

En vedette (20)

Applied Statistics And Doe Mayank
Applied Statistics And Doe MayankApplied Statistics And Doe Mayank
Applied Statistics And Doe Mayank
 
Statistics chapter1
Statistics chapter1Statistics chapter1
Statistics chapter1
 
Advanced statistical methods002
Advanced statistical methods002Advanced statistical methods002
Advanced statistical methods002
 
Optimal design of experiments
Optimal design of experimentsOptimal design of experiments
Optimal design of experiments
 
Introduction to experimental design
Introduction to experimental designIntroduction to experimental design
Introduction to experimental design
 
Basic Design of Experiments Using the Custom DOE Platform
Basic Design of Experiments Using the Custom DOE PlatformBasic Design of Experiments Using the Custom DOE Platform
Basic Design of Experiments Using the Custom DOE Platform
 
RESPONSE SURFACE METHODOLOGY OPTIMIZATION OF FACTORS AFFECTING THE CHARACTERI...
RESPONSE SURFACE METHODOLOGY OPTIMIZATION OF FACTORS AFFECTING THE CHARACTERI...RESPONSE SURFACE METHODOLOGY OPTIMIZATION OF FACTORS AFFECTING THE CHARACTERI...
RESPONSE SURFACE METHODOLOGY OPTIMIZATION OF FACTORS AFFECTING THE CHARACTERI...
 
Design of experiment methodology
Design of experiment methodologyDesign of experiment methodology
Design of experiment methodology
 
Doe Taguchi Basic Manual1
Doe Taguchi Basic Manual1Doe Taguchi Basic Manual1
Doe Taguchi Basic Manual1
 
How to use statistica for rsm study
How to use statistica for rsm studyHow to use statistica for rsm study
How to use statistica for rsm study
 
LeanUX: Online Design of Experiments
LeanUX: Online Design of ExperimentsLeanUX: Online Design of Experiments
LeanUX: Online Design of Experiments
 
Exploring Best Practises in Design of Experiments: A Data Driven Approach to ...
Exploring Best Practises in Design of Experiments: A Data Driven Approach to ...Exploring Best Practises in Design of Experiments: A Data Driven Approach to ...
Exploring Best Practises in Design of Experiments: A Data Driven Approach to ...
 
Response surface method
Response surface methodResponse surface method
Response surface method
 
Robust Design
Robust DesignRobust Design
Robust Design
 
Pharmaceutical Design of Experiments for Beginners
Pharmaceutical Design of Experiments for Beginners  Pharmaceutical Design of Experiments for Beginners
Pharmaceutical Design of Experiments for Beginners
 
Solutions. Design and Analysis of Experiments. Montgomery
Solutions. Design and Analysis of Experiments. MontgomerySolutions. Design and Analysis of Experiments. Montgomery
Solutions. Design and Analysis of Experiments. Montgomery
 
Introduction to Design of Experiments by Teck Nam Ang (University of Malaya)
Introduction to Design of Experiments by Teck Nam Ang (University of Malaya)Introduction to Design of Experiments by Teck Nam Ang (University of Malaya)
Introduction to Design of Experiments by Teck Nam Ang (University of Malaya)
 
Application of Design of Experiments (DOE) using Dr.Taguchi -Orthogonal Array...
Application of Design of Experiments (DOE) using Dr.Taguchi -Orthogonal Array...Application of Design of Experiments (DOE) using Dr.Taguchi -Orthogonal Array...
Application of Design of Experiments (DOE) using Dr.Taguchi -Orthogonal Array...
 
Quality by Design : Design of experiments
Quality by Design : Design of experimentsQuality by Design : Design of experiments
Quality by Design : Design of experiments
 
Optimization techniques
Optimization techniquesOptimization techniques
Optimization techniques
 

Similaire à Statistics And Design Of Experiments

Course Code EDU7702-8Course Start Date 02152016Sec.docx
Course Code EDU7702-8Course Start Date 02152016Sec.docxCourse Code EDU7702-8Course Start Date 02152016Sec.docx
Course Code EDU7702-8Course Start Date 02152016Sec.docx
vanesaburnand
 
Need a nonplagiarised paper and a form completed by 1006015 before.docx
Need a nonplagiarised paper and a form completed by 1006015 before.docxNeed a nonplagiarised paper and a form completed by 1006015 before.docx
Need a nonplagiarised paper and a form completed by 1006015 before.docx
lea6nklmattu
 
PR1 Module 5-Methodology-Ppt.ppt
PR1 Module 5-Methodology-Ppt.pptPR1 Module 5-Methodology-Ppt.ppt
PR1 Module 5-Methodology-Ppt.ppt
jeonalugon1
 

Similaire à Statistics And Design Of Experiments (20)

statistics.pdf
statistics.pdfstatistics.pdf
statistics.pdf
 
Meaning and Importance of Statistics
Meaning and Importance of StatisticsMeaning and Importance of Statistics
Meaning and Importance of Statistics
 
Quantitative Method
Quantitative MethodQuantitative Method
Quantitative Method
 
Texto estudiante etad01
Texto estudiante etad01Texto estudiante etad01
Texto estudiante etad01
 
How to write chapter three of your research project
How to write chapter three of your research projectHow to write chapter three of your research project
How to write chapter three of your research project
 
How to write chapter three of your research project
How to write chapter three of your research projectHow to write chapter three of your research project
How to write chapter three of your research project
 
Lesson 1-Key Concepts in Statistics, Essential Process, Data classification &...
Lesson 1-Key Concepts in Statistics, Essential Process, Data classification &...Lesson 1-Key Concepts in Statistics, Essential Process, Data classification &...
Lesson 1-Key Concepts in Statistics, Essential Process, Data classification &...
 
Research Method chapter 6.pptx
Research Method chapter 6.pptxResearch Method chapter 6.pptx
Research Method chapter 6.pptx
 
Lecture 1
Lecture 1Lecture 1
Lecture 1
 
Thiyagu statistics
Thiyagu   statisticsThiyagu   statistics
Thiyagu statistics
 
Week 1-2 -INTRODUCTION TO QUANTITATIVE RESEARCH.pptx
Week 1-2 -INTRODUCTION TO QUANTITATIVE RESEARCH.pptxWeek 1-2 -INTRODUCTION TO QUANTITATIVE RESEARCH.pptx
Week 1-2 -INTRODUCTION TO QUANTITATIVE RESEARCH.pptx
 
Basics stat ppt-types of data
Basics stat ppt-types of dataBasics stat ppt-types of data
Basics stat ppt-types of data
 
Lesson 5 chapter 3
Lesson 5   chapter 3Lesson 5   chapter 3
Lesson 5 chapter 3
 
Lesson 5 chapter 3
Lesson 5   chapter 3Lesson 5   chapter 3
Lesson 5 chapter 3
 
Basic-Statistics-in-Research-Design.pptx
Basic-Statistics-in-Research-Design.pptxBasic-Statistics-in-Research-Design.pptx
Basic-Statistics-in-Research-Design.pptx
 
Course Code EDU7702-8Course Start Date 02152016Sec.docx
Course Code EDU7702-8Course Start Date 02152016Sec.docxCourse Code EDU7702-8Course Start Date 02152016Sec.docx
Course Code EDU7702-8Course Start Date 02152016Sec.docx
 
Mm1
Mm1Mm1
Mm1
 
Stat 4325IS.pdf
Stat 4325IS.pdfStat 4325IS.pdf
Stat 4325IS.pdf
 
Need a nonplagiarised paper and a form completed by 1006015 before.docx
Need a nonplagiarised paper and a form completed by 1006015 before.docxNeed a nonplagiarised paper and a form completed by 1006015 before.docx
Need a nonplagiarised paper and a form completed by 1006015 before.docx
 
PR1 Module 5-Methodology-Ppt.ppt
PR1 Module 5-Methodology-Ppt.pptPR1 Module 5-Methodology-Ppt.ppt
PR1 Module 5-Methodology-Ppt.ppt
 

Plus de ANNA UNIVERSITY

Plus de ANNA UNIVERSITY (12)

OLD SEVEN TOOLS OF QUALTIY MANAGEMENT
OLD SEVEN TOOLS OF QUALTIY MANAGEMENTOLD SEVEN TOOLS OF QUALTIY MANAGEMENT
OLD SEVEN TOOLS OF QUALTIY MANAGEMENT
 
NEW SEVEN TOOLS OF QUALITY MANAGEMENT
NEW SEVEN TOOLS OF QUALITY MANAGEMENTNEW SEVEN TOOLS OF QUALITY MANAGEMENT
NEW SEVEN TOOLS OF QUALITY MANAGEMENT
 
FAILURE MODE EFFECT ANALYSIS
FAILURE MODE EFFECT ANALYSISFAILURE MODE EFFECT ANALYSIS
FAILURE MODE EFFECT ANALYSIS
 
Quality Initiatives Iso 9001 2000[1]
Quality Initiatives Iso 9001 2000[1]Quality Initiatives Iso 9001 2000[1]
Quality Initiatives Iso 9001 2000[1]
 
QUALITY FUNCTION DEPLOYMENT
QUALITY FUNCTION DEPLOYMENTQUALITY FUNCTION DEPLOYMENT
QUALITY FUNCTION DEPLOYMENT
 
New Seven Management Tools
New Seven Management ToolsNew Seven Management Tools
New Seven Management Tools
 
New seven management tools
New seven management toolsNew seven management tools
New seven management tools
 
QUALITY FUCTION DEPLOYMENT
QUALITY FUCTION DEPLOYMENTQUALITY FUCTION DEPLOYMENT
QUALITY FUCTION DEPLOYMENT
 
Tqm fmea
Tqm fmeaTqm fmea
Tqm fmea
 
Tqm new tools
Tqm new toolsTqm new tools
Tqm new tools
 
Tqm old tools
Tqm old toolsTqm old tools
Tqm old tools
 
Statistics and design_of_experiments
Statistics and design_of_experimentsStatistics and design_of_experiments
Statistics and design_of_experiments
 

Dernier

Making and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdfMaking and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdf
Chris Hunter
 
Seal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptxSeal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptx
negromaestrong
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdf
ciinovamais
 
Beyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactBeyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global Impact
PECB
 

Dernier (20)

ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.ICT role in 21st century education and it's challenges.
ICT role in 21st century education and it's challenges.
 
Key note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdfKey note speaker Neum_Admir Softic_ENG.pdf
Key note speaker Neum_Admir Softic_ENG.pdf
 
ICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptxICT Role in 21st Century Education & its Challenges.pptx
ICT Role in 21st Century Education & its Challenges.pptx
 
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
Presentation by Andreas Schleicher Tackling the School Absenteeism Crisis 30 ...
 
Making and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdfMaking and Justifying Mathematical Decisions.pdf
Making and Justifying Mathematical Decisions.pdf
 
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
2024-NATIONAL-LEARNING-CAMP-AND-OTHER.pptx
 
microwave assisted reaction. General introduction
microwave assisted reaction. General introductionmicrowave assisted reaction. General introduction
microwave assisted reaction. General introduction
 
Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17Advanced Views - Calendar View in Odoo 17
Advanced Views - Calendar View in Odoo 17
 
Introduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The BasicsIntroduction to Nonprofit Accounting: The Basics
Introduction to Nonprofit Accounting: The Basics
 
Basic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptxBasic Civil Engineering first year Notes- Chapter 4 Building.pptx
Basic Civil Engineering first year Notes- Chapter 4 Building.pptx
 
Sociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning ExhibitSociology 101 Demonstration of Learning Exhibit
Sociology 101 Demonstration of Learning Exhibit
 
Seal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptxSeal of Good Local Governance (SGLG) 2024Final.pptx
Seal of Good Local Governance (SGLG) 2024Final.pptx
 
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...
TỔNG ÔN TẬP THI VÀO LỚP 10 MÔN TIẾNG ANH NĂM HỌC 2023 - 2024 CÓ ĐÁP ÁN (NGỮ Â...
 
Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...
Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...
Ecological Succession. ( ECOSYSTEM, B. Pharmacy, 1st Year, Sem-II, Environmen...
 
Activity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdfActivity 01 - Artificial Culture (1).pdf
Activity 01 - Artificial Culture (1).pdf
 
Unit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptxUnit-IV- Pharma. Marketing Channels.pptx
Unit-IV- Pharma. Marketing Channels.pptx
 
Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104Nutritional Needs Presentation - HLTH 104
Nutritional Needs Presentation - HLTH 104
 
Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024Mehran University Newsletter Vol-X, Issue-I, 2024
Mehran University Newsletter Vol-X, Issue-I, 2024
 
INDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptx
INDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptxINDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptx
INDIA QUIZ 2024 RLAC DELHI UNIVERSITY.pptx
 
Beyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global ImpactBeyond the EU: DORA and NIS 2 Directive's Global Impact
Beyond the EU: DORA and NIS 2 Directive's Global Impact
 

Statistics And Design Of Experiments

  • 1. Statistics and Design of Experiments: Role in Research George A. Milliken, PhD Department of Statistics Kansas State University Manhattan, Kansas September 2000 Department of Statistics Kansas State University
  • 2. September 2000 Department of Statistics Kansas State University Statistics: A collection of procedures and processes to enable researchers in the unbiased pursuit of Knowledge Statistics is an important part of the Scientific Method State a Hypothesis Analyze the Data Design a Study and Collect Data Interpret the Results—Draw Conclusions
  • 3. September 2000 Department of Statistics Kansas State University State a Hypothesis: The OBJECTIVE or OBJECTIVES of the Study A HYPOTHESIS OR SET OF HYPOTHESES should state exactly what you want to DO or LEARN or STUDY SHOULD ANSWER What are the factors to be studied and what relationships are to be investigated? What is the experimental material? Etc.?
  • 4. September 2000 Department of Statistics Kansas State University The area of STATISTICS would not be needed if each time you measured an experimental unit you would obtain the same response or value BUT, THE RESPONSES ARE NOT THE SAME SINCE THERE IS VARIABILITY or NOISE IN THE SYSTEM STATISTICAL METHODS EXTRACT THE SIGNAL FROM THE NOISE TO PROVIDE INFORMATION One of the Statistician’s JOBS is to make sense from DATA in the presence of VARIABILITY or noise by using DATA ANALYSIS TOOLS
  • 5. September 2000 Department of Statistics Kansas State University DESIGN VS. ANALYSIS The PURPOSE OF DATA COLLECTION is to GAIN INFORMATION OR KNOWLEDGE!! Collecting Data does not guarantee that information is obtained. INFORMATION ≠ DATA At best: INFORMATION=DATA+ANALYSIS
  • 6. September 2000 Department of Statistics Kansas State University If data are collected such that they contain NO information in the first place, then the analysis phase cannot find it!!! The best way to insure that appropriate information is contained in the collected data is to DESIGN (plan) and Carefully Control the DATA COLLECTION PROCESS The measured variables must relate to the stated OBJECTIVES of the study
  • 7. September 2000 Department of Statistics Kansas State University If you have a good design and process for data collection, it is quite often straight forward to construct an analysis that extracts all of the available information from the data The ROLE of a STATISTICIAN is to work with the REAEARCH TEAM (or researcher) from the START of the study
  • 8. September 2000 Department of Statistics Kansas State University A STATISTICIAN CAN HELP OBTAIN THE MAXIMUM AMOUNT INFORMATON FROM AVAILABLE RESOURCES The MOST IMPORTANT TIME for the statistician to become involved with a research study is in the very BEGINNING
  • 9. September 2000 Department of Statistics Kansas State University HOW??? HELP WITH THE DESIGN OF THE EXPERIMENT DETERMINE SAMPLE SIZE NEEDED DEVELOP PROCESS OF COLLECTING DATA DISCUSS VARIABLES TO BE MEASURED AND HOW THEY RELATE TO THE OBJECTIVES OF THE STUDY PROVIDE METHODS OF ANALYZING THE DATA HELP TRANSLATE STATISTICAL CONCLUSIONS INTO SUBJECT MATTER CONCLUSIONS
  • 10. September 2000 Department of Statistics Kansas State University THE CORE HELP FROM THE STATISTICIAN IS IN THE DESIGN OF THE EXPERIMENT Help with selecting conditions that relate to the objectives of the study Selecting the Experimental Units Deciding when REPLICATIONS exist Determining the ORDER in which the experiment is to be carried out THE DESIGN OF THE EXPERIMENT IS CRITICAL
  • 11. September 2000 Department of Statistics Kansas State University COMPONENTS OF DESIGNED EXPERIMENTS TREATMENT STRUCTURE: Factors or Populations or Treatments related to the objectives of the experiment: Brands of Product, Types of Uses of Product DESIGN STRUCTURE OR EXPERIMENTAL UNITS: Factors used in blocking the experimental units as well as characteristics of exp. Units Washing Machine, Person Using Machine, Products evaluated in Session by Taste Panelist
  • 12. September 2000 Department of Statistics Kansas State University Complete Designed Experiment Treatment Structure Design Structure RANDOMIZE – randomization plan to assign Treatment of TS to Experimental Units in DS
  • 13. September 2000 Department of Statistics Kansas State University RANDOMIZATION IS THE INSURANCE POLICY AGAINST INTRODUCING BIAS INTO THE STUDY Selecting an appropriate Treatment Structure, necessary Design Structure, and required Randomization Process provides the Statistician the information needed to construct an appropriate model APPROPRIATE MODEL = BEST ANALYSIS
  • 14. September 2000 Department of Statistics Kansas State University Key to the Design of the Experiment is the Concept of REPLICATION REPLICATON: The independent observation of a treatment An Experimental Unit Provides a Replication of the level of a Factor if the level is randomly assigned the the Experimental Unit and observed independently of the other Experimental Units Must make sure that Sub-samples are not considered to be Replications
  • 15. September 2000 Department of Statistics Kansas State University The Variability among Experimental Units treated independently alike provides the estimate of the variance (or Standard Error) to be used as the measuring stick for comparing the levels of treatments randomly assigned to those Experimental Units Between Sub-sample variance is generally much less than between Replication variance It is critical that the Replications are appropriately Identified Treatment Structure, Design Structure (with experimental units and replication) and Randomization describe the total Design
  • 16. September 2000 Department of Statistics Kansas State University ANALYZE THE DATA: Use the COMPLETED DESIGNED EXPERIMENT and the data type to construct an appropriate analysis Use Statistical Software – SAS, RS/1, JMP A software package you know will provide valid results
  • 17. September 2000 Department of Statistics Kansas State University The Statistician will provide the STATISTICAL interpretation of the results from the analyses – STATISTICAL ANALYSES CONCLUSIONS The Statistician will help the Researcher TRANSLATE the statistical analyses conclusions into subject matter conclusions Discuss how the statistical analyses provide results that relate to the STATED OBJECTIVES of the study. The expected results should be written along with the objectives. Results that are not expected should be looked at carefully
  • 18. September 2000 Department of Statistics Kansas State University Washing Machine Example: 4 brands or models -- one machine each 3 types of laundry – Whites, Wash/wear, Denim 3 persons to operate the Machines For each person: Randomly assign the order of Brands For each Brand, randomly assign the order of Types
  • 19. September 2000 Department of Statistics Kansas State University Brand D Brand B Brand A Brand C Random Order of Brands for Person 1 White White White White W/W W/W W/W W/W Denim Denim Denim Denim Machine Random Order of Types within each Machine Re-Randomize for each Person
  • 20. September 2000 Department of Statistics Kansas State University Machines are Experimental Unit for Brands and Variance is computed by Person*Brand Persons are Blocks of Machines Compare BRANDS by using the variability among Machines Treated Alike
  • 21. September 2000 Department of Statistics Kansas State University The Machines within a Person are Blocks for Types – Three Loads per Machine The Loads within a machine are the Experimental Units for Type and Brand*Type Variability among Loads treated alike provides the measuring stick for comparing the levels of Type and Brand*Type This Design Involves Persons as Blocks and Two Sizes of Experimental Unit Machine and Load
  • 22. September 2000 Department of Statistics Kansas State University If you ignore that this design involves TWO sizes of Experimental Units and there are Two Error Terms, the resulting error term is a combination of these two error terms The combined error term is Too Large for making comparisons involving Type and Brand*Type – won’t find things that are there The Combined error term is Too Small for Making comparisons involving Brand – will declare things to be different when they are not Statistical Conclusions can be very misleading
  • 23. September 2000 Department of Statistics Kansas State University STATISTICIAN’S JOB – to figure out how the study is being ran and help identify the type of design that is being used which includes determining if more than one size of experimental unit is involved This is accomplished BEST when the Statistician is involved at the Beginning of the Study
  • 24. September 2000 Department of Statistics Kansas State University SALSA TASTING EXPERIMENT NINE TYPES OR BRANDS OF SALSA A PERSON CAN TASTE ONLY THREE SALSAS DURING THE SESSION TWELVE PERSONS WILL BE USED IN THE STUDY
  • 25. September 2000 Department of Statistics Kansas State University ASSIGNMENT OF PRODUCTS TO PERSONS – with order Person Person Order 1 2 3 Order 1 2 3 1 C A B 7 F D E 2 H I G 8 A G D 3 E B H 9 C I F 4 G B F 10 D H C 5 I E A 11 F A H 6 C G E 12 B D I
  • 26. September 2000 Department of Statistics Kansas State University Each Product is Tasted 4 times – there are Four Replications of each product Since each person tastes only Three of the products, how do we compare the products? The Analysis obtains predicted values for each Product for each Person Want to compare the Products as if each Person had tasted all of the Products
  • 27. September 2000 Department of Statistics Kansas State University The Product Means of these Predicted Values are the “ADJUSTED MEANS” for each Product Called LEAST SQUARES MEANS by SAS ® The LSMEANS are the Predicted Means as if Each of the Persons has Tasted and evaluated all of the products
  • 28. September 2000 Department of Statistics Kansas State University Some times characteristics of experimental units are measured – to be used as possible covariates Study the effect of three types of Drugs on a persons heart rate Randomly Assign 12 persons to each of the Drugs -- person is experimental unit Dose the person with the assigned drug and measure the heart rate after 15 minutes
  • 29. September 2000 Department of Statistics Kansas State University Persons do not have identical heart rates before being given the respective drug Measure the initial heart rate – heart rate before giving the drug We want to compare the Drugs as if all experimental units (persons) had the same initial heart rate
  • 30. September 2000 Department of Statistics Kansas State University Analysis of Covariance uses a regression model to obtain predicted after drug heart rate values as if all persons had initial heart rates of, say, 74 beats per minute The Drug Means of these predicted heart rates are used to compare the Drugs – These means of Predicted Values are called LSMEANS
  • 31.
  • 32. September 2000 Department of Statistics Kansas State University Another Role of the Statistician is to provide appropriate models for the analysis of the data from a given study in order to take into account the Design Structure and covariates to provide estimates of the treatment effects as if all experimental units had observed all treatments or all experimental units had the same value of the covariate -- provide appropriate LSMEANS
  • 33.
  • 34. September 2000 Department of Statistics Kansas State University THE END THANK YOU FOR LISTENING