Copyright © 2013 Pearson Education, Inc. All rights reserved Chapter 10 Analysis of Variance Comparing More than Two Means.

Copyright © 2013 Pearson Education, Inc. All rights reserved

Chapter 10

Analysis of VarianceComparing More than Two

Means


10.1

Elements of a Design Study

10 - 3 Copyright © 2013 Pearson Education, Inc.. All rights reserved.

Definition


Definition


Definition


Definition


Definition


Definition


Figure 10.1 Sampling design: process and terminology


Figure 10.2 Two-factor golf study: Example 10.2


10.2

The Completely Randomized Design: Single Factor


Definition


Figure 10.3 MINITAB random assignments of consumers to brands


Table 10.1


Figure 10.4 MINITAB descriptive statistics for data in Table 10.1


Figure 10.5 Dot plot of SAT scores: difference between means dominated by sampling variability


Figure 10.6 Dot plot of SAT scores: difference between means large relative to sampling variability


Figure 10.7 MINITAB printout with ANOVA results for data in Table 10.1


Figure 10.8 Rejection region and calculated F-values for SAT score samples


Table 10.2


Figure 10.9 MINITAB descriptive statistics and ANOVA results for data in Table 10.2


Procedure


Definition


Table 10.3


Figure 10.10 F-test for completely randomized design: golf ball experiment


Figure 10.11 MINITAB ANOVA for completely randomized design


Table 10.4


Table 10.5


Figure 10.12 Partitioning of the total sum of squares for the completely randomized design


Figure 10.13 MINITAB histograms for golf ball driving distances


Figure 10.14 SAS box plots for golf ball distances


Procedure


Procedure


Figure SIA10.1 MINITAB one-way ANOVA for deviation from extract trail


10.3

Multiple Comparisons of Means


Procedure


Definition


Definition


Figure 10.15 SAS multiple-comparison printout for Example 10.6


Table 10.6


Figure 10.16 Summary of Tukey multiple comparisons


Figure 10.17 Alternative SAS multiple-comparison output for Example 10.6


Procedure


Figure SIA10.2 MINITAB Multiple Comparisons of Extract Trail Deviation Means


Table SIA10.1


10.4

The Randomized Block Design


Procedure


Table 10.7


Figure 10.18 Partitioning of the total sum of squares for the randomized block design


Figure 10.19 MINITAB printout with ANOVA results for the data in Table 10.7


Procedure


Definition


Figure 10.20 Illustration of completely randomized design and randomized block design: comparison of four golf ball brands


Table 10.8


Figure 10.21 SPSS printout for randomized block design ANOVA of data in Table 10.8


Table 10.9


Table 10.10


Figure 10.22 SPSS printout of Bonferroni confidence intervals for the randomized block design


Figure 10.23 Listing of brand means for randomized block design (Note: All differences are statistically significant


Table 10.11


Procedure


Procedure


10.5

Factorial Experiments: Two Factors


Definition


Table 10.12


Figure 10.24 Illustration of possible treatment effects: factorial experiment


Figure 10.25 Partitioning the total sum of squares for a two-factor factorial


Procedure

Continued on next slide


Procedure (cont’d)


Procedure


Procedure (cont’d)


Definition


Table 10.13


Figure 10.26 SAS printout for factorial ANOVA of golf data


Figure 10.27 SAS printout of Tukey rankings of golf ball brand means for each club


Figure 10.27 SAS printout of Tukey rankings of golf ball brand means for each club (cont’d)


Figure 10.28 SPSS means plot for factorial golf ball experiment


Table 10.14


Table 10.15


Table 10.16


Figure 10.29 SPSS printout of second factorial ANOVA


Figure 10.30 SPSS printout of Tukey rankings of brand means


Figure 10.31 Summary of Tukey Rankings of Brand Means


Figure 10.32 MINITAB means plot for second factorial golf ball experiment


Figure SIA10.3 Layout of experimental design for cockroach study


Figure SIA10.4 MINITAB two-way ANOVA for extract trail deviation


Figure SIA10.5 SAS Bonaferroni rankings of group means and trail means

Copyright © 2013 Pearson Education, Inc. All rights reserved Chapter 10 Analysis of Variance Comparing More than Two Means.

Documents