Experimental design and analysis / Steven R. Brown, Lawrence E. Melamed.

Format:

Book

Author/Creator:

Brown, Steven R. (Steven Randall), 1939-

Contributor:

Melamed, Lawrence E.

Series:

Sage university papars. Quantitative applications in the social sciences ; no. 07-074.

Sage university papers. Quantitative applications in the social sciences ; 74

Language:

English

Subjects (All):

Social sciences--Statistical methods.

Social sciences.

Statistical hypothesis testing.

Physical Description:

vi, 86 pages ; 23 cm.

Place of Publication:

Newbury Park, Calif. : Sage, [1990]

Summary:

This volume introduces the reader to one of the most fundamental topics in social science statistics: experimental design. The authors clearly show how to select an experimental design based on the number of independent variables and the number of subjects. Other topics addressed include variability, hypothesis testing, how ANOVA can be extended to the multi-group situation, the logic of the "t "test and completely randomized designs.

Contents:

2. Variability 6

3. t Test 9

4. Analysis of Variance 12

5. Completely Randomized Design 19

6. Comparisons and Trends 24

6.1 A Priori Comparisons 25

6.2 The Dunn Test 28

6.3 Trend Analysis 31

6.4 A Posteriori Comparisons 33

7. Treatments by Blocks 36

8. Algorithms 43

8.1 Nesting and Cross-Classifying Subjects 43

8.2 Degrees of Freedom and Sums of Squares 45

8.3 Mean Squares and F Ratios 50

9. Factorial Design 55

9.1 A Posteriori Testing 59

9.2 Hierarchical Designs 61

10. Split-Plot and Repeated Measures Designs 64

Appendix A Percentage Points of t Distribution (2-Tailed) 79

Appendix B Upper Percentage Points of F Distribution 80

Appendix C Upper Percentage Points of the F[subscript max] Statistic 81

Appendix D Studentized Range (Tukey's HSD Test) 82

Appendix E t[subscript D] Distribution (Dunn's Test) 83.

Notes:

Includes bibliographical references (pages 84-85).

ISBN:

0803938543

OCLC:

21229429