Jump to ContentJump to Main Navigation
Developing and Validating Rapid Assessment Instruments$

Neil Abell, David W. Springer, and Akihito Kamata

Print publication date: 2009

Print ISBN-13: 9780195333367

Published to Oxford Scholarship Online: September 2009

DOI: 10.1093/acprof:oso/9780195333367.001.0001

Show Summary Details
Page of

PRINTED FROM OXFORD SCHOLARSHIP ONLINE (www.oxfordscholarship.com). (c) Copyright Oxford University Press, 2018. All Rights Reserved. Under the terms of the licence agreement, an individual user may print out a PDF of a single chapter of a monograph in OSO for personal use (for details see www.oxfordscholarship.com/page/privacy-policy). Subscriber: null; date: 21 January 2019

(p.217) Index

(p.217) Index

Source:
Developing and Validating Rapid Assessment Instruments
Publisher:
Oxford University Press
Adjusted Bayesian information criterion (ABIC), 161, 169, 174
Adolescent Concerns Evaluation (ACE), 120, 122–124, 126
Akaike's information criterion (AIC), 161, 168–169, 174
Alpha-if-item-deleted, 89–91, 165, 187
Area under the curve (AUC), 127
Axioms of treatment, 7
Bayesian information criterion (BIC), 161, 168–169, 174
Bias
consequential interpretations, 20
cross-cultural, 194
developer's, 20, 102, 104
equivalence, 194
item, 195
method, 194
respondent's, 44
Burden, 37, 45, 66, 73–74, 183
Chi-square goodness-of-fit test statistic, 158–159
Classical measurement theory. See Classical test theory
Classical test theory, 11, 17, 81, 84
Clinical Measurement Package, 7
Clinical sample, 55–56, 120, 186
Coefficient alpha, 63, 66, 184, 187, 192
equation for, 87
internal consistency based on, 85–96
stratified, 92–94
Communality, 138, 139, 140, 145
Comparative Fit Index (CFI), 158–160, 168, 174. See also Nested vs. non-nested models
Concept, 25
Concept mapping, 25–27
Confirmatory factor analysis (CFA), 63, 133, 145–175, 184
with covariates, 169–172
(p.218) Confirmatory factor analysis (continued)
model fit, 156
multiple-group, 170, 172–175
in relation to item response theory (IRT), 177, 180
sample size, 64–65
violation of assumptions, 151
when to use, 181
Consistency, 71, 97, 100
over raters, 82
over time, 84–85
of scale scores, 13, 81, 83, 183, 187
Construct, 6, 35, 104, 183
conceptualization, 12, 41
item pool, 37
definition of, 10, 17
dimensionality, 38
representation, 42
scale items, 40
social relevance, 27
Construct validity. See Validity, evidence of
Content validity. See Validity, evidence of
Covariance, 85, 133
in confirmatory factor analysis, 147
data, 138, 158
error, 163, 171
implied, 138
between latent factors, 156, 158
matrix, 122, 139, 149, 150
in Comparative Fit Index, 159
predicted, 138
of the PSCS, 87–88, 92
reproduced, 158
in Standardized Root Mean Square Residual, 160
unique elements in, 148
weighted, 138
in nested vs. non-nested models, 168
for PSCS subscales, 93
Cross-cultural assessment, 193–197
Cutting scores, 78
Data collection package, 66
construct validity, 67
cost, 75–77
sequencing, 66, 70–73
Differential item functioning (DIF), 170–172, 175, 180
Dimensions, 38
Diversity, 193–197
Domain boundaries, 41–42
Domain sampling model, 41–43, 104
Domain scores, 121–123
Eigenvalue, 123, 135, 137
Equivalence
construct, 195
cross-cultural, 193
measurement unit, 195
scalar, 195
Error
correlated, 139, 162–164, 166, 168
measurement, 66, 79, 80, 96
random, 81
respondent, 76
score, 81
variance, 81, 84, 139, 147, 156–157
for the PSCS, 147, 149
Ethics, 31, 53, 193
Expert panels, 45, 58, 104–106, 185
content validity, 46, 106
quantitative ratings, 111
Exploratory factor analysis (EFA), 63, 133–145, 151, 184, 188
of the PSCS, 166
sample size, 64, 66
when to use, 181
(p.219) Face validity. See Validity, evidence of
Factor, 38, 40, 63, 64
Factor analytic models, 13, 131, 138, 140. See also CFA, EFA
equation for one factor model, 132
in relation to item response theory (IRT), 178
Factor axes, rotation of, 140–144
Factor extraction methods, 137
Factorial invariance, 14, 172, 173
Factor loadings, 144, 147, 149, 153, 184
definition of, 140
in modification indices, 162
in multiple-group CFA, 172
in multiple indicators multiple causes (MIMIC), 171
for the PSCS, 141–142, 165
in relation to item response theory (IRT), 178
Factor matrix, 141, 142, 143
Family Responsibility Scale (FRS), 21, 22, 39
Focus group, 27, 29–31, 185
Global score, 40, 90, 94
of the PSCS, 92, 114, 117
Heterogeneous, 57
HIV/AIDS Provider Stigma Inventory (HAPSI), 46, 105, 106, 108
Hypothesis, secondary or applied, 67, 74
Index, 10
Indivualized rating scales, 38
Information criteria, 168, 169, 173, 174. See also ABIC, AIC, BIC
Informed consent, 60–61, 66, 77, 185
Instrument design, 12, 15, 83
Internal consistency reliability. See Reliability
Inter-rater or interobserver reliability. See Reliability
Invariance
bilingual, 169
factorial, 175
differential item functioning (DIF), 170
multiple-group CFA, 172, 174
in relation to item response theory (IRT), 180
item, 175, 195, 197
measurement, 169
sample size, 62
Item difficulty, 86, 180
Item discrimination, 178, 179
Item response options, sensitivity, 50
Item-response theory (IRT), 14, 175–181
Item score, 132, 147–148, 156, 195
on Likert-type items, 176
in multiple indicators multiple causes (MIMIC), 170, 172
as variables in CFA, 151
Kaiser criterion, 135, 137, 184
Kuder-Richardson 20 (KR20), 86
Latent construct, 19
(p.220) Latent factors, 141, 147, 157
in exploratory factor analysis, 144
in factor analytic models, 132–133
in item response theory (IRT), 179
in modification indices, 163, 164
in multiple-group CFA, 173, 175
in multiple indicators multiple causes (MIMIC), 170
in nested vs. non-nested models, 168
Latent factors (continued)
in parameter estimation and interpretation, 151–153
in principal components analysis, 137
Latent traits, 13, 64, 131, 132
in multiple indicators multiple causes (MIMIC), 170
in relation to item response theory (IRT), 180
Latent variables, 13, 17, 64, 131–132, 145
Least square, 137–139
Likert-type category partitions, 47–50
Maximum likelihood, 137–139, 150, 158
Model fit, 65, 148, 156–162, 164–166
in multiple-group CFA, 173, 175
in nested vs. non-nested models, 168–169
Model identification, 148–150
just-identified, 148
overidentified, 148
underidentified, 148
Modification index, 153, 162–164, 178
in multiple indicators multiple causes (MIMIC), 171, 172, 178
in nested vs. non-nested models, 168
Mplus, 151, 158, 160, 171
in modification indices, 162
in multiple-group CFA, 173
in parameter interpretation, 153
in relation to item response theory (IRT), 178
Multiple indicators multiple causes (MIMIC), 169–172, 175, 180
Multivariate normality, 151
Negative predictive value (NPV), 123, 126
Nested vs. non-nested models, 168, 173
Nomological net, 116
Nonclinical samples, 56–58, 120, 186
Observable indicators, 17, 19, 35, 64
Observational measures, 35, 82
Observed score, 81, 84, 85, 95–96
Overburdening, 40
Overdetermination, 64
Parallel forms, 80, 84
Parental Self-Care Scale (PSCS)
CFA model for, 147
communality output for, 139
covariance matrices for, 93
description and original item pool of, 23–24
expert panel content validation for, 46
fit indices for, 169
reliability of, 90–94
scree plot for, 136
Pattern matrix, 142, 143
Population relevance, 57
Positive predictive value (PPV), 123, 126
Postcoding, 69–70
Practice effectiveness, 6
Precoding, 69–70
Principal axis factoring, 138–139
Principal components analysis, 137–138
Qualitative analysis, 25, 29, 30, 41, 107
Rapid assessment instruments (RAIs), 3, 37
Reactivity, 51–52, 66, 73–74
(p.221) Readability, 36, 66, 106
Reasonable, 43
Receiver operating characteristics (ROC), 125, 127
Reliability, 13, 63–64, 79, 165, 184
evidence of, 184, 187–188
for FRS, 89–90
how to estimate, 82–96
internal consistency, 43, 71, 82, 184, 188
and power analysis, 65–66
in relation to item response options, 50
and the Spearman-Brown prophecy formula, 37
inter-rater or interobserver, 82–83, 109, 184
of multidimensional scales, 90–94
in relation to validity coefficients, 115
standards of, 94–95
test-retest, 84–85, 184
theory of, 80–82
underestimation of, 92
of unidimensional scales, 89–90
variance, observed and true scores, 81–82
Research associates, 77, 187
Response options, 43, 47–50, 87, 194
and readability, 36
in relation to precoding and postcoding, 69
Response rate, 75
Reversed items, 43, 71
Root Mean Square Error of Approximation (RMSEA), 158–160
in multiple-group CFA, 174
in nested vs. non-nested models, 168
Rotation, 140–144. See also Factor axes
oblique, 140, 145
orthogonal, 140, 143, 145
promax, 140–141
varimax, 140, 143
Sample size, 62–65, 75, 100, 144–145, 186
in concept mapping, 26
effect on chi-square statistic, 158–159
effect on Mplus, 160
in item response theory (IRT), 177
Sampling
recruitment, 54, 59–62
violation of assumptions, 57
Scale, 3, 4, 10, 15
development of, 16–17
formats, 34
multidimensional, 38–40, 90–92, 120, 145, 183
and measurement error, 80
self-anchored, 38
standardized, 9, 124
unidimensional, 38–39, 90–92, 178, 183
and measurement error, 80
utility, 36, 183
Screening, 125–130
Scree plot, 135–137
Self-report, 17, 35, 85
Semantic differential, 47–51
Sensitivity, 123, 125–130
Simple structure, 141, 145–146, 150
in modification indices, 162
in multiple indicators multiple causes (MIMIC), 170
in parameter interpretation, 153
in the PSCS, 164
(p.222) Single-item indicators, 67, 113, 191
Skew, 57, 151
Social consequences, 20, 25
Social relevance, consequential interpretations, 20
Spearman-Brown prophecy formula, 37, 87
Specificity, 123, 125–130
Standard error of measurement (SEM), 13, 63, 95–96, 184, 188
in multiple indicators multiple causes (MIMIC), 172
Standardized Root Mean Square Residual, (SRMR), 158, 160, 162
in multiple-group CFA, 174
in nested vs. non-nested models, 168
Statistical Package for the Social Sciences (SPSS), 88, 92, 152
estimates using, 141, 142
and exploratory factor analysis, 134–135, 137
illustration on the PSCS, 138–139
Structural equation modeling, 17, 64, 151
in relation to item response theory (IRT), 177
Structure matrix, 142, 143
Test-retest reliability. See Reliability
Theoretical saturation, 41, 54, 64
Three-indicator rule, 149
Total score. See Global score
Translation, 193–197
True score, 81, 84, 86, 95–96
t-rule, 148
Tucker-Lewis Index, 158, 159, 160
in multiple-group CFA, 174
in nested vs. non-nested models, 168
Two-indicator rule, 149
Univariate normality, 121, 151
Unstandardized scales, 38
Validity, evidence of, 10, 13, 99–100, 184, 190–191
bilingual, 197–199
construct, 13, 63, 111–118, 130, 190
convergent, 99, 111, 112–115
discriminant, 99, 111, 115–118, 119
mean validity coefficient, 114
content, 43–45, 103–111
criterion, 118–125, 199
concurrent, 118
known-groups, 119–124
violation of assumptions, 121
known instruments, 124–125
predictive, 118
cut-off scores, 126–127, 129
false-negatives, 126
false-positives, 126–127
gold standard, 118, 124, 125, 128, 199
incremental, 200
translation, 197–199
types of evidence, 101
Vignettes, 58–59