Lecture Notes on Analysis of variance

© All Rights Reserved

47 visualizações

Lecture Notes on Analysis of variance

© All Rights Reserved

- Factors Influencing the Growth of Hair Salon Enterprises in Kenya: A Surveyof Hair Salon Enterprises in Kisii Town
- 84520340 Factors Influencing the Gdp of India
- stat401ch15_01
- DOE Course Plan
- How much does industry matter really
- Application of Taguchi Method in the Optimization of Dissolution
- EC117 - HW
- How to Perform a MANOVA in SPSS
- Finance and Economic Growth nexus: Case of Zimbabwe
- IMPACT OF FII FLOW ON THE BSE SENSEX AND NIFTY
- 7-CapMar 6
- 1-s2.0-S0925527396001156-main
- 5965
- Taguchi 184 T565
- Minitab DOE Tutorial2015
- Accuracy and reproducibility of two manual periodontal probes. An in vitro study..pdf
- Leeflang.M. MSc
- Stat Result Taruc Malinis Hrm 2
- EViews Guide
- r and r

Você está na página 1de 12

Randall Miller

Definition 10.1

The response variable is the variable of interest to be measured in the experiment. We also refer

to the response as the dependent variable.

Definition 10.2

Factors are those variables whose effect on the response is of interest to the experimenter.

Quantitative factors are measured on a numerical scale, whereas qualitative factors are not

(naturally) measured on a numerical scale.

Definition 10.3

Factor levels are the values of the factor utilized in the experiment.

Definition 10.4

The treatments of an experiment are the factor-level combinations utilized.

Definition 10.5

An experimental unit is the object on which the response and factors are observed or measured.

Definition 10.6

A designed experiment is an experiment in which the analyst controls the specification of the

treatments and the method of assigning the experimental units to each treatment. An

observational experiment is an experiment in which the analyst simply observes the treatments

and the response on a sample of experimental units.

1|Page

Lecture Notes

Chapter Ten: Analysis of Variance

Randall Miller

Definition 10.7

The completely randomized design is a design in which treatments are randomly assigned to the

experimental units or in which independent random samples of experimental units are selected for

each treatment.

H 0 : 1= 2= ...= k

H a : At least two treatment means differ.

MST

MSE

Rejection region: F > F where F is based on=

1

Test statistic: F =

2

( k 1) numerator

degrees of freedom

1. The samples are randomly selected in an independent manner from the k treatment

populations. (This can be accomplished by randomly assigning the experimental units to the

treatments.)

2. All k sampled populations have distributions that are approximately normal.

3. The k population variances are equal (i.e., 12= 22= ...= k2 ).

Source

Treatments

df

k 1

SS

SST

Error

nk

SSE

Total

n 1

SS(Total)

MS

SST

k 1

SSE

MSE =

nk

MST

MSE

MST =

What Do You Do When the Assumptions are not Satisfied for the Analysis of

Variance for a Completely Randomized Design?

Answer: Use a nonparametric statistical method such as the Kruskal-Wallis H-test of section

14.5.

2|Page

Lecture Notes

Chapter Ten: Analysis of Variance

Randall Miller

1. Make sure that the design is truly completely randomized, with independent random samples

for each treatment.

2. Check the assumptions of normality and equal variances.

3. Create an ANOVA summary table that specifies the variabilitys attributable to treatments

and error, making sure that those variabilitys lead to the calculation of the F-statistic for

testing the null hypothesis that the treatment means are equal in the population. Use a

statistical software package to obtain the numerical results. If no such package is available,

use the calculation formulas in Appendix B.

4. If the F-test leads to the conclusion that the means differ,

a. Conduct a multiple-comparisons procedure for as many of the pairs of means as you

wish to compare. (See Section 10.3.) Use the results to summarize the statistically

significant differences among the treatment means.

b. If desired, from confidence intervals for one or more individual treatment means.

5. If the F-test leads to the nonrejection of the null hypothesis that the treatment means are

equal, consider the following possibilities;

a. The treatment means are equal; that is, the null hypothesis is true.

b. The treatment means really differ, but other important factors affecting the response

are not accounted for by the completely randomized design. These factors inflate the

sampling variability, as measured by MSE, resulting in smaller values of the Fstatistic. Either increase the sample size for each treatment, or use a different

experimental design (as in 10.4) that accounts for the other factors affecting the

response.

[Note: Be careful not to automatically conclude that the treatment means are equal since the

possibility of a Type II error must be considered if you accept H 0 .]

3|Page

Lecture Notes

Chapter Ten: Analysis of Variance

Randall Miller

CM = Correction for mean

n

yi

2

( Total of all observations )

i =1

=

=

Total number of observations

n

=

=

(Sum of squares of all observations

)

=

CM

y

i =1

2

i

CM

Sum of squares of treatments totals with

T2 T2

T2

= 1 + 2 + ... + k CM

nk

n1 n2

SSE = Sum of squares for error = SS(Total) SST

SST

MST = Mean square for treatments =

k 1

SSE

MSE = Mean square for error =

nk

MST

F = Test statistic =

MSE

Where

n = Total number of observations

k = Number of treatments

=

Ti Total

=

for treatment i ( i 1, 2,..., k )

4|Page

Lecture Notes

Chapter Ten: Analysis of Variance

Randall Miller

Determining the Number of Pairwise Comparisons of Treatment Means

In general, if there are k treatment means, there are

=

c k ( k 1) / 2

pairs of means that can be compared.

Method

Tukey

Bonferroni

Scheff

Equal

Equal or unequal

Equal or unequal

Types of comparisons

Pairwise

Pairwise

General contrasts

Definition 10.8

The randomized block design consists of a two-step procedure:

1. Matched sets of experimental units, called blocks, are formed, with each block consisting of k

experimental unites (where k is the number of treatments). The b blocks should consist of

experimental units that are as similar as possible.

2. One experimental unit from each block is randomly assigned to each treatment, resulting in a

total of n = bk responses.

H 0 : 1= 2= ...= k

H a : At least two treatment means differ.

MST

MSE

Rejection region: F > F where F is based on ( k 1) numerator degrees of freedom and

Test statistic: F =

Conditions Required for a Valid ANOVA F-Test: Randomized Block Design

1. The b blocks are randomly selected, and all k treatments are applied (in random order) to each

block.

2. The distributions of observations corresponding to all bk block-treatment combinations are

approximately normal.

3. The bk block-treatment distributions have equal variances.

5|Page

Lecture Notes

Chapter Ten: Analysis of Variance

Randall Miller

Source

Treatments

Blocks

Error

Total

df

k 1

b 1

n k b +1

n 1

SS

SST

SSB

SSE

SS(Total)

MS

MST

MSB

MSE

F

MST/MSE

1. Be sure that the design of blocks (preferably, blocks of homogeneous experimental units) and

that each treatment is randomly assigned to one experimental unit in each block.

2. If possible, check the assumptions of normality and equal variances for all block-treatment

combinations. [Note: This may be difficult to do, since the design will likely have only one

observation for each block-treatment combination.]

3. Create an ANOVA summary table that specifies the variability attributable to treatments,

blocks, and error, and that leafs to the calculation of the F-statistic to test the null hypothesis

that the treatment means are equal in the population. Use a statistical software package or the

calculation formulas in Appendix B to obtain the necessary numerical ingredients.

4. If the F-statistic leads to the conclusion that the means differ, employ the Bonferroni or

Tukey procedure, or a similar procedure, to conduct multiple comparisons of as many of the

pairs of means as you wish. Use the results to summarize the statistically significant

differences among the treatment means. Remember that, in general, the randomized block

design cannot be employed to form confidence intervals for individual treatment means.

5. If the F-test leads to the nonrejection of the null hypothesis that the treatment means are

equal, several possibilities exist:

a. The treatment means are equal: that is, the null hypothesis is true.

b. The treatment means really differ, but other important factors affecting the response

are not accounted for by the randomized block design. These factors inflate the

sampling variability, as measured by MSE, resulting in smaller values of the Fstatistic. Either increase the sample size for each treatment, or conduct an experiment

that accounts for the other factors affecting the response (as is to be done in Section

10.5). Do not automatically reach the former conclusion, since the possibility of a

Type II error must be considered if you accept H 0 .

6. If desired, conduct the F-test of the null hypothesis that the block means are equal. Rejection

of this hypothesis lends statistical support to the utilization of the randomized block design.

What Do You Do When the Assumptions Are Not Satisfied for the Analysis of

Variance for a Randomized Block Design?

Answer: Use a nonparametric statistical method such as the Friedman Fr test of Section 14.6.

6|Page

Lecture Notes

Chapter Ten: Analysis of Variance

Randall Miller

CM = Correction for mean

n

yi

2

( Total of all observations )

i =1

=

=

Total number of observations

n

=

=

(Sum of squares of all observations

)

=

CM

y

i =1

2

i

CM

Sum of squares of treatments totals with

2

2

2

T

T

T

= 1 + 2 + ... + k CM

b

b

b

SST = Sum of square for blocks

Sum of squares of block totals with

2

2

2

B

B

B

= 1 + 2 + ... + k CM

k

k

k

SST

MST = Mean square for treatments =

k 1

SSB

MSB = Mean square for blocks =

b 1

SSE

MSE = Mean square for error =

n k b +1

MST

F = Test statistic =

MSE

7|Page

Lecture Notes

Chapter Ten: Analysis of Variance

Randall Miller

Where

n = Total number of observations

b = Number of block

k = Number of treatments

=

Ti Total

=

for treatment i ( i 1, 2,..., k )

=

Bi Total

=

for block i ( i 1, 2,..., b )

5. Factorial Experiments

Definition 10.9

A complete factorial experiment is a factorial experiment in which every factor-level

combination is utilized. That is, the number of treatments in the experiment equals the total

number of factor-level combinations.

Factor A

At a levels

Level

1

2

3

1

Trt. 1

Trt. b + 1

Trt. 2b + 1

Factor B at b levels

2

3

Trt. 2

Trt. 3

Trt. b + 2

Trt. b + 3

Trt. 2b + 2

Trt. 2b + 3

Trt. (a-1)b + 1

Trt. (a-1)b + 2

Trt. (a-1)b + 3

B

Trt. b

Trt. 2b

Trt. 3b

Trt. ab

1. Partition the total sum of squares into the treatment and error components (stage 1 of Figure

10.21). Use either a statistical software package or the calculation formulas in Appendix C to

accomplish the partitioning.

2. Use the F-ratio of the mean square for treatments to the mean square for error to test the null

hypothesis that the treatment means are equal.

a. If the test results in nonrejection of the null hypothesis, consider refining the

experiment by increasing the number of replications or introducing other factors.

Also, consider the possibility that the response is unrelated to the two factors.

b. If the test results in rejection of the null hypothesis, then proceed to step 3.

3. Partition the treatment sum of squares into the main effect and the interaction sum of squares

(stage 2 of Figure 10.21). Use either a statistical software package or the calculation

formulas in Appendix B to accomplish the partitioning.

8|Page

Lecture Notes

Chapter Ten: Analysis of Variance

Randall Miller

4. Test the null hypothesis that factors A and B do not interact to affect the response by

comparing the F-ratio of the mean square for interaction to the mean square for error.

a. If the test results in nonrejection of the null hypothesis, proceed to step 5.

b. If the test results in rejection of the null hypothesis, conclude that the two factors

interact to affect the mean response. Then proceed to step 6a.

5. Conduct tests of two null hypotheses that the mean response is the same at each level of

factor A and factor B. Compute tow F-ratios by comparing the mean square for each factor

main effect with the mean square for error.

a.

6. Compare the mean;

a. If the test for interaction (step 4) is significant, use a multiple-comparison procedure

to compare any or all pairs of the treatment means.

b. If the test for one or both main effects (step 5) is significant, use a multiplecomparison procedure to compare the pairs of means corresponding to the levels of

the significant factor(s).

Replicates per Treatment

Test for Treatment Means

H 0 : No difference among the ab treatment means

MST

MSE

Rejection region: F F , based on ( ab 1) numerator and ( n ab ) denominator degrees of

Test statistic: F =

H 0 : Factors A and B do not interact to affect the response mean

H a : Factors A and B do interact to affect the response mean

Test statistic: F =

MS ( AB )

MSE

Rejection region: F F , based on ( a 1)( b 1) numerator and ( n ab ) denominator degrees of

freedom

9|Page

Lecture Notes

Chapter Ten: Analysis of Variance

Randall Miller

H 0 : No difference among the a mean levels of factor A

H a : At least two factor A mean levels differ

Test statistic: F =

MS ( A )

MSE

Rejection region: F F , based on ( a 1) numerator and ( n ab ) denominator degrees of freedom

H 0 : No difference among the b mean levels of factor B

Test statistic: F =

MS ( B )

MSE

Rejection region: F F , based on ( b 1) numerator and ( n ab ) denominator degrees of freedom

1. The response distribution for each factor-level combination (treatment) is normal.

2. The response variance is constant for all treatments.

3. Random and independent samples of experimental units are associated with each treatment.

Replicates, where Factor A has a Levels and Factor B has b Levels

Source

A

B

AB

Error

Total

df

a 1

b 1

( a 1)( b 1)

SS

SSA

SSB

SSAB

MS

MSA

MSB

MSAB

ab ( r 1)

n 1

SSE

MSE

F

MSA/MSE

MSB/MSE

MSAB/MSE

SS(Total)

10 | P a g e

Lecture Notes

Chapter Ten: Analysis of Variance

Randall Miller

CM = Correction for mean

n

yi

2

( Total of all observations )

i =1

=

=

Total number of observations

n

=

(Sum of squares of all observations

)

=

CM

y

i =1

2

i

CM

Sum of squares of the totals A1 , A2 ,..., Aa

A

i =1

2

i

br

CM

Sum of squares of the totals B1 , B2 ,..., Ba

B

i =1

2

i

ar

CM

Sum of squares of the cells totals

=

the number of measurements in

AB

=j 1 =i 1

2

ij

SS ( A ) SS ( B ) CM

11 | P a g e

Lecture Notes

Chapter Ten: Analysis of Variance

Randall Miller

Where

n = Total number of observations

a = Number of levels of factor A

b = Number of levels of factor B

r = Number of replicates ( observations per treatment )

Ai Total

for level i of factor A ( i 1, 2,..., a )

=

=

Bi = Total for level i of factor B ( i = 1, 2,..., b )

ABij = Total for treatment ( ij ) , i.e., for ith level of factor A and ith level of factor B

12 | P a g e

- Factors Influencing the Growth of Hair Salon Enterprises in Kenya: A Surveyof Hair Salon Enterprises in Kisii TownEnviado porInternational Organization of Scientific Research (IOSR)
- 84520340 Factors Influencing the Gdp of IndiaEnviado porVivek Agrawal
- stat401ch15_01Enviado pormelkyed
- DOE Course PlanEnviado porshaqrasta
- How much does industry matter reallyEnviado porOno Joksim
- Application of Taguchi Method in the Optimization of DissolutionEnviado porPasha Tan
- EC117 - HWEnviado porshangsyndrome
- How to Perform a MANOVA in SPSSEnviado poradurahul
- Finance and Economic Growth nexus: Case of ZimbabweEnviado porMoses Chunga
- IMPACT OF FII FLOW ON THE BSE SENSEX AND NIFTYEnviado porShuja Shabbir
- 7-CapMar 6Enviado porbemb1e
- 1-s2.0-S0925527396001156-mainEnviado porAmrik Singh
- 5965Enviado porWaqar Munir
- Taguchi 184 T565Enviado porOctavio Romero
- Minitab DOE Tutorial2015Enviado porpuddin245
- Accuracy and reproducibility of two manual periodontal probes. An in vitro study..pdfEnviado porDennis La Torre Zea
- Leeflang.M. MScEnviado porAnnisa 'anis' Dwi Pratiwi
- Stat Result Taruc Malinis Hrm 2Enviado porJaycee Tuala
- EViews GuideEnviado porAnisha Jaiswal
- r and rEnviado porBharat
- Biblio_1.pdfEnviado porIonut Tamas
- Repeated MeasuresEnviado porFarizAgyan
- Annova.pdfEnviado porRKJhalendra
- ANOvaEnviado porنور روسلن
- Univariate Analysis of Variance.docxEnviado porNurul Fauziyah
- art43Enviado porlylya_bejenaru
- Apa TablesEnviado porBlacky_87
- Cloud Gaming Virtual Community - A Case StudyEnviado porxolilev
- Design Of Experiments.pptxEnviado porTarak Gupta
- Book1Enviado pornguyenshy manh

- Random Process BookEnviado porvignanaraj
- ECE Regulation 2017 Full SyllabusEnviado porNandha Kumar
- Finite Diff Equation NotesEnviado porvignanaraj
- Question Bank on Z transforms.docxEnviado porvignanaraj
- Numerical Method for engineers-chapter 8Enviado porMrbudakbaek
- LECTURE Notes on Design of ExperimentsEnviado porvignanaraj
- LECTURE NOTES PROBABILITY DISTRIBUTIONS.docxEnviado porvignanaraj
- Lecture Notes on Design Of Experiments.docxEnviado porvignanaraj
- Numerical Methods for Electrical EngineersEnviado porvignanaraj
- TUTORIAL PROBLEMS IN NUMERICAL METHODSEnviado porvignanaraj
- Lecture Notes Finite DifferencesEnviado porvignanaraj
- Using R for Linear RegressionEnviado porMohar Sen
- Gaussian QuadEnviado porchikukotwal
- Numerical methods in CivilEnviado porvignanaraj
- Statistics Using R TutorialEnviado porvignanaraj
- Numerical Methods Question BankEnviado porvignanaraj
- Mechanical Engg 2014Enviado porvignanaraj
- Electromagnetic TheoryEnviado porRana Umar
- Tutorial Prob AnsEnviado porvignanaraj
- TPDE-QB.pdfEnviado porvignanaraj
- SR Profile July 2014Enviado porvignanaraj
- willettp4Enviado porvignanaraj
- Annotations for Symmetric Probabilistic Encryption Algorithm Based on Chaotic Attractors of Neural NetworksEnviado porvignanaraj
- 06-Fuzzy Set TheoryEnviado porCHANDRA BHUSHAN
- Computational Intelligence for Big Data Analytics - BDA 2013Enviado porvignanaraj
- Fourier Series Two Marks QuestionsEnviado porvignanaraj
- MA 2211 Unit 4Enviado porCSETUBE
- Saratha DeviEnviado porvignanaraj

- Sample Size and Power CalculationEnviado porRendy Adhitya Pratama
- Projective TestsEnviado porAlcaraz Paul Joshua
- Called for Document Verification List1Enviado porjigar00775
- Stat 491 Chapter 8--Hypothesis Testing--Two Sample InferenceEnviado porHarry Berry
- confidence intervalEnviado pormatrixnaz
- NDT NABLEnviado porPrabir Kumar
- ap statistics 2017-2018 term 3 assignment sohee hanEnviado porapi-369740044
- PSAT 2010Enviado porFletcherGuidance
- t-test TI-NSpire CalculatorEnviado porAnastasia
- What is Psychometrics.docxEnviado porjyoti_752940472
- Exercises WilcoxonEnviado porRohaila Rohani
- Question Paper CheckedEnviado porAbhishek Kumar Chambel
- Cat 2010 Analysis and Expected Cut OffEnviado porgajendra221
- 45_1Enviado pormahyar777
- Canivez - 2016 - Bifactor Modeling Chapter 12Enviado porLuis Anunciacao
- Research HypothesisEnviado porAndrra Tanase
- MOST WINNING A/B TEST RESULTS ARE ILLUSORYEnviado porcaaricaari
- Inferential StatisticsEnviado porxandercage
- ttestEnviado porMadhu Maddy
- Survey ResearchEnviado porahmeddawod
- Bangladeshi Data AnalysisEnviado porSaidur Rahman Milon
- Aquarius 12: People on stairs graduated upwardsEnviado porStarling
- Http NceesEnviado porSudhir Ravipudi
- Selection, Verification and Validation of Methods.pdfEnviado poraloediyah
- FileHandler.pdfEnviado porShalini
- lampiran 3Enviado porichel_muthz
- 102 Chapter 9 & 10 NotesEnviado portito asker
- collection books by Cronbach's alpha.pdfEnviado porMarjun Carreon Abear
- MCQs - IQ, Aptitude, CreativityEnviado porNazema_Sagi
- 1420_CQFINALMERITLIST201819MBBSBDSEnviado porNeepa

## Muito mais do que documentos

Descubra tudo o que o Scribd tem a oferecer, incluindo livros e audiolivros de grandes editoras.

Cancele quando quiser.