E Book Educational Research L R Gay Pearson 2012

582 APPENDIX A • REFERENCE TABLES

TABLE A.2 • Values of the correlation coefficient for different levels of significance

Source: From R. A. Fisher and F. Yates, Statistical Tables for Biological, Agricultural and Medical Research
(6th ed.), Pearson Education Limited, copyright © 1974 Longman Group Ltd. Reprinted with permission of
Pearson Education Limited.

APPENDIX A • REFERENCE TABLES 583

TABLE A.3 • Standard normal curve areas

Area

z

584 APPENDIX A • REFERENCE TABLES

TABLE A.3 • Continued

APPENDIX A • REFERENCE TABLES 585

TABLE A.3 • Continued

586 APPENDIX A • REFERENCE TABLES

TABLE A.3 • Continued

TABLE A.4 • Distribution of t

PROBABILITY

df .20 .10 .05 .02 .01 .001

1 3.078 6.314 12.706 31.821 63.657 636.619
2 1.886 2.920 4.303 6.965 9.925 31.598
3 1.638 2.353 3.182 4.541 5.841 12.941
4 1.533 2.132 2.776 3.747 4.604 8.610
5 1.476 2.015 2.571 3.365 4.032 6.859
6 1.440 1.943 2.447 3.143 3.707 5.959
7 1.415 1.895 2.365 2.998 3.499 5.405
8 1.397 1.860 2.306 2.896 3.355 5.041
9 1.383 1.833 2.262 2.821 3.250 4.781
10 1.372 1.812 2.228 2.764 3.169 4.587
11 1.363 1.796 2.201 2.718 3.106 4.437
12 1.356 1.782 2.179 2.681 3.055 4.318
13 1.350 1.771 2.160 2.650 3.012 4.221
14 1.345 1.761 2.145 2.624 2.977 4.140
15 1.341 1.753 2.131 2.602 2.947 4.073
16 1.337 1.746 2.120 2.583 2.921 4.015
17 1.333 1.740 2.110 2.567 2.898 3.965
18 1.330 1.734 2.101 2.552 2.878 3.922
19 1.328 1.729 2.093 2.539 2.861 3.883
20 1.325 1.725 2.086 2.528 2.845 3.850
21 1.323 1.721 2.080 2.518 2.831 3.819
22 1.321 1.717 2.074 2.508 2.819 3.792
23 1.319 1.714 2.069 2.500 2.807 3.767
24 1.318 1.711 2.064 2.492 2.797 3.745
25 1.316 1.708 2.060 2.485 2.787 3.725
26 1.315 1.706 2.056 2.479 2.779 3.707
27 1.314 1.703 2.052 2.473 2.771 3.690
28 1.313 1.701 2.048 2.467 2.763 3.674
29 1.311 1.699 2.045 2.462 2.756 3.659
30 1.310 1.697 2.042 2.457 2.750 3.646
40 1.303 1.684 2.021 2.423 2.704 3.551
60 1.296 1.671 2.000 2.390 2.660 3.460
120 1.289 1.658 1.980 2.358 2.617 3.373
` 1.282 1.645 1.960 2.326 2.576 3.291

Source: R. A. Fisher and F. Yates, Statistical Tables for Biological, Agricultural and Medical Research (6th ed.),
Pearson Education Limited, copyright © 1974 Longman Group Ltd. Reprinted with permission of Pearson
Education Limited.

587

588 APPENDIX A • REFERENCE TABLES

TABLE A.5 • Distribution of F

Source: From R. A. Fisher and F. Yates, Statistical Tables for Biological, Agricultural and Medical Research
(6th ed.), Pearson Education Limited, copyright © 1974 Longman Group Ltd. Reprinted with permission
of Pearson Education Limited.

APPENDIX A • REFERENCE TABLES 589

TABLE A.5 • Continued

590 APPENDIX A • REFERENCE TABLES

TABLE A.5 • Continued

APPENDIX A • REFERENCE TABLES 591

TABLE A.5 • Continued

592 APPENDIX A • REFERENCE TABLES

TABLE A.6 • Distribution of x2

Source: From R. A. Fisher and F. Yates, Statistical Tables for Biological, Agricultural and Medical Research
(6th ed.), Pearson Education Limited, copyright © 1974 Longman Group Ltd. Reprinted with permission of
Pearson Education Limited.

APPENDIX B

Statistical References

Figure B.12.1 Excel Options and Procedures for Creating a Pivot Table: Gender
by Ethnicity

Figure B.12.2 SPSS Options for Crosstab: Gender by Ethnicity
Figure B.12.3 Creating a Bar Graph with Excel: Gender by Economic Level
Figure B.12.4 Creating a Frequency Polygon in Excel of Achievement Test Scores
Figure B.12.5 SPSS Options for Correlation
Figure B.12.6 Variable Selection for Correlation
Figure B.13.1 SPSS Menu Options for Dependent (Paired) Samples t Test
Figure B.13.2 Paired-Samples t Test Window
Figure B.13.3 SPSS Menu for ANOVA Test
Figure B.13.4 SPSS Menu for ANOVA: Post Hoc Analysis
Figure B.13.5 SPSS Menu for ANOVA: Scheffe Multiple Comparison
Figure B.13.6 SPSS Menu for Multiple Regression Test
Figure B.13.7 Linear Regression Window
Figure B.13.8 SPSS Menu for Chi-Square Analysis
Figure B.13.9 Chi-Square Analysis Window
Table B.13.1 Pinecrest College Dataset

593

594 APPENDIX B • STATISTICAL REFERENCES

PROCEDURES 7. Click on Ethnicity and drag it to “Drop
Column Fields Here.”
1. Begin by highlighting Gender and Ethnicity
and then click on “Data” in the tool bar. This 8. Click on ID, since it serves as the data count,
is Step 1 of 3. and drag it to “Drop Data Items Here.”

2. Select “Pivot Table Report,” as illustrated in 9. The upper left corner of the Pivot table will
the screen below. typically default to “Sum of ID.” Change it
to “Count” by going to the Pivot Table menu
3. Click “Next” in the window to select the Excel in the box below the table, select “Field
list or data base. Settings,” and select “Count.” You can also
make a label by double-clicking above the
4. Data will already be highlighted, since you table where it will say “Double-click to add
selected it in #1 above. Click “Next.” header.”

5. Choose “New Sheet” and then “Finish.”
6. Click on Gender and drag it to “Drop Row

Fields Here.”

FIGURE B.12.1 • Excel options and procedures for creating a pivot table: Gender by ethnicity

APPENDIX B • STATISTICAL REFERENCES 595

FIGURE B.12.1 • Continued

596 APPENDIX B • STATISTICAL REFERENCES

FIGURE B.12.1 • Continued

APPENDIX B • STATISTICAL REFERENCES 597

PROCEDURES 2. Highlight the variable “Gender” and click
the arrow to place “Gender” in the row box.
1. Select “Analyze,” “Descriptive Statistics,” and Then highlight “Ethnicity” and click the
“Crosstabs,” as illustrated below. arrow to place “Ethnicity” in the column box.

3. Click “OK.”

FIGURE B.12.2 • SPSS options for crosstab: Gender by ethnicity

598 APPENDIX B • STATISTICAL REFERENCES

FIGURE B.12.2 • Continued

APPENDIX B • STATISTICAL REFERENCES 599

PROCEDURES 3. Select the chart or graphic display you wish.
Also use the Toolbox and additional options
1. Create a Pivot Table, as shown in the print under the Chart menu, which will appear in
screen below the Excel menu bar once you have selected
Chart. For the bar chart we created in
2. Click “Insert” in the Excel menu, and then Figure 12.3 we selected a variety of options,
“Chart.” A bewildering array of choices will a 3D format, and added text labels (e.g.,
appear, as shown in the following print high, medium, low).
screen.

FIGURE B.12.3 • Creating a bar graph with Excel: Gender by economic level

600 APPENDIX B • STATISTICAL REFERENCES

FIGURE B.12.3 • Continued

APPENDIX B • STATISTICAL REFERENCES 601

FIGURE B.12.4 • Creating a frequency polygon in Excel of achievement test scores

602 APPENDIX B • STATISTICAL REFERENCES

FIGURE B.12.5 • SPSS options for correlation

APPENDIX B • STATISTICAL REFERENCES 603

FIGURE B.12.6 • Variable selection for correlation

604 APPENDIX B • STATISTICAL REFERENCES

FIGURE B.13.1 • SPSS menu options for dependent (paired) samples t test

APPENDIX B • STATISTICAL REFERENCES 605

FIGURE B.13.2 • Paired-samples t test window

606 APPENDIX B • STATISTICAL REFERENCES

FIGURE B.13.3 • SPSS menu for ANOVA test

APPENDIX B • STATISTICAL REFERENCES 607

FIGURE B.13.4 • SPSS menu for ANOVA: Post hoc analysis

608 APPENDIX B • STATISTICAL REFERENCES

FIGURE B.13.5 • SPSS menu for ANOVA: Scheffe multiple comparison

APPENDIX B • STATISTICAL REFERENCES 609

FIGURE B.13.6 • SPSS menu for multiple regression test

610 APPENDIX B • STATISTICAL REFERENCES

FIGURE B.13.7 • Linear regression window

APPENDIX B • STATISTICAL REFERENCES 611

FIGURE B.13.8 • SPSS menu for chi-square analysis

612 APPENDIX B • STATISTICAL REFERENCES

FIGURE B.13.9 • Chi-square analysis window

APPENDIX B • STATISTICAL REFERENCES 613

TABLE B.13.1 • Pinecrest College dataset

StudentID Gender Econ ReadLevel HSGPA SAT MATH LANG CollGPA

1 1 2 2 2.52 425 57 54 2.65
2 2 1 3 1.7 334 54.6 64 2.82
3 1 1 1 2.43 433 37 44.9 2.67
4 1 2 1 2.68 544 46.2 35.2 2.54
5 2 1 3 2.33 489 63.8 58.3 2.85
6 1 1 1 1.58 378 31.2 23.1 2.3
7 2 1 3 3.23 538 53.6 75 3.46
8 1 3 3 3.58 550 72 91 3.78
9 2 1 2 2.33 403 53 48 2.56
10 1 1 2 1.76 478 62 55 2.88
11 2 3 3 3.74 533 72.3 78 3.58
12 1 1 1 2.66 424 28.4 43 2.59
13 2 1 3 3.28 555 42.3 78 3.56
14 1 1 1 2.18 560 34.8 27 1.88
15 2 3 3 3.45 710 63 88 3.22
16 2 2 3 2.98 469 63.6 59 2.67
17 1 3 2 2.45 580 72 77 3.67
18 2 3 3 3.43 720 84 92 3.23
19 1 2 2 1.78 435 62 67 2.88
20 2 1 2 2.45 320 64.6 48.5 2.25
21 1 3 2 3.22 470 58.5 78 3.54
22 1 1 1 1.78 593 22 27.2 2.3
23 2 2 2 2.54 530 34 42 2.26
24 2 1 3 2.78 650 62 77 3.24
25 1 2 2 2.17 490 48 59 2.86
26 2 3 3 3.54 580 58 46 3.22
27 2 3 3 2.88 525 59 83 3.45
28 1 1 2 3.22 450 57 75 3.68
29 2 2 3 2.45 476 62 86 3.54
30 2 2 3 2.68 590 48 52 2.45
31 1 3 2 3.27 582 71 78 3.58
32 1 2 2 2.77 485 48 57 2.85
33 2 3 3 2.85 678 73 82 3.48
34 1 1 2 1.88 538 56 52 2.34
35 2 2 3 2.54 486 64 88 3.48
36 2 2 2 2.33 438 38 47 2.25
37 1 3 2 3.47 498 66 73 3.25
38 1 1 2 2.54 552 52 47 2.36
39 1 3 3 2.66 620 82 85 3.54
40 2 1 3 2.34 468 43 65 2.88
41 2 1 3 1.78 432 47 72 2.65
42 1 2 2 2.53 444 53 48 2.24
43 2 3 2 3.54 585 52 48 2.85
44 2 2 3 2.88 535 54 84 3.24
45 1 2 2 2.44 588 61 73 3.16
46 2 1 3 1.78 438 43 68 2.68
47 2 2 2 3.35 450 47 38 2.48
48 1 2 1 2.55 580 36 44 2.25
49 1 3 2 2.82 465 64 82 3.54
50 2 1 3 2.94 510 48 52 2.74
51 1 2 2 2.32 435 57 54 2.65
52 2 1 3 1.75 356 45 64 2.78
53 1 1 2 2.58 487 54 44.9 2.67
54 1 2 1 2.48 454 38 42 2.64

614 APPENDIX B • STATISTICAL REFERENCES

TABLE B.13.1 • Continued

StudentID Gender Econ ReadLevel HSGPA SAT MATH LANG CollGPA

55 2 1 3 2.43 520 53 58.3 2.85

56 1 1 1 1.63 387 31.2 23.1 2.38

57 2 1 3 3.18 527 57 75 3.55

58 1 3 3 3.58 568 84 91 3.67

59 2 1 2 2.45 435 53 48 2.56

60 1 1 2 1.84 467 52 55 2.78

61 2 3 3 3.54 523 75 81 3.67

62 1 1 1 2.56 453 52 45 2.37

63 2 1 3 3.16 545 62 82 3.58

64 1 1 1 2.28 467 25 27 1.86

65 2 3 3 3.45 712 78 94 3.42

66 2 2 3 2.88 474 44 57 2.67

67 1 3 2 2.43 585 74 83 3.65

68 2 3 3 3.43 725 88.4 92 3.23

69 1 2 2 1.78 567 61 63 2.83

70 2 1 2 2.48 326 33 53 2.28

71 1 3 2 3.28 475 58.5 81 3.64

72 1 1 1 1.68 587 32 26 2.28

73 2 2 2 2.52 524 54 41 2.23

74 2 1 3 2.65 634 88 76 3.21

75 1 2 2 2.27 368 38 55 2.74

76 2 3 2 3.64 570 54 49 3.38

77 2 3 3 2.68 525 72 85 3.57

78 1 1 3 3.28 450 67 91 3.58

79 2 2 3 2.76 470 55 86 3.67

80 2 2 2 2.72 565 53 39 2.48

81 1 3 2 3.18 510 65 84 3.54

82 1 2 2 2.57 512 36 55 2.44

83 2 3 3 2.85 678 78 82 3.48

84 1 1 1 1.88 538 54 52 2.34

85 2 2 3 2.54 486 64 88 3.48

86 2 2 3 2.78 457 43 52 2.35

87 1 3 2 3.37 523 53 74 3.18

88 1 1 1 2.54 552 52 47 2.36

89 1 3 2 2.66 620 63 85 3.54

90 2 1 3 2.34 568 52 65 2.88

91 2 1 3 1.78 432 47 72 2.65

92 1 2 2 2.53 444 53 48 2.24

93 2 3 2 3.54 585 52 48 2.85

94 2 2 3 2.88 535 42 84 3.24

95 1 2 3 2.44 588 58 73 3.16

96 2 1 3 1.78 438 45 68 2.68

97 2 2 2 3.35 450 54 38 2.48

98 1 2 1 2.55 580 54 44 2.25

99 1 3 2 2.82 465 65 82 3.54

100 2 1 2 2.94 510 48 52 2.74

101 1 1 2 1.84 467 52 55 2.78

102 2 3 3 3.54 595 45 81 3.67

103 1 1 2 2.56 453 32 45 2.37

104 2 1 3 3.16 545 42.3 82 3.58

105 1 1 1 2.28 467 36 27 1.86

106 2 3 3 3.45 712 83 94 3.42

107 2 2 2 2.88 474 63.6 57 2.67

108 1 3 3 2.43 585 64.2 83 3.65

109 2 3 3 3.43 725 78 92 3.23

APPENDIX B • STATISTICAL REFERENCES 615

TABLE B.13.1 • Continued

StudentID Gender Econ ReadLevel HSGPA SAT MATH LANG CollGPA

110 1 2 2 1.78 567 61 63 2.83

111 2 1 2 2.48 326 57 53 2.28

112 2 1 1 2.45 320 34 48.5 2.25

113 1 3 3 3.22 570 69 78 3.54

114 1 1 1 1.78 543 22 27.2 2.3

115 2 2 2 2.54 530 58.4 42 2.26

116 2 1 2 2.78 547 47 77 3.24

117 1 2 2 2.17 498 52 59 2.86

118 2 3 2 3.54 580 58 46 3.22

119 2 3 3 2.88 525 59 83 3.45

120 1 1 2 3.22 585 57 75 3.68

121 2 2 3 2.45 476 51 86 3.54

122 2 2 2 2.68 645 48 52 2.45

123 2 3 2 3.54 585 34 48 2.85

124 1 2 1 2.48 454 38 42 2.64

125 1 2 2 2.27 525 57 59 2.86

This page intentionally left blank

APPENDIX C

Suggested Responses

SELF-TEST FOR TASK 1A The Major Conclusion
(PAGE 32)
Instructional support and emotional support help
Hamre, B. K., & Pianta, R. C. (2005). Can at-risk children achieve academic scores compa-
instructional and emotional support in the rable to their lower risk peers. Emotional support,
first-grade classroom make a difference but not instructional support, also helps functionally
for children at risk of school failure?, Child at-risk children to relate to their teachers in a more
Development, 76, 949–967. socially appropriate way.

Topic Studied SELF-TEST FOR TASK 1B
(PAGE 32)
This study addresses how certain characteristics of
the first-grade classroom affect children at risk of Sleeter, C. (2009). Developing teacher epis-
academic and social difficulties at school. temological sophistication about multicul-
tural curriculum: A case study. Action in
The Procedures Teacher Education, 31(1), 3–13.

To evaluate their hypothesis that supportive class- Topic Studied
rooms would help at-risk children to succeed, Hamre
and Pianta studied 910 first graders. These children How does teachers’ thinking about curriculum
were part of a longitudinal study of 1,364 families develop in the context of teacher education course-
from 10 U.S. cities. The researchers measured the work, and how might an analysis of a novice
children’s academic and cognitive skills using a teacher’s learning to think more complexly inform
standardized psychometric test that included tests teacher education pedagogy?
of reading, mathematics, memory, and auditory
processing. They also asked the current first-grade The Procedures
teachers to report their perceptions of conflict with
each student, using a 28-item rating scale. Addi- Case study research that included the following
tionally, trained data collectors spent a day observ- data sources: (1) course assignments including an
ing each classroom to rate classroom quality and instructional unit, (2) researcher journal, (3) obser-
teacher behaviors. vational field notes, and (4) tape recorded interview.

The Method of Analysis The Method of Analysis

The primary statistical test used in this study was The author used qualitative analytic methods,
analysis of covariance (ANCOVA). including use of a heuristic tool for reflection (see

617

618 APPENDIX C • SUGGESTED RESPONSES

Table 1: Thinking Complexly About Multicultural statistical relationship exists between two
Curriculum). or more variables. Here, the researchers
are interested in the similarity of the two
The Major Conclusions tests.
3. Research Approach: Causal–comparative
The author concluded that: (1) reflective discus- research. In causal–comparative research, at
sions and writings embedded in teachers’ classroom least two groups (fifth graders from single-
work prompt thinking that can dislodge novice parent families and those from two-parent
assumptions, (2) to facilitate development beyond families) are compared on a dependent
novice thinking, it is essential to provide space and variable or effect (in this case, achievement
support for uncertaintly, and (3) teachers value of reading).
opportunities to learn from peers. 4. Research Approach: Experimental
research. Experimental research allows
SELF-TEST FOR TASK 1C researchers to make cause–effect statements
(PAGE 32) about a study. In addition, researchers have
a great deal of control over the study; here
1. Research Approach: Survey research. Survey the researchers determined the two groups
research involves collecting data to answer (at random) and applied different treatments
questions about the current status of issues or (the two methods of conflict resolution) to
topics; a questionnaire was administered to the two groups.
find out how teachers feel about an issue. 5. Research Approach: Ethnographic
research. Ethnographic research studies
2. Research Approach: Correlational participants in their natural culture or setting;
research. Correlational research seeks to the culture of recent Armenian emigrants is
determine whether, and to what degree, a examined in their new setting.

APPENDIX C • SUGGESTED RESPONSES 619

SELF-TEST FOR TASK 11 (PAGES 573–576)

Akos, P., & Galassi, J. P. (2004). Gender and race as variables in psychosocial adjustment
to middle and high school. The Journal of Educational Research, (98)2, 102–109.

General Evaluation Criteria

INTRODUCTION

Problem CODE

A statement? Y
Paragraph (¶)11, sentence (S)11  

Researchable? Y
Background information? Y
 
e.g., ¶10 Y
Significance discussed?  
Y
e.g., ¶10 Y
Variables and relations discussed?  
Definitions? Y

e.g., ¶7, S4
Researcher knowledgeable?

Review of Related Literature  
Comprehensive? Y
Appears to be
Well organized?  
Critical analysis? Y
Y
e.g., ¶1–10
References relevant?  
Summary? Y
Rationale for hypotheses? N
Sources primary? N
References complete and accurate? Y
Y

Hypotheses  
Questions or hypotheses? Y

¶11  
Testable? Y
Expected differences stated? Y
Variables defined? Y

METHOD

Participants CODE

Population described? Y
Very briefly  

Accessible and target populations described? Y
Sample selection method described? NA
Selection method limited or biased? NA
Sample described? Y&Y
 
Size, yes; characteristics, yes N
Minimum sizes?

Instruments  
Guidelines met for protecting participants? Permissions obtained? NA
Appropriate? Y

1 ¶7 refers to paragraph 7 of the introduction section of the article.The introduction section ends where “Method” begins.

620 APPENDIX C • SUGGESTED RESPONSES

Type of instrument correct? Y
Rationale for selection? N
Instrument purpose and content described? Y
 
¶15, 16 & 17 Y
Validity discussed? Y
Reliability discussed?  
N
¶16 N
Subtest reliabilities? N
Evidence that it is appropriate for sample?  
Procedures for development described? N
Performance posttest not described Y
Administration, scoring, and interpretation procedures described?
Researcher skilled in test construction, administration?

Design and Procedure  
Design appropriate? Y
Procedures sufficiently detailed? Y
Procedures logically related? Y
Instruments and procedures applied correctly? Y
Pilot study described? NA
Control procedures described? NA
Confounding variables discussed? NA

RESULTS Y
 
Appropriate descriptive statistics?
Table 1 & 2 Y
Tests of significance appropriate? Y
Parametric assumptions not violated? NA
Probability level specified in advance? NA
Appropriate degrees of freedom? NA
Inductive logic explicit? Y
Results clearly presented? Y
Tables and figures well organized? Y
Data in each table and figure described?

DISCUSSION (CONCLUSIONS AND RECOMMENDATIONS)

Results discussed in terms of hypothesis? Y

Results discussed in terms of previous research? Y

e.g., ¶22–26  

Generalizations consistent with results? Y

Implications discussed? Y

e.g., ¶37  

Effects of uncontrolled variables discussed? NA

Recommendations for action? Y

e.g., ¶37 & 38  

ABSTRACT OR SUMMARY Y
Y&N
Problem stated?  
Participants and instruments described?
N
Participants briefly; instruments indirectly N
Design identified? Y
Procedures?
Results and conclusions?

APPENDIX C • SUGGESTED RESPONSES 621

TYPE-SPECIFIC EVALUATION CRITERIA Y

Design used: Causal–comparative Y
Y
• Are the characteristics or experiences that differentiate the
Y
groups (i.e., the grouping variable) clearly defined or described?  
• Are critical extraneous variables identified?
• Were any control procedures applied to equate the groups Y
 
on extraneous variables?
• Are causal relations discussed with due caution?

e.g., ¶36
• Are plausible alternative hypotheses discussed?

e.g., ¶37

This page intentionally left blank

Glossary

A-B design A single-subject design in which baseline baseline design, multi-element manipulation design, or
measurements are repeatedly made until stability is simultaneous treatment design.
presumably established, treatment is introduced, and
an appropriate number of measurements are made alternative assessment See performance assessment.
during treatment.
alternative-forms reliability See equivalence.
A-B-A design A single-subject design in which baseline
measurements are repeatedly made until stability is analysis of covariance A statistical method of equat-
presumably established, treatment is introduced, an ing groups on one or more variables and for increas-
appropriate number of measurements are made, and ing the power of a statistical test; adjusts scores on
the treatment phase is followed by a second baseline a dependent variable for initial differences on some
phase. other variable (e.g., pretest performance or IQ) related
to performance on the dependent variable.
A-B-A-B design A single-subject design in which base-
line measurements are repeatedly made until stability analysis of narrative In narrative research, a process
is presumably established, treatment is introduced, an in which the researcher collects stories as data and
appropriate number of measurements are made, and analyzes common themes to produce a description
the treatment phase is followed by a second baseline that applies to all the stories captured in the narratives.
phase, which is followed by a second treatment phase. Compare narrative analysis.

abstract A summary of a study that describes the analysis of variance An inferential statistics technique
hypotheses, procedures, and conclusions. used to test for significant differences among the means
of three or more groups.
accessible population The population from which the
researcher can realistically select subjects. Also called anonymity State of being unknown; study participants
available population. Compare target population. are anonymous when their identities are hidden from
the researcher.
accidental sampling See convenience sampling.
applied research Research conducted for the purpose
achievement test An instrument that measures an indi- of applying, or testing, a theory to determine its useful-
vidual’s current proficiency in given areas of knowledge ness in solving practical problems.
or skill.
aptitude test A measure of potential used to predict
action research Any systematic inquiry conducted by how well an individual is likely to perform in a future
teachers, principals, school counselors, or other stake- situation.
holders in the teaching–learning environment to gather
information about the ways in which their particular artificial categories Categories that are operationally
schools operate, the teachers teach, and the students defined by a researcher.
learn.
assessment General term for the process of collecting,
additive design Any of the variations of the single- synthesizing, and interpreting information; also, the
subject A-B design that involve the addition of another instrument used for such purposes. A test is a type of
phase or phases in which the experimental treatment assessment.
is supplemented with another treatment.
assumption Any important fact presumed to be true but
affective characteristic A mental characteristic related not actually verified; assumptions should be described
to emotion, such as attitude, interest, and value. in the procedure section of a research plan or report.

affective test An assessment designed to measure attenuation The reduction in correlation coefficients
mental characteristics related to emotion. that tends to occur if the measures being correlated
have low reliability.
alternating treatments design A variation of
multiple-baseline design that involves the relatively attitude scale A measurement instrument used to deter-
rapid alternation of treatments for a single participant. mine what a respondent believes, perceives, or feels
Also called multiple schedule design, multi-element about self, others, activities, institutions, or situations.

attrition See mortality.

623

624 GLOSSARY

authentic assessment See performance assessment. common variance The variation in one variable that is
attributable to its tendency to vary with another vari-
available population See accessible population. able. Also called shared variance.

baseline measures Multiple measures of pretest per- compensatory rivalry See John Henry effect.
formance conducted in single-subject research designs
to control for threats to validity. concurrent validity The degree to which the scores on
a test are related to the scores on a similar test admin-
basic research Research conducted for the purpose of istered in the same time frame or to some other valid
developing or refining a theory. measure available at the same time; a form of criterion-
related validity.
bias Distortion of research data that renders the data
suspect or invalid; may occur due to characteristics of confidentiality Right to have information about one-
the researcher, the respondent, or the research design self kept private; researchers protect confidentiality
itself. when they know the identities of study participants but
do not disclose that information.
Buckley Amendment See Family Educational Rights
and Privacy Act of 1974. consequential validity The extent to which an instru-
ment creates harmful effects for the user.
case study The in-depth investigation of one unit (e.g.,
individual, group, institution, organization, program, construct An abstraction that cannot be observed
or document). directly; a concept invented to explain behavior.

category A classification of ideas and concepts in quali- construct validity The degree to which a test measures
tative data analysis. an intended hypothetical construct or nonobservable
trait that explains behavior.
causal–comparative research Research that attempts
to determine the cause, or reason, for existing differ- content validity The degree to which a test measures
ences in the behavior or status of groups of individuals. an intended content area; it is determined by expert
Also called ex post facto research. judgment and requires both item validity and sampling
validity.
census survey Descriptive research that involves
acquiring data from every member of a population. control Efforts on the part of a researcher to remove
the influence of any variable other than the indepen-
changing criterion design A variation of the A-B-A dent variable that may affect performance on a depen-
design in which the baseline phase is followed by dent variable.
successive treatment phases, each of which has a
more stringent criterion for acceptable or improved control group A group of participants in a research
behavior. study who either receive a different treatment than the
experimental group or are treated as usual.
chi square A nonparametric test of significance appro-
priate when the data are in the form of frequency control variable A nonmanipulated variable, usually
counts; compares proportions observed in a study with a physical or mental characteristic of the subjects
proportions expected by chance. (e.g., IQ).

clinical replication The development and application convenience sampling The process of including who-
of a treatment package, composed of two or more ever happens to be available in a sample (e.g., volun-
interventions that have been found to be effective indi- teers). Also called accidental sampling or haphazard
vidually, designed for persons with complex behavior sampling.
disorders.
correlation A quantitative measure of the degree of
closed-ended item See structured item. correspondence between two or more variables.

cluster Any location that contains an intact group with correlation coefficient A decimal number between
similar characteristics (e.g., population members). Ϫ1.00 and ϩ1.00 that indicates the degree to which
two variables are related.
cluster sampling Sampling in which intact groups, not
individuals, are randomly selected. correlational research Research that involves collect-
ing data to determine whether, and to what degree,
coding The process of categorically marking or ref- a relation exists between two or more quantifiable
erencing units of text (e.g., words, sentences, para- variables.
graphs, and quotations) with codes and labels as a way
to indicate patterns and meaning in qualitative data. counterbalanced design A quasi-experimental design
in which all groups receive all treatments, each group
cognitive characteristic A mental characteristic related receives the treatments in a different order, the num-
to intellect, such as mathematics achievement, literacy, ber of groups equals the number of treatments, and all
reasoning, or problem solving. groups are tested after each treatment.

cognitive test An assessment designed to measure
intellectual processes.

GLOSSARY 625

credibility A term used in qualitative research to data saturation A point in qualitative research at which
indicate that the topic was accurately identified and so much data are collected that it is very unlikely that
described. additional data will add new information.

criterion variable In a prediction study or analysis of database A sortable, analyzable collection of units of
concurrent or predictive validity, the variable that is information maintained on a computer.
predicted.
deductive hypothesis A hypothesis derived from the-
criterion-referenced scoring A scoring approach in ory that provides evidence to support, expand, or
which an individual’s performance on an assessment is contradict the theory.
compared to a predetermined, external standard.
deductive reasoning Reasoning that involves develop-
criterion-related validity Validity that is determined ing specific predictions based on general principles,
by relating performance on a test to performance on observations, or experiences.
another criterion (e.g., a second test or measure);
includes concurrent and predictive validity. dependent variable The change or difference in a
behavior or characteristic that occurs as a result of the
critical action research A type of action research independent or grouping variable. Also called effect,
in which the goal is liberating individuals through outcome, or posttest.
knowledge gathering. Also called emancipatory action
research. descriptive research Research that determines and
describes the way things are; involves collecting
critical ethnography A highly politicized form of eth- numerical data to test hypotheses or answer questions
nography written by a researcher to advocate against about the current subject of study. Also called survey
inequalities and domination of particular groups that research.
exist in society.
descriptive statistics Data analysis techniques that
Cronbach’s alpha (␣) The general formula for estimat- enable a researcher to describe many pieces of data
ing internal consistency based on a determination of meaningfully with numerical indices.
how all items on a test relate to all other items and to
the total test. The Kuder-Richardson 20 (KR-20) is a descriptive validity The degree to which qualitative
special case of the Cronbach’s alpha general formula. research is factually accurate.

cross-sectional survey A survey in which data are col- design A general strategy or plan for conducting a
lected from selected individuals in a single time period. research study; indicates the basic structure and goals
Compare longitudinal survey. of the study.

cross-validation Validation of a prediction equation developmental survey A study concerned with behav-
with at least one group other than the group on which ior variables that differentiate individuals at different
it was developed; results in the removal from the equa- levels of age, growth, or maturation.
tion of variables no longer found to be related to the
criterion measure. diagnostic test A type of achievement test that yields
scores for multiple areas of achievement to facilitate
culture The set of attitudes, values, concepts, beliefs identification of a student’s weak and strong areas.
and practices shared by members of a group; a central
construct in ethnographic research. dialectic action research spiral A four-step process
for conducting action research, including identifying
curvilinear relation A relation in which an increase an area of focus, data collection, data analysis and
in one variable is associated with a corresponding interpretation, and action planning.
increase in another variable to a point at which a
further increase in the first variable results in a corre- differential selection of subjects Selection of subjects
sponding decrease in the other variable (or vice versa); who have differences at the start of a study that may at
represented graphically as a curve. least partially account for differences found on a post-
test; a threat to internal validity.
data (sing. datum) Pieces of information.
direct replication Replication of a study by the same
data analysis An attempt by a researcher to investigator, with the same subjects or with different
summarize data, collected for a study, in a depend- subjects, in a specific setting.
able and accurate manner. In qualitative research,
data analysis usually involves coding and finding directional hypothesis A research hypothesis that
patterns or themes in narrative data. Compare data states the expected direction of the relation or differ-
interpretation. ence between variables.

data interpretation An attempt by a researcher to find ecological validity See external validity.
meaning in the data collected for a study. Compare
data analysis. educational research The formal, systematic applica-
tion of the scientific method to the study of educational
problems.

626 GLOSSARY

environmental variable A variable in the setting face validity The degree to which a test appears to
of a study (e.g., learning materials) that may cause measure what it claims to measure.
unwanted differences between groups.
factorial analysis of variance A statistical technique
equivalence The degree to which two similar forms that allows the researcher to determine the effects of
of a test produce similar scores from a single group of independent or grouping variables and control vari-
test takers. Also called equivalent-forms reliability or ables on the dependent variable both separately and in
alternate-forms reliability. combination. It is the appropriate statistical analysis if
a study is based on a factorial design and investigates
equivalent-forms reliability See equivalence. two or more independent or grouping variables and
the interactions between them; yields a separate F ratio
ethnographic case study A form of ethnography that for each variable and one for each interaction.
focuses on describing the activities of a specific group
and the shared patterns of behavior it develops over time. factorial design Any experimental design that involves
two or more independent or grouping variables, at
ethnographic research The study of the cultural pat- least one of which is manipulated, to study the effects
terns and perspectives of participants in their natural of the variables individually and in interaction with
setting; a form of qualitative research. Also called each other.
ethnography.
Family Educational Rights and Privacy Act of
ethnography Ethnographic research; also, the narrative 1974 Federal law that protects the privacy of student
produced to summarize the results of such research. educational records. Also called Buckley Amendment.

ethnomethodolgy A qualitative approach to studying field notes Qualitative research material gathered,
how participants make sense of everyday activities and recorded, and compiled, usually on-site, during the
act in a social way. course of a study.

evaluation research The systematic process of collect- field-oriented research See qualitative research.
ing and analyzing data on the quality, effectiveness,
merit, or value of programs, products, or practices for fieldwork Qualitative data collection; involves spend-
the purpose of making decisions about those programs, ing considerable time in the setting under study,
products, or practices. immersing oneself in this setting, and collecting as
much relevant information as possible as unobtrusively
evaluative validity The degree to which a qualitative as possible.
researcher is able to present data objectively, without
being evaluative or judgmental. formative evaluation Evaluation whose function is to
form and improve a program or product under devel-
experimental group A group of participants in a opment so that weaknesses that can be remedied
research study who typically receive the new treatment during implementation.
under investigation.
generalizability The applicability of research findings
experimental research Research in which at least one to settings and contexts different from the one in which
independent variable is manipulated, other relevant they were obtained.
variables are controlled, and the effect on one or more
dependent variables is observed. grading on the curve See norm-referenced scoring.

experimental variable See independent variable. grounded theory A qualitative approach in which the
researcher focuses on how an individually derived
experimenter bias A situation in which a researcher’s theory about a phenomenon is grounded in the data
expectations of study results contribute to producing in a particular setting.
the outcome.
halo effect The phenomenon whereby initial impres-
experimenter effects Threats to the external validity sions concerning an individual (e.g., positive or nega-
of an experiment caused by the researcher’s uninten- tive) affect subsequent measurements.
tional or intentional influences on participants or on
study procedures. haphazard sampling See convenience sampling.

ex post facto research See causal–comparative Hawthorne effect A type of reactive arrangement
research. resulting from the subjects’ knowledge that they are
involved in an experiment or their feelings that they
external observation See nonparticipant observation. are in some way receiving special attention.

external validity The degree to which results are gen- historical research A qualitative approach in which
eralizable or applicable to groups and environments the researcher focuses on collecting and evaluating
outside the experimental setting. Also called ecological data to understand and interpret past events.
validity.
history Any event occurring during a study that is
F ratio A computation used in analysis of variance to not part of the experimental treatment but may affect
determine whether variances among sample means are
significantly different.

GLOSSARY 627

performance on the dependent variable; a threat to item validity The degree to which test items are
internal validity. relevant to the measurement of the intended content
area.
hypothesis An explanation for the occurrence of cer-
tain behaviors, phenomena, or events; a prediction of John Henry effect The phenomenon in which mem-
research findings. bers of a control group who feel threatened or chal-
lenged by being in competition with an experimental
independent variable A behavior or characteristic group outdo themselves and perform way beyond
under the control of the researcher and believed to what would normally be expected. Also called com-
influence some other behavior or characteristic. Also pensatory rivalry.
called experimental variable, manipulated variable,
cause, or treatment. judgment sampling See purposive sampling.

inductive hypothesis A generalization based on Kuder-Richardson 20 (KR-20) See Cronbach’s alpha.
observation.
Likert scale An instrument on which individuals
inductive reasoning Reasoning that involves develop- respond to a series of statements by indicating whether
ing generalizations based on observations of a limited they strongly agree (SA), agree (A), are undecided
number of related events or experiences. (U), disagree (D), or strongly disagree (SD) with each
statement.
inferential statistics Data analysis techniques for
determining how likely it is that results obtained from limitation An aspect of a study that the researcher
a sample or samples are the same results that would knows may negatively affect the results or generaliz-
have been obtained for the entire population. ability of the results but over which the researcher has
no control.
instrument In educational research, a test or other tool
used to collect data. linear relation A relation in which an increase (or
decrease) in one variable is associated with a corre-
instrumentation Unreliability in measuring instru- sponding increase (or decrease) in another variable;
ments that may result in invalid assessment of partici- represented graphically as a straight line.
pants’ performance.
longitudinal survey A survey in which data are col-
interaction A situation in which different values of the lected at two or more times to measure changes or
independent or grouping variable are differentially growth over time. Compare cross-sectional survey.
effective depending on the level of a second (e.g.,
control) variable. matching A technique for equating sample groups on
one or more variables, resulting in each member of one
interjudge reliability The consistency of two or more group having a direct counterpart in another group.
independent scorers, raters, or observers.
maturation Physical, intellectual, and emotional changes
internal validity The degree to which observed differ- that naturally occur within subjects over a period of
ences on the dependent variable are a direct result of time; poses a threat to internal validity because changes
manipulation of the independent variable, not some may affect subjects’ performance on a measure of the
other variable. dependent variable.

interpretive research Collective, generic term for qual- mean The arithmetic average of a set of scores.
itative research approaches.
measurement The process of quantifying or scoring
interpretive validity The degree to which a qualitative performance on an assessment instrument.
researcher attributes the appropriate meaning to the
behavior or words of the participants in the study and measurement scale A system for organizing data so
therefore captures the participants’ perspective. that data may be inspected, analyzed, and interpreted.

interval scale A measurement scale that classifies and measures of central tendency Indices that represent
ranks subjects, is based on predetermined equal inter- the typical or average score for a group of scores.
vals, but does not have a true zero point.
measures of variability Indices that indicate how
intervening variable A variable (e.g., anxiety) that spread out the scores are in a distribution.
intervenes between or alters the relation between an
independent variable and a dependent variable but median The midpoint in a distribution; 50% of the
that cannot be directly observed or controlled. scores are above the median and 50% are below.

interview An oral, in-person question-and-answer ses- meta-analysis A statistical approach to summarizing
sion between a researcher and an individual respon- the results of many quantitative studies that address
dent; a purposeful interaction in which one person is basically the same problem.
trying to obtain information from the other.
mixed methods research designs Research designs
intrajudge reliability The consistency of one indi- that include both quantitative and qualitative data in
vidual’s scoring, rating, or observing over time. a single study.

628 GLOSSARY

mode The score that is attained by more subjects in a naturalistic research See qualitative research.
group than any other score.
negatively skewed distribution A distribution with
mortality A reduction in the number of research partic- more extreme scores at the lower end than at the upper,
ipants that occurs over time as individuals drop out of or higher, end.
a study; poses a threat to internal validity because sub-
jects who drop out of a study may share a characteristic nominal scale A measurement scale that classifies per-
and their absence may therefore have a significant sons or objects into two or more categories. A person can
effect on the results of the study. Also called attrition. be in only one category, and members of a category have
a common set of characteristics. Variables measured on a
multi-element baseline design See alternating treat- nominal scale are called nominal or categorical variables.
ments design.
nondirectional hypothesis A research hypothesis
multi-element manipulation design See alternating that states simply that a relation or difference exists
treatments design. between variables.

multiple comparisons Procedures used following nonequivalent control group design A quasi-
application of analysis of variance to determine which experimental design involving at least two groups, both
means are significantly different from which other of which are pretested; one group receives the experi-
means. Also called post hoc comparisons. mental treatment, and both groups are posttested.

multiple prediction equation See multiple regression nonparametric test A test of significance appropriate
equation. when the data are measured on an ordinal or nominal
scale, when a parametric assumption has been greatly vio-
multiple regression equation A prediction equation lated, or when the nature of the distribution is not known.
using two or more variables that individually predict
a criterion to make a more accurate prediction. Also nonparticipant observation Observation in which the
called multiple prediction equation. observer is not directly involved in the situation being
observed; that is, the observer does not intentionally
multiple schedule design See alternating treatments interact with or affect the object of the observation.
design. Also called external observation.

multiple time-series design A variation of the time- nonprobability sampling The process of selecting a
series design that involves the addition of a control sample using a technique that does not permit the
group to the basic design. researcher to specify the probability, or chance, that
each member of a population will be selected for the
multiple-baseline design A single-subject design in sample. Also called nonrandom sampling.
which baseline data are collected on several behaviors
for one subject, one behavior for several subjects, or one nonrandom sampling See nonprobability sampling.
behavior and one subject in several settings. Treatment
is applied systematically over a period of time to each norm-referenced scoring A scoring approach in which
behavior (or each subject or setting) one at a time until all an individual’s performance on an assessment is com-
behaviors (or subjects or settings) are under treatment. pared to the performance of others. Also called grading
on the curve.
multiple-treatment interference Phenomenon that
occurs when carryover effects from an earlier treat- novelty effect The increased interest, motivation, or
ment make it difficult to assess the effectiveness of a participation participants develop simply because
later treatment; a threat to external validity. they are doing something different; a type of reactive
arrangement.
narrative analysis In narrative research, the develop-
ment of a narrative or story that focuses on particular null hypothesis A hypothesis stating that there is no
knowledge about how or why an outcome occurred. relation (or difference) between variables and that any
Compare analysis of narrative. relation/difference found will be due to chance; i.e.,
the result of sampling error.
narrative research The study of how different humans
experience the world around them; involves a meth- observer bias The phenomenon whereby an observer
odology that allows people to tell the stories of their does not observe objectively and accurately, thus pro-
“storied lives.” ducing invalid observations.

National Research Act of 1974 Act that led to the observer effect The phenomenon whereby persons
establishment of federal regulations governing the pro- being observed behave atypically simply because
tection of human subjects in research; mandates that they are being observed, thus producing invalid
activities involving human participants be reviewed observations.
and approved by an authorized group before execu-
tion of the research. one-group pretest–posttest design A pre-experimental
design involving one group that is pretested, exposed
naturalistic inquiry See qualitative research. to a treatment, and posttested.

GLOSSARY 629

one-shot case study A pre-experimental design involv- post hoc comparisons See multiple comparisons.
ing one group that is exposed to a treatment and then
posttested. posttest-only control group design A true experimen-
tal design involving at least two randomly formed
one-way analysis of variance See simple analysis of groups; one group receives a new or unusual treat-
variance. ment, and both groups are posttested.

ordinal scale A measurement scale that classifies power The ability of a significance test to identify a
persons or objects and ranks them in terms of the true research finding (i.e., there’s really a difference,
degree to which they possess a characteristic of and the statistical test shows a significant difference),
interest. allowing the experimenter to reject a null hypothesis
that is false.
organismic variable A characteristic of a subject or
organism (e.g., sex) that cannot be directly controlled practical action research A type of action research
but can be controlled for. that emphasizes a how-to approach and has a less
philosophical bent than critical action research.
parameter A numerical index describing the behavior
of a population. prediction study An attempt to determine which of a
number of variables are most highly related to a crite-
parametric test A test of significance appropriate when rion variable, a complex variable to be predicted.
the data represent an interval or ratio scale of measure-
ment and other assumptions have been met. predictive validity The degree to which a test is able
to predict how well an individual will do in a future
participant effects See reactive arrangements. situation; a form of criterion-related validity.

participant observation Observation in which the predictor In a prediction study or analysis of concur-
observer becomes a part of and a participant in the rent or predictive validity, the variable on which the
situation being observed. prediction is based.

participant variable A variable on which partici- pretest–posttest control group design A true experi-
pants in different groups in a study may differ (e.g., mental design that involves at least two randomly
intelligence). formed groups; both groups are pretested, one group
receives a new or unusual treatment, and both groups
Pearson r A measure of correlation appropriate when are posttested.
both variables are expressed as continuous (i.e.,
ratio or interval) data; it takes into account every pretest sensitization See testing.
score and produces a coefficient between Ϫ1.00 and
ϩ1.00. pretest-treatment interaction Phenomenon that occurs
when subjects respond or react differently to a treat-
percentile rank A measure of relative position indicat- ment because they have been pretested; a threat to
ing the percentage of scores that fall at or below a external validity.
given score.
primary source Firsthand information, such as the tes-
performance assessment A type of assessment that timony of an eyewitness, an original document, a relic,
emphasizes a respondent’s performance of a process or a description of a study written by the person who
or creation of a product. Also called authentic assess- conducted it.
ment or alternative assessment.
probability sampling The process of selecting a
phenomenology A qualitative approach in which the sample using a sampling technique that permits the
researcher focuses on capturing the experience of an researcher to specify the probability, or chance, that
activity or concept from participants’ perspectives. each member of a defined population will be selected
for the sample.
pilot study A small-scale trial of a study conducted
before the full-scale study to identify problems with problem statement See topic statement.
the research plan.
projective test An instrument that includes ambigu-
placebo effect Any beneficial effect caused by a per- ous stimuli. The test taker’s responses to the stimuli
son’s expectations about a treatment rather than the are interpreted as projections of his or her feelings or
treatment itself. personality.

population General term for the larger group from which prospective causal–comparative research A variation
a sample is selected or the group to which the researcher of the basic approach to causal–comparative research;
would like to generalize the results of the study. Compare involves starting with the causes and investigating
target population and accessible population. effects.

positively skewed distribution A distribution in purposive sampling The process of selecting a sample
which there are more extreme scores at the upper, or that is believed to be representative of a given popula-
higher, end than at the lower end. tion. Also called judgment sampling.

630 GLOSSARY

qualitative research The collection, analysis, and reliability The degree to which a test (or qualita-
interpretation of comprehensive narrative and visual tive research data) consistently measures whatever it
data to gain insights into a particular phenomenon of measures.
interest. Sometimes called naturalistic research, natu-
ralistic inquiry, or field-oriented research. replication A repetition of a study using different
subjects or retesting its hypothesis.
qualitative sampling The process of selecting a small
number of individuals for a study in such a way that research The formal, systematic application of the
the selected individuals can help the researcher under- scientific method to the study of problems.
stand the phenomenon under investigation.
research and development (R&D) An extensive pro-
quantitative research The collection of numerical cess of researching consumer needs and then devel-
data to explain, predict and/or control phenomena oping products specifically designed to fulfill those
of interest. needs; R&D efforts in education focus on creating
effective products for use in schools.
quartile deviation One half of the difference between
the upper quartile (the 75th percentile) and the lower research hypothesis A statement of the expected rela-
quartile (the 25th percentile) in a distribution. tion or difference between two variables.

questionnaire A written collection of self-report ques- research plan A detailed description of a proposed
tions to be answered by a selected group of research study designed to investigate a given problem.
participants.
response set The tendency of an assessed individual to
quota sampling The process of selecting a sample respond in a particular way to a variety of instruments,
based on required, exact numbers (i.e., quotas) of such as when a respondent repeatedly answers as he
persons of varying characteristics. or she believes the researcher desires even when such
answers do not reflect the respondent’s true feelings;
random sampling The process of selecting individuals also, the tendency of an observer to rate the majority
for a sample on a completely chance basis. of observees the same regardless of the observees’
behavior.
range The difference between the highest and lowest
score in a distribution. restorying A process, unique to narrative research, in
which a researcher gathers stories, analyzes them for
rating scale A measurement instrument used to deter- key elements, and then synthesizes them into a coher-
mine a respondent’s attitude toward self, others, activi- ent story with a chronological sequence.
ties, institutions, or situations.
retrospective causal–comparative research The basic
ratio scale A measurement scale that classifies subjects, approach to causal–comparative research; involves
ranks them, is based on predetermined equal intervals, starting with effects and investigating causes.
and has a true zero point.
review of related literature The systematic identifica-
raw score The numerical calculation of the number tion, location, and analysis of documents containing
or point value of items answered correctly on an information related to a research problem; also, the
assessment. written component of a research plan or report that
discusses the reviewed documents.
reactive arrangements Threats to the external
validity of a study associated with the way in which sample A number of individuals, items, or events
a study is conducted and the feelings and attitudes selected from a population for a study, preferably in
of the subjects involved. Also called participant such a way that they represent the larger group from
effects. which they were selected.

realist ethnography A form of ethnography written sample survey Research in which information about
with an objective style and using common categories a population is inferred based on the responses of a
(e.g., “family life”) for cultural description, analysis, sample selected from that population.
and interpretation.
sampling The process of selecting a number of indi-
reasoning The process of using logical thought to viduals (i.e., a sample) from a population, preferably in
reach a conclusion. such a way that the selected individuals represent the
larger group from which they were selected.
refereed journal A journal in which articles are
reviewed by a panel of experts in the field and are thus sampling bias Systematic sampling error; two major
seen as more scholarly and trustworthy than articles sources of sampling bias are samples including only
from nonrefereed or popular journals. volunteers and sampling based on available groups.

relationship study An attempt to gain insight into the sampling error Expected, chance variation in vari-
variables, or factors, that are related to a complex vari- ables that occurs when a sample is selected from a
able, such as academic achievement, motivation, or population.
self-concept.

GLOSSARY 631

sampling validity The degree to which a test samples single-subject experimental designs Designs applied
the total content area of interest. when the sample size is one; used to study the behav-
ior change that an individual or group exhibits as a
Scheffé test A conservative multiple comparison tech- result of some intervention or treatment. Also called
nique appropriate for making any and all pairwise single-case experimental designs.
comparisons involving a set of means.
single-variable design Any experimental design that
scientific method An orderly process that entails rec- involves only one independent variable, which is
ognition and definition of a problem, formulation of manipulated.
hypotheses, collection of data, and statement of con-
clusions regarding confirmation or disconfirmation of single-variable rule An important principle of single-
the hypotheses. subject research that only one variable should be
manipulated at a time.
secondary source Secondhand information, such as a
brief description of a study written by someone other skewed distribution A nonsymmetrical distribution in
than the person who conducted it. which there are more extreme scores at one end of the
distribution than the other.
selection–maturation interaction Phenomenon that
occurs when already-formed groups are included in Solomon four-group design A true experimental
a study and one group profits more (or less) from design that involves random assignment of subjects
treatment or has an initial advantage (or disadvantage) to one of four groups; two groups are pretested, and
because of maturation factors; a threat to internal valid- two are not; one of the pretested groups and one of
ity. Selection may also interact with factors such as the unpretested groups receive the experimental treat-
history and testing. ment; and all four groups are tested again.

selection–treatment interaction Phenomenon that Spearman rho A measure of correlation appropriate
occurs when nonrepresentative groups are included in when the data for at least one variable is expressed as
a study and the results of the study apply only to the rank or ordinal data; it produces a coefficient between
groups involved and are not representative of the treat- Ϫ1.00 and ϩ1.00.
ment effect in the population; a threat to external validity.
specificity of variables Refers to the fact that a
self-referenced scoring A scoring approach in which given study is conducted with a specific kind of
an individual’s repeated performances on a single subject, using specific measuring instruments, at a
assessment are compared over time. specific time, and under a specific set of circum-
stances. These factors affect the generalizability of
semantic differential scale An instrument that requires the results.
an individual to indicate his or her attitude about a
topic (e.g., property taxes) by selecting a position on a split-half reliability A measure of internal consistency
continuum that ranges from one bipolar adjective (e.g., that involves dividing a test into two equivalent halves
fair) to another (e.g., unfair). and correlating the scores on the two halves.

shared variance See common variance. stability The degree to which scores on a test are consis-
tent, or stable, over time. Also called test–retest reliability.
shrinkage The tendency of a prediction equation to
become less accurate when used with a group other standard deviation A measure of variability that is
than the one on which the equation was originally stable and takes into account every score in a distri-
developed. bution. Calculated as the square root of the variance,
or amount of spread among test scores, it is the most
simple analysis of variance (ANOVA) A parametric frequently used statistical index of variability.
test of significance used to test for a difference between
two or more means at a selected probability level. Also standard error of the mean The standard deviation
called one-way analysis of variance. of sample means; indicates by how much one sample
mean can be expected to differ from the means of
simple random sampling The process of selecting a other samples from the same population.
sample in such a way that all individuals in the defined
population have an equal and independent chance of standard error of measurement An estimate of how
selection for the sample. often one can expect errors of a given size in an indi-
vidual’s test score.
simultaneous replication Replication that involves a
number of subjects with the same problem, at the same standard score A derived score that expresses how far
location, at the same time. a given raw score is from some reference point, typi-
cally the mean, in terms of standard deviation units.
simultaneous treatment design See alternating treat-
ments design. standardized test A test that is administered, scored,
and interpreted in the same way no matter where or
single-case experimental designs See single-subject when it is given.
experimental designs.