Muutke küpsiste eelistusi

Detection Theory: A User's Guide 3rd edition [Pehme köide]

, (University of Massachusetts Amherst), (University of Auckland, New Zealand)
  • Formaat: Paperback / softback, 434 pages, kõrgus x laius: 254x178 mm, kaal: 916 g, 110 Tables, black and white; 130 Line drawings, black and white; 130 Illustrations, black and white
  • Ilmumisaeg: 28-Sep-2021
  • Kirjastus: Routledge
  • ISBN-10: 1138320854
  • ISBN-13: 9781138320857
Teised raamatud teemal:
  • Formaat: Paperback / softback, 434 pages, kõrgus x laius: 254x178 mm, kaal: 916 g, 110 Tables, black and white; 130 Line drawings, black and white; 130 Illustrations, black and white
  • Ilmumisaeg: 28-Sep-2021
  • Kirjastus: Routledge
  • ISBN-10: 1138320854
  • ISBN-13: 9781138320857
Teised raamatud teemal:

Detection Theory: A User’s Guide is an introduction to one of the most important tools for the analysis of data where choices must be made, and performance is not perfect. In these cases, detection theory can transform judgments about subjective experiences, such as perceptions and memories, into quantitative data ready for analysis and modeling.

For beginners, the first three chapters introduce measuring detection and discrimination, evaluating decision criteria, and the utility of receiver operating characteristics. Later chapters cover more advanced research paradigms including: complete tools for application, including flowcharts, tables, and software; student-friendly language; complete coverage of content area, including both one-dimensional and multidimensional models; integrated treatment of threshold and nonparametric approaches; an organized, tutorial level introduction to multidimensional detection theory; and popular discrimination paradigms presented as applications of multidimensional detection theory.

This modern summary of signal detection theory is both a self-contained reference work for users and a readable text for graduate students and researchers learning the material either in courses or on their own.

Arvustused

"The second edition of Detection Theory has been my invaluable companion for many years. It has always been in easy reach to answer my questions. Now that book will move to a place of honored retirement as I call on this new and improved third edition to guide me." -- Jeremy Wolfe, Brigham and Womens Hospital & Harvard Medical School, USA

"The great value of signal detection theory is that it protects you from the dangerous intuitions you will almost certainly otherwise have. After these erroneous intuitions are used to interpret data or build a theory, they will eventually be corrected by someone who knows the difference between d and . It would be better to avoid that fate, and the best way to do that is to carefully study this comprehensive handbook." -- John Wixted, University of California, San Diego, USA

"Signal detection theory was developed in the context of research in sensory psychology, but its impact quickly spread to many other areas, in part because the two previous editions of this book provided such a clear explanation of the theory along with a review of its many applications. This third edition of Detection Theory: A Users Guide has been thoroughly updated and will continue to be an invaluable reference and textbook." -- Walt Jesteadt, Boys Town National Research Hospital, USA

"More than anything else, this book has served as a signpost for my research career. Its that powerful; the tools that general." -- Caren Rotello, University of Massachusetts, Amherst, USA "The second edition of Detection Theory has been my invaluable companion for many years. It has always been in easy reach to answer my questions. Now that book will move to a place of honored retirement as I call on this new and improved third edition to guide me."

Jeremy Wolfe, Brigham and Womens Hospital & Harvard Medical School, USA

"The great value of signal detection theory is that it protects you from the dangerous intuitions you will almost certainly otherwise have. After these erroneous intuitions are used to interpret data or build a theory, they will eventually be corrected by someone who knows the difference between d and . It would be better to avoid that fate, and the best way to do that is to carefully study this comprehensive handbook."

John Wixted, University of California, San Diego, USA

"Signal detection theory was developed in the context of research in sensory psychology, but its impact quickly spread to many other areas, in part because the two previous editions of this book provided such a clear explanation of the theory along with a review of its many applications. This third edition of Detection Theory: A Users Guide has been thoroughly updated and will continue to be an invaluable reference and textbook."

Walt Jesteadt, Boys Town National Research Hospital, USA

"More than anything else, this book has served as a signpost for my research career. Its that powerful; the tools that general."

Caren Rotello, University of Massachusetts, Amherst, USA

Preface xiv
Introduction xvii
PART I Basic Detection Theory and One-Interval Designs
1(136)
1 The Yes-No Experiment: Sensitivity
3(24)
Understanding Yes-No Data
3(5)
Implied Receiver Operating Characteristics
8(6)
The Signal-Detection Model
14(3)
Calculational Methods
17(1)
Essay: The Provenance of Detection Theory
18(2)
Summary
20(1)
Computational Appendix
20(1)
Supplementary Material
21(1)
Problems
22(2)
References
24(3)
2 The Yes-No Experiment: Response Bias
27(27)
Two Examples
27(1)
Measuring Response Bias
28(4)
Alternative Measures of Bias
32(2)
Isomas Curves
34(1)
Experimental Manipulation of Bias
35(2)
Comparing the Bias Measures
37(5)
How Does the Participant Choose a Decision Rule?
42(2)
Calculating Hit and False-Alarm Rates from Parameters
44(1)
Variability of Decision Criteria
45(1)
Essay: On Human Decision-Making
45(1)
Summary
46(1)
Computational Appendix
47(1)
Supplementary Material
47(1)
Problems
48(3)
References
51(3)
3 Beyond Binary Responses: The Rating Experiment and Empirical
Receiver Operating Characteristics
54(1)
Design of Rating Experiments
54(1)
Receiver Operating Characteristic Analysis
55(2)
Relationship between Binary and Rating Responses
57(9)
ROC Analysis with Slopes Other Than 1
59
Estimating Bias
66(3)
Systematic Parameter Estimation and Methods of Calculation
69(2)
Alternative Ways to Generate ROCs
71(4)
Another Kind of ROC: Type 2
72
Essay: Are ROCs Necessary?
75(2)
Summary
77(1)
Computational Appendix
77(1)
Supplementary Material
78(1)
Problems
79(4)
References
83(2)
4 Classification Experiments for One-Dimensional Stimulus Sets
85(24)
Design of Classification Experiments
85(1)
Perceptual One-Dimensionality
85(2)
Two-Response Classification
87(9)
Experiments with More Than Two Responses
96(3)
Nonparametric Measures
99(1)
Comparing Classification and Discrimination
100(2)
Summary
102(1)
Problems
103(3)
References
106(3)
5 Threshold Models and Choice Theory
109(28)
Single High-Threshold Theory
110(3)
Low-Threshold Theory
113(2)
Double High-Threshold Theory
115(4)
Choke Theory
119(6)
Measures Based on Areas in ROC Space: Unintentional Applications of Choice Theory
125(3)
Nonparametric Analysis of Rating Data
128(1)
Essay: The Appeal of Discrete Models
128(2)
Summary
130(1)
Computational Appendix
131(1)
Problems
132(2)
References
134(3)
PART II Multidimensional Detection Theory and Multi-Interval Discrimination Designs
137(114)
6 Detection and Discrimination of Compound Stimuli: Tools for Multidimensional Detection Theory
139(19)
Distributions in One- and Two-Dimensional Spaces
140(5)
Some Characteristics of Two-Dimensional Spaces
145(3)
Compound Detection
148(6)
Inferring the Representation from Data
154(2)
Summary
156(1)
Problems
156(1)
References
157(1)
7 Comparison (Two-Distribution) Designs for Discrimination
158(26)
Two-Alternative Forced-Choice
158(13)
Yes-No Reminder Paradigm
171(2)
Two-Alternative Forced-Choice Reminder
173(2)
Data
175(2)
Essay: Psychophysical Comparisons and Comparison Designs
177(1)
Summary
177(1)
Computational Appendix
178(1)
Problems
178(3)
References
181(3)
8 Classification Designs: Attention and Interaction
184(22)
One-Dimensional Representations and Uncertainty
185(2)
Two-Dimensional Representations
187(4)
Two-Dimensional Models for Extrinsic Uncertain Detection
191(3)
Uncertain Simple and Compound Detection
194(2)
Selective- and Divided-Attention Tasks
196(3)
Attention Operating Characteristics
199(2)
Summary
201(1)
Problems
201(3)
References
204(2)
9 Classification Designs for Discrimination
206(25)
Same-Different
207(12)
ABX (Matching-to-Sampte)
219(5)
Oddity (Triangle Task)
224(2)
Summary
226(1)
Computational Appendix
226(1)
Problems
227(2)
References
229(2)
10 Identification of Multidimensional Objects and Multiple Observation Intervals
231(20)
Object Identification
231(3)
Interval Identification: m-Altemative Forced-Choice
234(3)
Comparisons among Discrimination Paradigms
237(3)
Simultaneous Detection and Identification
240(3)
Using Identification to Test for Perceptual Interaction
243(3)
Essay: How to Choose an Experimental Design
246(1)
Summary
247(1)
Problems
248(1)
References
249(2)
PART III Stimulus Factors
251(46)
11 Adaptive Methods for Estimating Empirical Thresholds
253(27)
Two Examples
254(1)
The Tracking Algorithm: Choices for the Adaptive Tester
255(1)
Psychometric Functions
255(15)
Evaluation of Tracking Algorithms
270(2)
Two More Choices: Discrimination Paradigm and the Issue of Slope
272(2)
Summary
274(1)
Problems
274(3)
References
277(3)
12 Components of Sensitivity
280(17)
Stimulus Determinants of d' in One Dimension
281(4)
Basic Processes in Multiple Dimensions
285(6)
Hierarchical Models
291(1)
Essay: Psychophysics versus Psychoacoustics (etc.)
292(1)
Summary
293(1)
Problems
293(2)
References
295(2)
PART IV Statistics
297(32)
13 Statistics and Detection Theory
299(30)
Hit and False-Alarm Rates
300(3)
Sensitivity and Bias Measures
303(12)
Sensitivity Estimates Based on Averaged Data
315(6)
Systematic Statistical Frameworks for Detection Theory
321(3)
Summary
324(1)
Computational Appendix
324(1)
Problems
325(2)
References
327(2)
Appendix 1 Elements of Probability and Statistics
329(11)
Probability
329(7)
Statistics
336(3)
Reference
339(1)
Appendix 2 Logarithms and Exponentials
340(2)
Appendix 3 Flowcharts to Sensitivity and Bias Calculations
342(5)
Chart 1 Guide to Subsequent Charts
342(1)
Chart 2 Yes-No Sensitivity
342(1)
Chart 3 Yes-No Response Bias
343(1)
Chart 4 Rating-Design Sensitivity
343(1)
Chart 5 Definitions of Multi-Interval Designs
344(1)
Chart 6 Multi-Interval Sensitivity
344(1)
Chart 7 Multi-Interval Bias
345(1)
Chart 8 Classification
345(1)
References
346(1)
Appendix 4 Some Useful Equations
347(8)
Yes-No (Equal-Variance Signal Detection Theory)
347(1)
Yes-No (Choice Theory)
348(1)
Yes-No (Unequal-Variance Signal Detection Theory)
349(1)
Threshold and "Nonparametric"
350(1)
One-Dimensional Classification
350(1)
Forced-Choice (Two-Alternative Forced-Choice)
351(1)
Forced-Choice (m-Altemative Forced-Choice)
352(1)
Reminder Paradigm
352(1)
Same-Different
352(1)
ABX
353(1)
Statistics
353(2)
Appendix 5 Tables
355(38)
A5.1 Normal Distribution (p to z)
356(1)
A5.2 Normal Distribution (z to p) Given z, Find Φ(z), the Proportion Less Than z
357(2)
A5.3 Values of d' for Same-Different (Independent-Observation Model) and ABX (Independent-Observation and Difference Models)
359(12)
A5.4 Values of d' for Same-Different (Difference Model)
371(13)
A5.5 Values of 6! for Oddity, Gaussian Model (M = Number of Intervals)
384(4)
A5.6 Values of p(c) given A' for Oddity (Difference and Independent-Observation Model, Normal), and form AFC
388(1)
A5.7 Values of d' for m-Interval Forced Choice or Identification
389(3)
References
392(1)
Appendix 6 Software for Detection Theory
393(2)
SDT Assistant
393(1)
Websites
394(1)
References
394(1)
Appendix 7 Solutions to Selected Problems
395(18)
Glossary 413(11)
Index 424
Michael J. Hautus is Head of the Psychophysics Laboratory in the School of Psychology at the University of Auckland, New Zealand. His research interests include quantitative assessment of the functioning of the auditory system, modeling auditory, visual, and flavor judgment, and modeling cognitive processes involved in judgment.

Neil A. Macmillan is a retired Professor of Psychology at Brooklyn College, USA. C. Douglas Creelman, deceased, was a Professor of Psychology at the University of Toronto, Canada. Both of them were privileged to study with founders of detection theory: Creelman with Wilson Tanner and John Swets at the University of Michigan, Macmillan with David Green and Duncan Luce at the University of Pennsylvania.