Health Measurement Scales : A practical guide to their development and Use

by Streiner, David L; Norman, Geoffrey R

• ISBN13: 9780199231881
• ISBN10: 0199231885
• Edition: 4th
• Format: Paperback
• Copyright: 2008-12-15
• Publisher: Oxford University Press

Summary

Clinicians and those in health sciences are frequently called upon to measure subjective states such as attitudes, feelings, quality of life, educational achievement and aptitude, and learning style in their patients. This fourth edition of Health Measurement Scales enables these groups, whooften have limited knowledge of statistics, to both develop scales to measure non-tangible health outcomes, and better evaluate and differentiate between existing tools. It covers how the individual items are developed; various biases that can affect responses (eg social desirability, yea-saying, framing); various response options; how to select the best items in the set; how to combine them into a scale; and then how to determine the reliability and validity of thescale. It concludes with a discussion of ethical issues that may be encountered, and guidelines for reporting the results of the scale development process. Appendices include a comprehensive guide to finding existing scales, and a brief introduction to exploratory and confirmatory factor analysis. It synthesizes the theory of scale construction with practical advice, making it the ultimate guide to how to develop and validate measurement scales that are to be used in the health sciences.

Author Biography

David Streiner attended the City College of New York, and then did his graduate work in clinical psychology at Syracuse University. In 1968, he joined the newly-formed Department of Psychiatry at McMaster University, and became the Chief Psychologist at the McMaster University Medical Centre. In 1980, he also became a member of the Department of Clinical Epidemiology and Biostatistics at McMaster, and was the Deputy Chair of CE&B for two years. He was one of the founding editors of Evidence-based Mental Health, and is currently editor of the Statistical Developments and Applications section of the Journal of Personality Assessment, as well as being on the editorial board of numerous other journals.
Geoff Norman attended the University of Manitoba as an undergraduate, graduating with an honours degree in physics in 1965. He did graduate work in nuclear physics, obtaining a PhD in 1970. At that point he began a career in health sciences education, and subsequently obtained an M.A. in educational psychology from Michigan State University in 1977. He joined the faculty at McMaster in 1977, and has remained at McMaster for the next three decades. He has won numerous awards in medical education, including the Hubbard Award of the National Board of Medical Examiners (US), and lifetime achievement awards from the Medical Council of Canada and the American Educational Research Association, among others. In 2001, he was awarded a Canada Research Chair. In 2007, he was elected to the Royal Society of Canada. He has published over 200 papers in education, epidemiology, psychiatry and physics, as well as authoring and editing several books.

Table of Contents

Introduction	p. 1
Basic concepts	p. 5
Searching the literature	p. 6
Critical review	p. 6
Empirical forms of validity	p. 9
The two traditions of assessment	p. 11
The reduction of measurement error	p. 14
Summary	p. 15
Devising the items	p. 17
The source of items	p. 18
Content validity	p. 23
Generic versus specific scales and the 'fidelity versus bandwidth' issue	p. 27
Translation	p. 29
Scaling responses	p. 37
Introduction	p. 37
Some basic concepts	p. 37
Categorical judgments	p. 38
Continuous judgments	p. 40
To rate or to rank	p. 66
Multidimensional scaling	p. 68
Selecting the items	p. 77
Interpretability	p. 77
Face validity	p. 82
Frequency of endorsement and discrimination	p. 83
Homogeneity of the items	p. 85
Multifactor inventories	p. 96
When homegeneity does not matter	p. 97
Putting it all together	p. 98
Biases in responding	p. 103
The differing perspectives	p. 103
Answering questions: the cognitive requirements	p. 104
Optimizing and satisficing	p. 108
Social desirability and faking good	p. 110
Deviation and faking bad	p. 115
Yea-saying or acquiescencne	p. 118
End-aversion, positive skew, and halo	p. 119
Framing	p. 122
Biases related to the measurement of change	p. 123
Estimates of the prior state-implicit theory of change	p. 125
Reconciling the two positions	p. 125
Proxy reporting	p. 126
Testing the items	p. 127
From items to scales	p. 135
Weighting the items	p. 135
Missing items	p. 139
Multiplicative composite scores	p. 140
Transforming the final score	p. 143
Percentiles	p. 144
Standard and standardized scores	p. 146
Normalized scores	p. 149
Age and sex norms	p. 149
Establishing cut points	p. 151
Methods based on characteristics of the distribution	p. 152
Methods based on judgment	p. 154
Absolute methods	p. 154
Receiver operating characteristics curves	p. 156
Summary	p. 163
Reliability	p. 167
Basic concepts	p. 167
Philosophical implications	p. 170
Terminology	p. 173
Defining reliability	p. 174
Other considerations in calculating the reliability of a test	p. 177
The observer nested within subject	p. 179
Multiple observations	p. 180
Other types of reliability	p. 182
Different forms of the reliability coefficient	p. 183
Kappa coefficient versus the ICC	p. 188
The method of Bland and Altman	p. 190
Issues of interpretation	p. 190
Improving reliability	p. 196
Standard error of the reliability coefficient and sample size	p. 198
Reliability generalization	p. 202
The average value of r and ¿	p. 203
The variance of the reliability estimates	p. 204
Combining estimates	p. 205
Factors affecting the reliability	p. 206
Summary	p. 207
Generalizability theory	p. 211
Generalizability theory fundamentals	p. 213
An Example	p. 214
The First Step-the ANOVA	p. 215
From ANOVA to G coefficients	p. 218
Relative vs. Absolute Error	p. 219
Equivalent for the nested design	p. 222
Generalizability of an average	p. 222
from G study to D study	p. 223
ANOVA for statisticians and ANOVA for psychometricians	p. 224
Confidence intervals for G coefficients	p. 225
The general rules to compute G coefficients	p. 226
Getting the computer to do it for you	p. 227
Some Common Examples	p. 228
Uses and abuses of G theory	p. 244
Summary	p. 245
Validity	p. 247
Why assess validity?	p. 247
Reliability and validity	p. 248
A history of the 'types' of validity	p. 249
Content validation	p. 252
Criterion validation	p. 254
Construct validation	p. 257
Construct validational studies	p. 258
Extreme groups	p. 261
Convergent and discriminant validation	p. 262
Consequential validation	p. 263
The multitrait-multimethod matrix	p. 264
Summary	p. 265
Responsiveness and sensitivity to change	p. 266
Validity and 'types of indices'	p. 267
Biases in validity assessment	p. 268
Unreliability of the criterion	p. 271
Changes in the sample	p. 273
Validity generalization	p. 274
Summary	p. 274
Measuring change	p. 277
Introduction	p. 277
The goal of measurement of change	p. 277
Why not measure change directly?	p. 278
Measures of association-reliability and sensitivity to change	p. 280
Difficulties with changes scores in experimental designs	p. 285
Change scores and quasi-experimental designs	p. 286
Measuring change using multiple observations: growth curves	p. 288
How much change is enough?	p. 293
Summary	p. 295
Item response theory	p. 299
Problems with classical test theory	p. 299
The introduction of item response theory	p. 301
Item characteristic curves	p. 302
The one-parameter model	p. 304
The two-and three-parameter models	p. 306
Polytomous models	p. 309
Item information	p. 312
Item fit	p. 313
Person fit	p. 315
Differential item functioning	p. 315
Unidimensionality and local independence	p. 316
The standard error of measurement	p. 320
Equating tests	p. 321
Sample size	p. 322
Mokken scaling	p. 323
Advantages	p. 324
Disadvantages	p. 326
Computer programs	p. 327
Methods of administration	p. 331
Face-to-face interviews	p. 331
Advantages	p. 331
Disadvantages	p. 332
Telephone questionnaires	p. 334
Random digit dialling	p. 336
Advantages	p. 337
Disadvantages	p. 338
Mailed questionnaires	p. 340
The necessity of persistence	p. 346
Computer-assisted administration	p. 348
Using e-mail and the Web	p. 351
Personal data assistants	p. 354
Reporting response rates	p. 356
Ethical considerations	p. 365
Reporting test results	p. 373
Standards for Educational and Psychological Testing	p. 374
The STARD initiative	p. 376
Summary	p. 379
Appendices
Further reading	p. 381
Where to find tests	p. 387
A (very) brief introduction to factor analysis	p. 409
Author Index	p. 415
Subject Index	p. 423
Table of Contents provided by Ingram. All Rights Reserved.