## Are you sure?

This action might not be possible to undo. Are you sure you want to continue?

Chapter 10

Design of Experiments and Analysis of Variance

10 - 1

Learning Objectives

© 2003 Pearson Prentice Hall

1. Describe Analysis of Variance (ANOVA) 2. Explain the Rationale of ANOVA 3. Compare Experimental Designs 4. Test the Equality of 2 or More Means

Completely Randomized Design Randomized Block Design Factorial Design

10 - 2

© 2003 Pearson Prentice Hall

Experiments

10 - 3

Experiment

© 2003 Pearson Prentice Hall

**1. Investigator Controls (Or Observes) One or More Independent Variables
**

Called Treatment Variables or Factors Contain Two or More Levels (Subcategories) Treatments are combinations of factor-levels for the factordifferent factors Response to Levels of Independent Variable

2. Observes Effect on Dependent Variable

**3. Experimental Design: Plan Used to Test Hypotheses
**

10 - 4

10 .Examples of Experiments © 2003 Pearson Prentice Hall 1. Variable). Two Hundred Consumers Are Randomly Assigned 1 of 3 (Levels) Brands of Juice (Independent Variable) to Study Reaction (Dependent Variable).5 . Variable). 2. Thirty Stores Are Randomly Assigned 1 of 4 (Levels) Store Displays (Independent Variable) to See the Effect on Sales (Dependent Variable).

5: Observational Or Designed? a.6 . Run ads in four national publications. Unemployment rate and production by state. Are they related? c. over past 10 years. Compare rainfall in four states over past 5 years. 10 .© 2003 Pearson Prentice Hall 10. track sales attributable to the ads f.

Identify a.9 © 2003 Pearson Prentice Hall High vs. Response Factor(s) and factor levels Treatments Experimental units 10 . new account vs. b.7 . c.Exercise 10. d. low tech. account maintenance Four samples of students Each confronted with one of four situations Each evaluates ethical behavior of sales person on 1-7 1scale.

© 2003 Pearson Prentice Hall Types of Regression Models Experimental Designs Completely Randomized Randomized Block Factorial One-Way Anova Two-Way Anova 10 .8 .

© 2003 Pearson Prentice Hall Completely Randomized Design 10 .9 .

10 .© 2003 Pearson Prentice Hall Types of Regression Models Experimental Designs Completely Randomized Randomized Block Factorial One-Way Anova Two-Way Anova 10 .

© 2003 Pearson Prentice Hall Completely Randomized Design 1. One Factor or Independent Variable 3. Analyzed by One-Way ANOVA One- 10 . Experimental Units (Subjects) Are Assigned Randomly to Treatments Subjects are Assumed Homogeneous 2 or More Treatment Levels or Classifications 2.11 .

28 hrs. . 29 hrs. 17 hrs.© 2003 Pearson Prentice Hall Randomized Design Example Factor (Training Method ) Level 1 Level 2 Level 3 Factor levels (Treatments) Experimental units Dependent variable (Response) 10 . 25 hrs. 31 hrs. 27 hrs. 20 hrs. 22 hrs.12 21 hrs.

© 2003 Pearson Prentice Hall OneOne-Way ANOVA F-Test F- 10 .13 .

14 .© 2003 Pearson Prentice Hall Types of Regression Models Experimental Designs Completely Randomized Randomized Block Factorial One-Way Anova Two-Way Anova 10 .

15 .OneOne-Way ANOVA F-Test F© 2003 Pearson Prentice Hall 1. Tests the Equality of 2 or More (p) (p Population Means 2. Used to Analyze Completely Randomized Experimental Designs 10 . Variables One Nominal Scaled Independent Variable 2 or More (p) Treatment Levels or Classifications (p One Interval or Ratio Scaled Dependent Variable 3.

Randomness & Independence of Errors Independent Random Samples are Drawn for each condition Populations (for each condition) are Normally Distributed Populations (for each condition) have Equal Variances 2.16 .© 2003 Pearson Prentice Hall OneOne-Way ANOVA F-Test FAssumptions 1. Homogeneity of Variance 10 . Normality 3.

Mean is Different Treatment Effect 238 Q1 { Q2 { ..17 . { Qp 10 ....© 2003 Pearson Prentice Hall OneOne-Way ANOVA F-Test FHypotheses H0: Q1 = Q2 = Q3 = . = Qp All Population Means are Equal No Treatment Effect Ha: Not All Qj Are Equal At Least 1 Pop.

= Qp All Population Means are Equal No Treatment Effect Ha: Not All Qj Are Equal Q1 = Q 2 = Q3 f(X) X At Least 1 Pop.... { Qp Q1 = Q2 Q3 X 10 . Mean is Different Treatment Effect 238 Q1 { Q2 { .© 2003 Pearson Prentice Hall OneOne-Way ANOVA F-Test FHypotheses f(X) H0: Q1 = Q2 = Q3 = .18 ..

19 .Why Variances? © 2003 Pearson Prentice Hall Observe one sample from each treatment group Their means may be slightly different How different is enough to conclude population means are different? Depends on variability within each population Higher variance in population higher variance in means Statistical tests are conducted by comparing variability between means to variability within each sample 10 .

© 2003 Pearson Prentice Hall Two Possible Experiment Outcomes Reject equality of means! Pop 1 Pop 2 Pop 3 Same treatment variation Different random variation A Pop 1 Pop 2 Pop 3 Pop 4 Pop 5 Pop 6 Pop 4 Pop 5 Pop 6 10 .20 Can¶t reject equality of means! .

© 2003 Pearson Prentice Hall Two More Possible Experiment Outcomes Same treatment variation Different treatment variation Different random variation Same random variation A Reject Pop 1 Pop 2 Pop 3 B Pop 1 Pop 2 Pop 3 Reject Pop 5 Pop 4 Pop 5 Pop 6 Pop 4 Pop 6 10 .21 Can¶t reject equality of means! .

If Treatment Variation Is Significantly Greater Than Random Variation then Means Are Not Equal 4. Comparison Basis Is Ratio of Variances 3.© 2003 Pearson Prentice Hall OneOne-Way ANOVA Basic Idea 1.22 . Variation Measures Are Obtained by µPartitioning¶ Total Variation 10 . Compares 2 Types of Variation to Test Equality of Means 2.

23 .© 2003 Pearson Prentice Hall OneOne-Way ANOVA Partitions Total Variation 10 .

© 2003 Pearson Prentice Hall OneOne-Way ANOVA Partitions Total Variation Total variation 10 .24 .

© 2003 Pearson Prentice Hall OneOne-Way ANOVA Partitions Total Variation Total variation Variation due to treatment 10 .25 .

© 2003 Pearson Prentice Hall OneOne-Way ANOVA Partitions Total Variation Total variation Variation due to treatment Variation due to random sampling 10 .26 .

27 Variation due to random sampling .© 2003 Pearson Prentice Hall OneOne-Way ANOVA Partitions Total Variation Total variation Variation due to treatment Sum of Squares Among Sum of Squares Between Sum of Squares Treatment Among Groups Variation 10 .

© 2003 Pearson Prentice Hall OneOne-Way ANOVA Partitions Total Variation Total variation Variation due to treatment Sum of Squares Among Sum of Squares Between Sum of Squares Treatment (SST) Among Groups Variation 10 .28 Variation due to random sampling Sum of Squares Within Sum of Squares Error (SSE) Within Groups Variation .

Total Variation © 2003 Pearson Prentice Hall SS .

Total ! .

X 11 X .

.X 21 X .

X DX Group 1 10 .X ij X 2 2 2 Response.29 Group 2 Group 3 .

n p X p X Response. X 2 2 2 DX3 DX DX1 Group 1 10 .Treatment Variation © 2003 Pearson Prentice Hall SST ! n1 X 1 X n2 X 2 X .30 DX2 Group 2 Group 3 .

X 2 2 2 DX3 DX1 Group 1 10 .Random (Error) Variation © 2003 Pearson Prentice Hall SSE ! X 11 X 1 X 21 X 1 . X pj X p Response.31 DX2 Group 2 Group 3 .

. i !1 j !1 n1 ni n1 ni .SS=SSE+SST SS ! § § X ij X .

! § §

X ij X i.

X i. X ..

i !1 j !1 n1 ni 2 n1 ni

?

A

2

! § §

X ij X i. § §

i !1 j !1 i !1 j !1 2 .X i.. X .

2 § § .

i !1 j !1 n1 ni .X ij X i.. X i. X .

But © 2003 Pearson Prentice Hall i !1 j !1 n1 .

§ § .

ni i !1 n1 j !1 n1 ni ! § . X .. X i.X ij X i.

X i. § .. X .

! § .X ij X i.

. .X i. X .

n X i. n X i. i !1 !0 10 .33 .

Thus. SS=SSE+SST © 2003 Pearson Prentice Hall SS ! § § i !1 j !1 n1 ni .

.

§ §. ij ij i.

2 2 !§§ i !1 j !1 n1 ni 2 § ni . 2 i !1 j !1 n1 i !1 n1 ni i. ..

i. i.34 . ! SSE SST 10 . ..

Test Statistic S / .© 2003 Pearson Prentice Hall OneOne-Way ANOVA F-Test FTest Statistic 1.

p 1 F = MST / MSE ! SS / .

35 . Degrees of Freedom R 1 = p -1 R2 = n . Groups.n p MST Is Mean Square for Treatment MSE Is Mean Square for Error 2. or Levels n = Total Sample Size 10 .p p = # Populations.

p) 10 .© 2003 Pearson Prentice Hall OneOne-Way ANOVA Summary Table Mean Square (Variance) F Source of Degrees Sum of Variation of Squares Freedom Treatment Error Total p-1 n-p n-1 SST SSE SS(Total) = SST+SSE MST = MST SST/(p .36 .1) MSE MSE = SSE/(n .

37 F ( v1 ..e.The F distribution © 2003 Pearson Prentice Hall Two parameters increasing either one decreases F-alpha (except Ffor v2<3) I. v2 ) E F . the distribution gets smushed to the left See Section 9.5 E 0 10 .

F = MST / MSE } 1. n p) Always One-Tail! One- © 1984-1994 T/Maker Co.38 .© 2003 Pearson Prentice Hall OneOne-Way ANOVA F-Test FCritical Value Reject H0 Do Not Reject H0 0 If means are equal. 1984- 10 . Only reject large F! E F Fa ( p1.

10 23. 0 As production manager.10 21. 0 & experienced workers.75 assign 15 similarly trained 23. 0 20. 0 23. is there a difference in mean filling times? 10 . At the .50 mean filling times.© 2003 Pearson Prentice Hall OneOne-Way ANOVA F-Test FExample Mach3 20.39 .75 20.20 19.31 21. Mach1 Mach2 you want to see if 3 filling 25.80 2 . 0 machines have different 2 .00 22. 5 per machine.05 level. to the machines.7 25. You 22.

05 Conclusion: There Is Evidence Pop.40 3.9211 ! 25.5820 .05 Test Statistic: F! MST MSE ! 23.OneOne-Way ANOVA F-Test FSolution © 2003 Pearson Prentice Hall H 0: Q 1 = Q 2 = Q 3 Ha: Not All Equal E = .05 R1 = 2 R2 = 12 Critical Value(s): E = .89 F . Means Are Different 0 10 .6 Decision: Reject at E = .

41 .2172 From Computer 10 .0532 15 .60 15 .9211 F Source of Degrees of Sum of Variation Freedom Squares Treatment (Machines) Error Total 3-1=2 47.© 2003 Pearson Prentice Hall Summary Table Solution Mean Square (Variance) 23.3 = 12 11.1640 7.1640 25.1 = 14 58.5820 .

© 2003 Pearson Prentice Hall Reminder: Assumptions for Equality of Means Test Independent random samples from each population All population probabilities are normally distributed All populations have equal variances (Test starts with assumption of equal means as well. but that may be rejected as a result of the test) 10 .42 .

Dev.701946 42 3 | 15.703249 47 ------------+ ------------+-----------------------------------Total | 24.878451 139 .214286 23. ------------+ ------------+-----------------------------------1 | 30.035438 50 2 | 26.057554 20.Exercise 10.12766 15.64 20.26 | Summary of value condition | Mean Std. Freq.

909707 Bartlett's test for equal variances: chi2(2) = 7.5396 138 435.26 Analysis of Variance Source SS df MS F Prob > F -----------------------------------------------------------------------Between groups 6109.395776 -----------------------------------------------------------------------Total 60155.7141 2 3054.0007 Within groups 54045.Exercise 10.8255 136 397.027 .1931 Prob>chi2 = 0.69 0.85705 7.

Is there a difference in mean learning times of 12 people using 4 different training methods (E =.05)? (E =.45 © 1984-1994 T/Maker Co. 10 .© 2003 Pearson Prentice Hall OneOne-Way ANOVA F-Test FThinking Challenge You¶re a trainer for Microsoft Corp. .05)? M1 M2 M3 M4 10 11 13 18 9 16 8 23 5 9 9 25 Use the following table.

© 2003 Pearson Prentice Hall Summary Table (Partially Completed) Mean Square (Variance) F Source of Degrees of Sum of Variation Freedom Squares Treatment (Methods) Error Total 348 80 10 .46 .

OneOne-Way ANOVA F-Test FSolution* © 2003 Pearson Prentice Hall H 0: Q 1 = Q 2 = Q 3 = Q 4 Ha: Not All Equal E = .6 Decision: Reject at E = .05 Conclusion: There Is Evidence Pop. Means Are Different 0 10 .05 Test Statistic: F! MST MSE ! 116 10 116 ! 11.47 4.07 F .05 R1 = 3 R2 = 8 Critical Value(s): E = .

© 2003 Pearson Prentice Hall Summary Table Solution* Mean Square (Variance) 116 10 F Source of Degrees of Sum of Variation Freedom Squares Treatment (Methods) Error Total 4-1=3 12 .1 = 11 348 80 428 11.6 10 .48 .4 = 8 12 .

9707 P > |t| = 0.21429 3.70195 18.65729 23. Err.03544 24.10999 33. 2 TwoTwo-sample t test with equal variances -----------------------------------------------------------------------------Group | Obs Mean Std.94599 36.61957 2.26: condition 1 vs.270253 21.7755 24.631963 13.12914 ---------+ ---------+-------------------------------------------------------------------diff | 4.9707 P < t = 0.833439 20.8329 Ha: diff > 0 t = 0. Std.3343 Ha: diff < 0 t = 0. Interval] ---------+ ---------+-------------------------------------------------------------------1 | 50 30. [95% Conf.559216 -4.1671 .425714 4.48339 -----------------------------------------------------------------------------Degrees of freedom: 90 Ho: mean(1) .9707 P > t = 0.10.64 2.mean(2) = diff = 0 Ha: diff != 0 t = 0.60033 ---------+ ---------+-------------------------------------------------------------------combined | 92 28.82824 33.33401 2 | 42 26. Dev.

[95% Conf.0051 . Std.47586 -----------------------------------------------------------------------------Degrees of freedom: 87 Ho: mean(2) .65729 23. Err.51701 19. 3 TwoTwo-sample t test with equal variances -----------------------------------------------------------------------------Group | Obs Mean Std.0102 Ha: diff < 0 t = 2. Interval] ---------+ ---------+-------------------------------------------------------------------2 | 42 26.70195 18.70325 10.10.mean(3) = diff = 0 Ha: diff != 0 t = 2.176533 20.60033 3 | 47 15.290554 15.220767 2.6267 P > |t| = 0.68495 ---------+ ---------+-------------------------------------------------------------------diff | 11.35955 2.12766 2.6267 P < t = 0.6267 P > t = 0.21429 3.73831 ---------+ ---------+-------------------------------------------------------------------combined | 89 20.53337 16.82824 33.03415 24. Dev.08663 4.26 condition 2 vs.697394 19.9949 Ha: diff > 0 t = 2.

© 2003 Pearson Prentice Hall Multiple Comparisons Problem P{At least one of p intervals fails to contain the true difference} = 1 ± P{All c intervals contain the true differences} = 1 ± (1-alpha)c > alpha (1If comparing many pairs. need greater confidence for any one of them than you would for rejecting equality of any one pair 10 .51 .

Post Hoc Procedure Done After Rejection of Equal Means in ANOVA 3. Tells Which Population Means Are Significantly Different Example: Q1 = Q2 { Q3 2. etc. Output From Many Statistical computer Programs± Programs± various versions (Tukey.© 2003 Pearson Prentice Hall Multiple Comparisons Procedure 1.52 . Bonferroni.) 10 .

26 Multiple Comparisons (Bonferroni) Row Mean-| Col Mean | 1 2 ---------+---------------------2 | | | 3 | | -15.42571 0.10.0866 0.5123 0.872 .001 -11.029 -4.

54 .© 2003 Pearson Prentice Hall Randomized Block Design 10 .

55 .© 2003 Pearson Prentice Hall Types of Regression Models Experimental Designs Completely Randomized Randomized Block Factorial One-Way Anova Two-Way Anova 10 .

56 . Experimental Units (Subjects) Are Assigned Randomly to Blocks Blocks are Assumed Homogeneous 2. One Blocking Factor 10 . One Factor or Independent Variable of Interest 2 or More Treatment Levels or Classifications 3.© 2003 Pearson Prentice Hall Randomized Block Design 1.

. . . Factor Levels: (Treatments) Experimental Units Block 1 Block 2 Block 3 . B.© 2003 Pearson Prentice Hall Randomized Block Design A. . . D Treatments are randomly assigned within blocks A C D B C D B A B A D C . C. . . . .57 D C A B . Block b 10 . . . . .

Randomized Block F-Test F© 2003 Pearson Prentice Hall 1. Tests the Equality of 2 or More (p) (p Population Means 2. Variables One Nominal Scaled Independent Variable 2 or More (p) Treatment Levels or Classifications (p One Nominal Scaled Blocking Variable One Interval or Ratio Scaled Dependent Variable 3. Used with Randomized Block Designs 10 .58 .

© 2003 Pearson Prentice Hall Randomized Block F-Test FAssumptions 1.59 . Homogeneity of Variance 10 . Normality Probability Distribution of each BlockBlockTreatment combination is Normal Probability Distributions of all BlockBlockTreatment combinations have Equal Variances 2.

{ Qp Is Wrong 10 ....© 2003 Pearson Prentice Hall Randomized Block F-Test FHypotheses H0: Q1 = Q2 = Q3 = ..60 . Mean is Different Treatment Effect Q1 { Q2 { . = Qp All Population Means are Equal No Treatment Effect Ha: Not All Qj Are Equal At Least 1 Pop.

61 . Mean is Different Treatment Effect Q1 { Q2 { ..© 2003 Pearson Prentice Hall Randomized Block F-Test FHypotheses f(X) H0: Q1 = Q2 = Q3 = ... = Qp All Population Means are Equal No Treatment Effect Ha: Not All Qj Are Equal Q1 = Q 2 = Q3 f(X) X At Least 1 Pop. { Qp Is Wrong Q1 = Q2 Q3 X 10 ..

The F Ratio for Randomized Block Designs SS=SSE+SSB+SST MST SST / .

p 1 ! F! MSE MSE / .

n 1 p 1 b 1 SST / .

p 1 ! MSE / .

n p b 1 .

Degrees of Freedom R 1 = p -1 R2 = n ± b ± p +1 p = # Treatments. b = # Blocks. n = Total Sample Size 10 .© 2003 Pearson Prentice Hall Randomized Block F-Test FTest Statistic 1.63 . Test Statistic F = MST / MSE MST Is Mean Square for Treatment MSE Is Mean Square for Error 2.

Only reject large F! E F Fa ( p1. 1984- 10 . n p) Always One-Tail! One- © 1984-1994 T/Maker Co.64 .© 2003 Pearson Prentice Hall Randomized Block F-Test FCritical Value Reject H0 Do Not Reject H0 0 If means are equal. F = MST / MSE } 1.

000 B: 38.000 C: 48. B.000 C: 52.000 D: 48.000 A: 44.000 B: 36.000 .000 C: 50.© 2003 Pearson Prentice Hall Randomized Block F-Test FExample You wish to determine which of four brands of tires has the longest tread life. and D) to a tire location on each of 5 cars.000 A: 39.000 Right Front Left Rear C: 58.000 D: 51. At the .000 B: 40.65 Left Front A: 42. C.000 D: 39.000 Right Rear D: 44.000 A: 39.05 level.000 D: 42.000 B: 38. is there a difference in mean tread life? Tire Location Block Car 1 Car 2 Car 3 Car 4 Car 5 10 .000 A: 41.000 C: 43.000 B: 35. You randomly assign one of each brand (A.

Randomized Block F-Test FSolution © 2003 Pearson Prentice Hall H 0: Q 1 = Q 2 = Q 3 = Q 4 Ha: Not All Equal E = .66 3.49 F .05 R1 = 3 R2 = 12 Critical Value(s): E = . Means Are Different 0 10 .05 Test Statistic: F = 11.9933 Decision: Reject at E = .05 Conclusion: There Is Evidence Pop.

10 .47 © 2003 Pearson Prentice Hall What is the purpose of blocking on weeks in this study? c.Exercise 10.67 . Are the mean number of walkers different among the prompting conditions? d. What assumptions are required for the analysis in c and d? a. Which pairwise means are significantly different? e.

© 2003 Pearson Prentice Hall Factorial Experiments 10 .68 .

69 .© 2003 Pearson Prentice Hall Types of Regression Models Experimental Designs Completely Randomized Randomized Block Factorial One-Way Anova Two-Way Anova 10 .

Experimental Units (Subjects) Are Assigned Randomly to Treatments Subjects are Assumed Homogeneous 2.70 . Analyzed by Two-Way ANOVA Two10 .Factorial Design © 2003 Pearson Prentice Hall 1. Two or More Factors or Independent Variables Each Has 2 or More Treatments (Levels) 3.

. 22 hr. 31 hr. (Motivation) Level 2 27 hr.71 29 hr. 25 hr.© 2003 Pearson Prentice Hall Factorial Design Example Factor 2 (Training Method) Factor Level 1 Level 2 Level 3 Levels Level 1 19 hr. Treatment Factor 1 (High) 11 hr. (Low) 10 . 17 hr. 20 hr. 49 hr. 30 hr. 31 hr.

© 2003 Pearson Prentice Hall Advantages of Factorial Designs 1.. Could Use Separate Completely Randomized Designs for Each Variable 2.g. Controls Confounding Effects by Putting Other Variables into Model 3. Saves Time & Effort e. Can Explore Interaction Between Variables 10 .72 .

73 .© 2003 Pearson Prentice Hall TwoTwo-Way ANOVA 10 .

74 .© 2003 Pearson Prentice Hall Types of Regression Models Experimental Designs Completely Randomized Randomized Block Factorial One-Way Anova Two-Way Anova 10 .

TwoTwo-Way ANOVA © 2003 Pearson Prentice Hall 1. Tests the Equality of 2 or More Population Means When Several Independent Variables Are Used 2. Used to Analyze Factorial Designs 10 .75 . Same Results as Separate One-Way OneANOVA on Each Variable But Interaction Can Be Tested 3.

Independence of Errors 10 .© 2003 Pearson Prentice Hall TwoTwo-Way ANOVA Assumptions 1.76 . Homogeneity of Variance 3. Normality Populations are Normally Distributed Populations have Equal Variances Independent Random Samples are Drawn 2.

. X121 ....77 Xijk Level i Factor A Level j Factor B . : : Xa21 .© 2003 Pearson Prentice Hall TwoTwo-Way ANOVA Data Table Factor B 2 .... Xa22 . X221 .... X222 .. X122 ... b X1b1 X1b2 X2b1 X2b2 : Xab1 Xab2 Observation k Factor A 1 X111 1 X112 X211 2 X212 : : Xa11 a Xa12 10 ..

78 . No Interaction of Factors A & B 10 . = Q. = Qa... = Q2. = Q.© 2003 Pearson Prentice Hall TwoTwo-Way ANOVA Null Hypotheses 1.2.1. =... =. No Difference in Means Due to Factor B 3. H0: ABij = 0 2.. No Difference in Means Due to Factor A H0: Q1...b. H0: Q.

79 Variation Due to Treatment B SSB Variation Due to Random Sampling SSE .© 2003 Pearson Prentice Hall TwoTwo-Way ANOVA Total Variation Partitioning Total Variation SS(Total) Variation Due to Treatment A SSA Variation Due to Interaction SS(AB) 10 .

© 2003 Pearson Prentice Hall TwoTwo-Way ANOVA Summary Table Mean Square MS(A) MS(B) F MS(A) MSE MS(B) MSE Source of Degrees of Sum of Variation Freedom Squares A (Row) B (Column) a-1 b-1 SS(A) SS(B) SS(AB) SSE SS(Total) AB (a-1)(b-1) (a-1)(b(Interaction) Error Total 10 .80 MS(AB) MS(AB) MSE MSE Same as Other Designs n .ab n-1 .

When Significant. Interpretation of Main Effects (A & B) Is Complicated 3. Occurs When Effects of One Factor Vary According to Levels of Other Factor 2.81 . Can Be Detected In Data Table. Pattern of Cell Means in One Row Differs From Another Row In Graph of Cell Means.Interaction © 2003 Pearson Prentice Hall 1. Lines Cross 10 .

B.82 B C A B C .Graphs of Interaction © 2003 Pearson Prentice Hall Effects of Motivation (High or Low) & Training Method (A. C) on Mean Learning Time Interaction No Interaction Average Response High Low Average Response High Low A 10 .

3 . .63 © 2003 Pearson Prentice Hall 8 Male Mini al Mo erate S stantial E tre e Male e ale e ale 1.Exercise 10.83 ¤ §¦ ¥ Mini al Mo erate S s tantial E tre e ¤ © ¨ ¤ £ ¢ ¡ . 2 .38 .1 . 2. 2 3 2 1 0 10 .3 .

84 . Tested the Equality of 2 or More Means Completely Randomized Design Factorial Design 10 . Explained the Rationale of ANOVA 3. Compared Experimental Designs 4. Described Analysis of Variance (ANOVA) 2.Conclusion © 2003 Pearson Prentice Hall 1.

.End of Chapter Any blank slides that follow are blank intentionally.

- AMPT-14_TOC
- SBE_11e Ch13b DOE and Analysis of Variance DOE ANOVA
- Probing and feeding characteristics of the greenhouse whitefly in association whit hotplant acceptance and whitefly strains.pdf
- An Analysis of the Extent of Implementation of Environmental Cost Management and Its Impact on Output of Oil and Gas Companies
- An Ova
- Analysis of Variance (ANOVA)
- After ANOVA
- 1-s2.0-S0531513105000762-main
- Artigo Anova e Glm
- 2014 Lab 5 (Topic 8)
- Anova & Reml Manual
- ANOVA Literature Review
- Cross Cultural Decision Making 5813150
- Powerpoint for Blogspot
- TF1589_C001
- Pg Sas Manual2014 Web
- Optimization of rapid prototyping parameters for production of flexible ABS object
- psyc300b researchpaper
- DSC2008 Exam 2014 Apr (With Answers)
- Yyzzzz Fluidization Characteristics of Moist Food Particles - 2006 - (Int Jour of Food Eng)
- 63
- Additional
- Introduction Final Report
- Chapter 8 Exercises - Lyman Ott Michael Longnecker an Introduc
- Research.docx
- Case 9 Uniform Uniforms
- General Information
- MAN_RM1
- 27Cross Cultural PLOS2014
- IBM SPSS Statistics 23 Step by - Darren George

Skip carousel

- Investigation of Shell & Tube Heat Exchanger Performance for Plastic Injection Molding Machine By Using RSM
- tmp6766.tmp
- tmp9941.tmp
- tmpA909.tmp
- tmp18AE.tmp
- A Review on Various Approach for Process Parameter Optimization of Burnishing Process and TAGUCHI Approach for Optimization
- UT Dallas Syllabus for hcs6313.501.07s taught by Herve Abdi (herve)
- Knowledge of female genital cutting among parents in south west Nigeria
- Experimental Investigation for Nitride Ceramic Cutting Insert for Material Removal Rate on High Chrome Steel
- tmp79C
- UT Dallas Syllabus for psy2317.002 06s taught by Nancy Juhn (njuhn)
- UT Dallas Syllabus for psy3392.001 06f taught by Betty-gene Edelman (bedelman)
- tmpF2E
- tmp24B.tmp
- UT Dallas Syllabus for psy2317.001 06s taught by Nancy Juhn (njuhn)
- UT Dallas Syllabus for psy2317.001.07s taught by Nancy Juhn (njuhn)
- tmpFDED.tmp
- UT Dallas Syllabus for psy2317.001.09f taught by Nancy Juhn (njuhn)
- UT Dallas Syllabus for psy2317.501.08f taught by Nancy Juhn (njuhn)
- UT Dallas Syllabus for psy2317.002.07f taught by Nancy Juhn (njuhn)
- UT Dallas Syllabus for psy2317.501.07s taught by Nancy Juhn (njuhn)
- UT Dallas Syllabus for psy2317.501.09f taught by Nancy Juhn (njuhn)
- Selection of optimal process parameters in machining Aerospace Material by Wire Electric Discharge machining process
- UT Dallas Syllabus for psy2317.001.07f taught by Nancy Juhn (njuhn)
- tmpAD7D
- tmpA69C
- Tmp 1160
- tmp8C8D
- tmpA899.tmp
- UT Dallas Syllabus for psy2317.501.08s taught by Nancy Juhn (njuhn)

Sign up to vote on this title

UsefulNot usefulClose Dialog## Are you sure?

This action might not be possible to undo. Are you sure you want to continue?

Close Dialog## This title now requires a credit

Use one of your book credits to continue reading from where you left off, or restart the preview.

Loading