Muutke küpsiste eelistusi

Design and Analysis of Experiments: Classical and Regression Approaches with SAS [Kõva köide]

4.00/5 (4 hinnangut Goodreads-ist)
  • Formaat: Hardback, 856 pages, kõrgus x laius: 234x156 mm, kaal: 1292 g
  • Ilmumisaeg: 29-Jul-2008
  • Kirjastus: Chapman & Hall/CRC
  • ISBN-10: 1420060546
  • ISBN-13: 9781420060546
Teised raamatud teemal:
Design and Analysis of Experiments: Classical and Regression Approaches with SASSuurem pilt
  • Formaat: Hardback, 856 pages, kõrgus x laius: 234x156 mm, kaal: 1292 g
  • Ilmumisaeg: 29-Jul-2008
  • Kirjastus: Chapman & Hall/CRC
  • ISBN-10: 1420060546
  • ISBN-13: 9781420060546
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9781420060546.html
Märksõnad:
Unlike other books on the modeling and analysis of experimental data, Design and Analysis of Experiments: Classical and Regression Approaches with SAS not only covers classical experimental design theory, it also explores regression approaches. Capitalizing on the availability of cutting-edge software, the author uses both manual methods and SAS programs to carry out analyses.

The book presents most of the different designs covered in a typical experimental design course. It discusses the requirements for good experimentation, the completely randomized design, the use of orthogonal contrast to test hypotheses, and the model adequacy check. With an emphasis on two-factor factorial experiments, the author analyzes repeated measures as well as fixed, random, and mixed effects models. He also describes designs with randomization restrictions, before delving into the special cases of the 2k and 3k factorial designs, including fractional replication and confounding. In addition, the book covers response surfaces, balanced incomplete block and hierarchical designs, ANOVA, ANCOVA, and MANOVA.

Fortifying the theory and computations with practical exercises and supplemental material, this distinctive text provides a modern, comprehensive treatment of experimental design and analysis.
Preface xxi
Acknowledgments xxv
Author xxvii
Introductory Statistical Inference and Regression Analysis
1(74)
Elementary Statistical Inference
1(32)
Unbiased and Efficient Estimators
2(2)
Point and Interval Estimation
4(1)
Confidence Intervals for Parameters of a Populations
4(1)
Confidence Intervals for the Means
5(2)
Confidence Intervals for Differences between Two Means
7(3)
Confidence Intervals for Proportions
10(1)
Confidence Interval for Difference between two Proportions
10(2)
Tests of Hypotheses
12(1)
The Null Hypothesis
12(1)
The Alternative Hpothesis
12(1)
Type I and Type II Errors
13(1)
Level of Significance
13(1)
Test of Hypothesis Parametric Tests
13(1)
Tests for a Single Parameter (Mean) Involving the Normal Distribution
14(5)
Tests of Hypotheses for Single Means Involving the Student's t-Distibution
19(2)
Comparing Two Populations Using t-Distribution
21(1)
Paired Comparison or Matched Pari t-Test
22(2)
Pooled Variance t-Test
24(3)
Two-Sample t-Test with Unknown Variances
27(2)
Operating Characteristic Curves
29(2)
The p-Value Approach to Decisions in Statistical Inference
31(1)
Making a Decision in Hypothesis Testing with p-Value
32(1)
Applications to the Decisions Made in Previous Examples
32(1)
Regression Analysis
33(35)
Simple Linear Regression
35(5)
Checking Model Adequacy---Diagnosis by Residual Plots
40(5)
Checking Model Adeqacy---Lack of Fit Test
45(3)
Multiple Linear Regression
48(4)
Ploynomial Regression
52(1)
Fitting a Parabola
53(4)
Fitting Higher Order Polynomials
57(1)
Orthogonal Polynomials
58(1)
Fitting Othogonal Polynomials
59(3)
SAS Analysis of the Data of Example 1.4
62(2)
Use of Dummy Variables in Regression Models
64(4)
Exercises
68(5)
References
73(2)
Expermietnts, the Completely Randomized Design---Classical and Regression Approaches
75(94)
Expermients
75(2)
Experiments to Compare Treatments
77(28)
An Illustrative Example
78(1)
Idea I
78(1)
Idea II
79(1)
Idea III
79(3)
Some Basic Ideas
82(1)
Requirements of a Good Experiment
83(1)
One-Way Experimental Layout or the Completely Randomized Design: Design and Analysis
84(2)
Analysis of Experimental Data (Fixed Effects Model)
86(2)
Expercted Values for the Sums of Squares
88(4)
Estimating the Parameters of the Model
92(1)
Analysis of Vairance Table
93(3)
Follow-Up Analysis to Check for Validity of the Model
96(2)
Least signigficant Difference Methods
98(1)
Duncan's Multiple range Test
98(1)
Tukey's Studentized Range Test
99(3)
SAS Program for Analysis of Responses of the Experiment in Example 2.2
102(3)
Checking Model Assumptions
105(16)
Analysis of Residuals
106(4)
Checking for Normality
110(1)
Hitogram
110(1)
Normal Probability Plot
110(3)
Nonhomogeneity of Variances
113(1)
Modified Levene's Test for Homogeneity of Variances
114(1)
Application of Data from Example 2.2 on Varieties of Nutrient Extractions of Fruit
115(1)
Dealing with Heteroscedasticity
116(1)
Variance-Stabilizing Transformations
116(1)
Use of Welch F-test to Deal with Responses with Unequal Variances
117(1)
One-Way ANOVA with Unequal Observations per Group
117(4)
Applications of Orthogonal Contrasts
121(16)
Analytical Study of Components of Treatment Effect Using Orthogonal Contrasts
121(4)
SAS Program for Analysis of Data of Example 2.3
125(2)
Fitting Response Curves in One-Way Anova (CRD) Using Orthogonal Polynomial Contrasts
127(2)
Fitting of Polynomials by the Least Squares Regression Method
129(4)
Fitting of Response Curves to Data using Orthodgonal Contrasts
133(4)
Regression Models of the CRD (One-Way Layout)
137(11)
Regression Models fro CRD (Effects Coding Method)
137(1)
Regression Models for the Responses f Example 2.2
138(1)
Analysis of Varuance to Test the Significance of the Fitted Model
139(2)
SAS Program for Analysis of Data of Example 2.2 Using Regression Mode (Effects Coding method)
141(2)
Refression Model for Cell Reference Methods
143(3)
SAS Program for Regression Model fot Example 2.2 (Reference Cell Coding Method)
146(2)
Regrssion Models for ANOVA for CRD Using Orthogonal Contrasts
148(1)
Regression Model for Example 2.2 Using Orthogonal Contrasts Coding (Helmert Coding)
149(7)
SAS Analysis of Data of Example 2.2 Using Orthogonal Contrasts (Helmert Coding)
154(2)
Regression Model for Example 2.3 Using Orthogonal Contrasts Coding
156(6)
SAS Analysis of Data of Example 2.3 Using Orthogonal Contrasts (Helmert Coding)
160(2)
Exercises
162(3)
References
165(4)
Two-Factor Factorial Experiments and Repeated Measures Designs
169(50)
Full Two-Factor Factorial Experiment (Two-Way ANOVA with Replication)---Fixed Effects Model
169(21)
SAS Analysis of Data of Example 3.1
175(3)
Simple Effects of an Independent Variable
178(1)
Absence of Interaction in a Factorial Experiment
179(2)
Presence of Interaction in a Factorial Experiment
181(3)
Interpreting Interaction by Testing Simple Effects
184(1)
Choosing the Simple Effects to Test
184(1)
Testing the Simple Effects
185(2)
Examination of Interaction for Example 3.1 through Analysis of Simple Effects
187(2)
Testing for Homogeneity of Variances
189(1)
Two-Factor Factorial Effects (Random Effects Model)
190(6)
SAS Analysis of Data of Example 3.2
194(2)
Two-Factor Factorial Experiment (Mixed Effects Model)
196(3)
SAS Analysis of Data of Example 3.2a (Mixed Effects Model)
198(1)
Repeated Measures Design (One-Way RMD)
199(8)
The Model
199(2)
Mixed Randomized Complete Block Design
201(1)
Mixed RCBD versus One-Way RMD
202(5)
Mixed RCBD (Involving Two Factors)
207(7)
SAS Analysis of Responses of Example 3.4
211(3)
Exercises
214(3)
References
217(2)
Regression Approaches to the Analysis of Responses of Two-Factor Experiments and Repeated Measures Designs
219(58)
Regression Models for the Two-Way ANOVA (Full Two-Factor Factorial Experiment)
219(12)
Regression Model for Two-Factor Factorial Design with Effects Coding for Dummy Varibles
220(1)
Estimation of Parameters for the Regression Model for the General Two-Factor Factorial Design with Effect Coding for Dummy Variables
220(1)
Application of the Regression Model for the Two-Factor Factorial Design, with Effect Coding for Dummy Variables to Example 3.1
221(1)
Relations for Estimation of Parameters for the Regression Model with Effect Coding for Dummy Variables for Responses of Example 3.1
221(1)
Estimation of Parameters for the Regression Model
222(4)
SAS Program for Example 3.1 (Effects Coding for Dummy Variables)
226(3)
Splitting Regression Sum of Squares according to Factorial Effect and Performing ANOVA
229(2)
Regression Model for Two-Factor Factorial Experiment Using Reference Cell Coding for Dummy Variables
231(8)
Estimation of Parameters for the Regression Model with Reference Cell Coding for Dummy Variables (Example 3.1)
232(4)
SAS Program
236(3)
Use of SAS for the Analysis of Responses of Mixed Models
239(3)
Implementation of the General Linear Mixed Model in PROC MIXED in SAS
241(1)
Use of PROC Mixed in the Analysis of Responses of RMD in SAS
242(14)
Choosing the Covariance Structure to Use
244(1)
Analysis of Responses of the Experiment on Guinea-Pig Ventricular Mycotes (Example 3.3) with PROC MIXED in SAS
245(3)
Residual Analysis for the Guinea-Pig Mycotes Experiment (Example 3.3)
248(3)
Analysis of Responses of Example 3.4 Using PROC MIXED in SAS
251(1)
Choosing Covariance Structure for Example 3.4
252(1)
Specifying the Model and Analyzing Responses of Example 3.4
253(3)
Discussion of SAS Output for Example 3.4
256(1)
Residual Analysis for the Vitamin Experiment (Example 3.4)
256(3)
Regression Model of the Two-Factor Factorial Design Using Orthogonal Contrasts (Example 3.1)
259(9)
Use of PROC Mixed in SAS to Estimate Variance Components When Levels of Factors Are Random
268(2)
SAS Program for Analysis of Data of Example 4.1
270(4)
Exercises
274(1)
References
275(2)
Designs with Randomization Restriction---Randomized Complete Block, Latin Squares, and Related Designs
277(64)
Randomized Complete Block Design
277(6)
Testing for Differences in Block Means
283(13)
Relative Efficiency of the RCBD to CRD
285(1)
Application to Example 5.1
285(1)
Residuals and Parameters Estimates in the RCBD
286(2)
SAS Analysis of Responses of Example 5.1
288(4)
SAS Analysis of Data of Example 5.2
292(3)
SAS Analysis of Responses of Example 5.3
295(1)
Estimation of a Missing Value in the RCBD
296(2)
Latin Squares
298(4)
Use of Latin Squares for Factorial Experiments
302(1)
Some Expected Mean Squares
302(5)
Estimation of Treatment Effects and Confidence Intervals for Differences between Two Treatments
303(4)
Replications in Latin Square Design
307(17)
Treatment of Residuals in Latin Squares
321(1)
Estimation of Missing Value in Unreplicated Latin Square Designs
321(3)
Graeco-Latin Square Design
324(7)
SAS Analysis of Data of Example 5.9
329(2)
Estimation of Parameters of the Model and Extraction of Residuals
331(2)
Application to Data of Example 5.9
331(2)
Exercises
333(7)
References
340(1)
Regression Models for Randomized Complete Block, Latin Squares, and Graeco-Latin Square Designs
341(80)
Regression Models for the Randomized Complete Block Design
341(5)
Dummy Variables Regression Model for RCBD with the Effects Coding Method
341(1)
Estimation of Parameters of the Regression Model for RCBD (Effects Coding Method)
342(2)
Application of the RCBD Regression Model 6.1 to Example 5.1 (Effects Coding Method)
344(1)
Estimation of Model Parameters for Example 5.1
344(2)
SAS Analysis of Responses of Example 5.1 Using Dummy Regression (Effects Coding Method)
346(2)
SAS Program for Regression Analysis of Data of Example 5.1 (Effects Coding Method for Dummy Variables)
347(1)
Dummy Variables Regression Model for the RCBD (Reference Cell Method)
348(7)
Regression Model for RCBD of Example 5.1 (Reference Cell Coding)
350(1)
Estimation of Parameters of the Model Fitted to Responses of Example 5.1 (Reference Cell Method)
350(3)
SAS Program for Regression Analysis of Responses of Example 5.1 (Reference Cell Coding for Dummy Variables)
353(2)
Application of Dummy Variables Regression Model to Example 5.2 (Effects Coding Method)
355(5)
Estimation of Parameters for the Regression Model for Responses of Example 5.2 (Effects Coding Method)
355(3)
SAS Program for Example 5.2 for the Regression Model with Effects Coding for Dummy Variables
358(2)
Regression Model for RCBD of Example 5.2 (Reference Cell Coding)
360(6)
SAS Analysis of Data of Example 5.2 Using Regression Model with Reference Cell Coding for Dummy Varibales
362(4)
Regression Models for the Latin Square Design
366(6)
Regression Model for the Latin Square Design Using Effects Coding Method to Define Dummy Variables
366(1)
Relations for Estimation Model Parameters (Effects Coding Method)
367(1)
Estimation of Parameters of Regression Model for Example 5.5 (Effects Coding Method)
368(1)
Extracting Residuals and Testing for Significance of the Model
368(1)
SAS Program for the Analysis of Responses of Example 5.5 (Effects Coding Method)
368(4)
Dummy Variables Regression Analysis for Example 5.5 (Reference Cell Method)
372(6)
Estimation of Model Parameters (Reference Cell Method)
373(3)
SAS Program for Fitting Model 6.16 (Reference Cell Method) for Experiment in Example 5.5
376(2)
Regression Model for Example 5.7 Using Effects Coding Method to Define Dummy Variables
378(9)
Estimation of Dummy Variables Regression Model Parameters for Example 5.7 (Effects Coding Method)
379(5)
SAS Program for Regression Analysis of Data of Example 5.7 (Effects Coding Method)
384(3)
Dummy Variables Regression Model for Example 5.7 (Reference Cell Coding Method)
387(10)
Estimation of Parameters of Regression Model for Example 5.7 (Reference Cell Coding)
389(4)
SAS Program for Analysis of Responses of Example 5.7 (Reference Cell Coding Method)
393(4)
Regression Model for the Graeco-Latin Square Design
397(6)
Regression Model for Graeco-Latin Squares Using Effects Coding Method
397(1)
Estimation of Regression Parameters for Example 5.9 for the Effects Coding Model
398(3)
SAS Program for Responses of Example 5.9 Using Effects Coding Model
401(2)
Regression Model for Graeco-Latin Squares (Reference Cell Method)
403(7)
Estimation of Model Parameters for Reference Cell Method
404(1)
Estimation of the Parameters of the Model Applied to Example 5.9
405(2)
SAS Program for Dummy Regression Analysis of Responses of Example 5.9 Using Reference Cell Method
407(3)
Regression Model for the RCBD Using Orthogonal Contrasts (Example 5.1)
410(4)
Regression Model for RCBD Using Orthogonal Contrasts (Example 5.2)
414(3)
Exercises
417(2)
References
419(2)
Factorial Designs---The 2k and 3k Factorial Designs
421(60)
Advantages of Factorial Designs
422(3)
The Concept of Interaction of Factors
422(3)
2k and 3k Factorial Designs
425(5)
22 Factorial Designs
426(1)
Standard Order for Treatment Combinations in 2k Designs
426(4)
Contrasts for Factorial Effects in 22 and 23 Factorial Designs
430(13)
The Models
433(10)
General 2k Factorial Design
443(2)
Factorial Contrasts in 2k Factorial Designs
443(2)
Link between Factorial Effects and Group Theory
445(1)
Factorial Effects in 2k Factorial Designs
445(11)
2k Factorial Designs---A Single Replicate
445(4)
Obtaining Estimates of Responses
449(5)
Dealing with Significant Higher Order Interactions in the Single and Half Replicates of a 2k Factorial Design
454(1)
Collapsing a Single Replicate of 2k Factorial Design into a Full 2k-1 Factorial Design
455(1)
3k Factorial Designs
456(16)
33 Factorial Design
464(8)
Extension to k Factors at Three Levels
472(2)
Exercises
474(4)
References
478(3)
Regression Models for 2k and 3k Factorial Designs
481(62)
Regression Models for the 22 Factorial Design Using Effects Coding Method (Example 7.1)
481(5)
Estimates of the Model Parameters
482(1)
Testing for Significance of the Fitted Model 8.2
483(1)
SAS Analysis of Data of Example 7.1 under the Model 8.1
484(2)
Regression Model for Example 7.1 Using Reference Cell to Define Dummy Variables
486(4)
Estimates of the Model Parameters
486(1)
Testing for Significance of the Fitted Model
487(1)
SAS Analysis of Data of Example 7.1 under the Model 8.1
488(2)
General Regression Models for the Three-Way Factorial Design
490(7)
Modeling the General Three-Way Factorial Design Using Effects Coding Method to Define Dummy Variables
490(1)
Estimation of Parameters for the General Three-Way Factorial Experiment with Effects Code Definition for Dummy Variables
491(1)
Fitting the Regression Model 8.6 (Effects Coding Method) for the Experimental Design of Example 7.2
492(2)
Testing for Significance of the Fitted Model
494(1)
SAS Analysis of Responses of a 23 Factorial Design (Example 7.2)
495(2)
The General Regression Model for a Three-Way ANOVA (Reference Cell Coding Method)
497(6)
Regression Model for 23 Factorial Design and Relations for Estimating Parameters (Reference Cell Method)
498(1)
Application to Example 7.2
499(1)
Testing for Significance of the Fitted Model 8.6 for Example 7.2
500(1)
SAS Program for Analysis of Data of Example 7.2 (Reference Cell Method)
501(2)
Regression Models for the Four-Factor Factorial Design Using Effects Coding Method
503(13)
Regression Model for the 24 Factorial Design Using Effects Coding Method for Defining Dummy Variables
505(1)
Application of the Model to Example 7.3 (Effects Coding Method)
505(4)
SAS Program for Analysis of Data of Example 7.3
509(1)
Regression Analysis for a Four-Factor Factorial Experiment Using Reference Cell Coding to Define Dummy Variables
510(2)
Application of Regression Model (Using Reference Cell Coding for Dummy Variables) to Example 7.3
512(1)
Estimation of Parameters of the Model
512(3)
SAS Program for Analysis of Data of Example 7.3
515(1)
Dummy Variables Regression Models for Experiment in 3k Factorial Designs
516(11)
Dummy Variables Regression Model (Effects Coding Method) for a 32 Factorial Design
517(1)
Relations for Estimating Parameters of the Model
517(1)
Fitting the Model to Example 7.4
518(2)
SAS Program and Analysis of Data for Example 7.4 (Effects Coding Model)
520(2)
Fitting the Model to Example 7.4 by Reference Cell Method
522(3)
SAS Program and Analysis of Data for Example 7.4 (Reference Cell Model)
525(2)
Fitting Regression Model for Example 7.5 (Effects Coding Method)
527(7)
SAS Analysis of Data of Example 7.5 Using Effects Coding Method
531(3)
Fitting Regression Model 8.22 (Reference Cell Coding Method) to Responses of Experiment of Example 7.5
534(6)
SAS Analysis of Data of Example 7.5
538(2)
Exercises
540(3)
Fractional Replication and Confounding in 2k and 3k Factorial Designs
543(52)
Construction of the 2k-1 Fractional Factorial Design
543(3)
Some Requirements of Good 2k-1 Fractional Factorial Designs
546(1)
Contrasts of the 2k-1 Fractional Factorial Design
546(5)
Estimation of the Effects of a 2k-1 Fractional Design Using a Full 2k-1 Factorial Design
547(4)
General 2k-p Fractional Design
551(3)
Resolution of a Fractional Factorial Design
554(4)
Resolution III Designs
555(2)
Resolution IV Designs
557(1)
Resolution V Designs
558(1)
Fractional Replication in 3k Factorial Designs
558(6)
One-Third Fraction of the 34 Factorial Design
563(1)
General 3k-p Factorial Design
564(1)
Confounding in 2k and 3k Factorial Designs
565(1)
Confounding in 2k Factorial Designs
566(12)
Blocking a Single Replicate of the 2k Factorial Design
572(2)
Blocking Fractionals of the 2k Factorial Design
574(1)
2k Factorial Design in 2p Blocks
575(3)
Confounding in 3k Factorial Designs
578(7)
Assignment of 3k Factorial Design in 3p Blocks (p=1)
578(4)
Assignment of the 3k Factorial Design into 3p Blocks (p=2)
582(2)
Assignment of the 3k Factorial Design into 3p Blocks (p>3)
584(1)
Partial Confounding in Factorial Designs
585(4)
Partial Confounding in 2k Factorial Design
585(2)
Partial Confounding in 3k Factorial Design
587(2)
Other Confounding Systems
589(1)
Exercises
589(4)
References
593(2)
Balanced Incomplete Blocks, Lattices, and Nested Designs
595(48)
Balanced Incomplete Block Design
595(8)
Balanced Incomplete Block Design---The Model and Its Analysis
596(2)
Estimation of Treatment Effect and Calculation of Treatment Sum of Squares for Balanced Incomplete Block Design
598(2)
SAS Analysis of Responses of Experiment in Example 10.1
600(2)
Precision of the Estimates and Confidence Intervals
602(1)
An Aside
602(1)
End of Aside
603(1)
Comparison of Two Treatments
603(2)
Orthogonal Contrasts in Balanced Incomplete Block Designs
605(2)
Lattice Designs
607(8)
Balanced Lattice Designs
607(5)
Adjustment of Treatment Totals and Further Analysis
612(3)
Partially Balanced Lattices
615(6)
Analysis of Partially Balanced Lattices
616(5)
Nested or Hierarchical Designs
621(11)
The Model, Assumptions, and Statistical Analysis
622(5)
Unbalanced Two-Stage Nested Design
627(4)
Higher Order Nested Designs
631(1)
Designs with Nested and Crossed Factors
632(4)
SAS Program for Example 10.6
635(1)
Exercises
636(4)
References
640(3)
Methods for Fitting Response Surfaces and Analysis of Covariance
643(56)
Method of Steepest Ascent
644(2)
Designs for Fitting Response Surfaces
646(1)
Designs for Fitting First-Order Models
646(1)
Fitting a First-Order Model to the Response Surface
647(13)
Designs for Fitting Second-Order Surfaces
656(1)
Use of 3k Factorial Designs
657(1)
Central Composite Designs
657(3)
Fitting and Analysis of the Second-Order Model
660(5)
Analysis of Covariance
665(1)
One-Way Analysis of Covariance
666(8)
Using SAS to Carry Out Covariance Analysis
673(1)
Other Covariance Models
674(19)
Tests about Significance of Regression
681(3)
Testing for Homogeneity of Slopes across Levels of Factors and Cells
684(2)
Using Regression for ANCOVA (Application to Two-Way ANCOVA)
686(3)
Mulltiple Covariates in ANCOVA
689(3)
Dealing with the Failure of the Homogeneity of Slopes Assumption in ANCOVA
692(1)
Blocking the Concomitant Variable
692(1)
The Johnson-Neyman Method
693(1)
Exercises
693(4)
References
697(2)
Multivariate Analysis of Variance (MANOVA)
699(78)
Link between ANOVA and MANOVA
699(1)
One-Way MANOVA
700(17)
Tests for Equality of Vectors of Treatment Effects
702(3)
Alternative Testing Methods
705(8)
SAS Analysis of Responses of Example 12.1
713(4)
Multivariate Analysis of Variance---The Randomized Complete Block Experiment
717(17)
SAS Solution for Example 12.2
729(5)
Multivariate Two-Way Experimental Layout with Interaction
734(17)
SAS Program for Example 12.3
745(6)
Two-Stage Multivariate Nested or Hierarchical Design
751(11)
SAS Program for Example 12.4
757(5)
Multivariate Latin Square Design
762(9)
SAS Program
767(4)
Exercises
771(4)
References
775(2)
Appendix: Statistical Tables 777(40)
Index 817
Onyiah, Leonard C.