Modern Psychometrics

John Rust is the founder of The Psychometrics Centre at the University of Cambridge, UK. He is a Senior Member of Darwin College, UK, and an Associate Fellow of the Leverhulme Centre for the Future of Intelligence, University of Cambridge, UK.Michal Kosinski is an associate professor of organizational behavior at Stanford Graduate School of Business, USA.David Stillwell is the academic director of the Psychometrics Centre at the University of Cambridge, UK. He is also a reader in computational social science at the Cambridge Judge Business School, UK.

"There is a robust science for predicting and explaining what people do in any area of life, and this remarkable book, by three leading scholars, will forever change the way you think about human behavior: a true masterpiece!" – Tomas Chamorro-Premuzic, Columbia University, USA and University College, UK."Measurement is the foundation of all science, and Psychology is no exception. So, with its authoritative, updated, and comprehensive coverage of psychometrics, this volume is set to become the go-to guide for any serious psychological scientist." – Sam Gosling, University of Texas, USA."The science of psychometrics is already changing our lives. For better or worse, it will shape our digital futures. This welcome new edition to the classic introduction to the field could hardly be more timely. " – Huw Price, University of Cambridge, UK.

• 1. The history and evolution of psychometric testingIntroductionWhat is psychometrics?Psychometrics in the 21st centuryHistory of assessmentChinese originsThe ability to learnThe nineteenth century Beginnings of psychometrics as a scienceIntelligence testingEugenics and the dark decades Psychometric testing of abilityThe dark ages come to an endAn abundance of abilities Tests of other psychological constructsPersonalityIntegrityInterestsMotivationValuesTemperamentAttitudeBelief Summary2. Constructing your own psychometric questionnaireThe purpose of the questionnaireMaking a blueprintWriting itemsAlternate-choice itemsMultiple-choice itemsRating-scale itemsAll questionnairesKnowledge-based questionnairesPerson-based questionnaires Designing the questionnairePiloting the questionnaireItem analysisFacilityDiscriminationDistractors Obtaining the reliabilityCronbach’s alphaSplit-half reliability Assessing validityFace validityContent validity Standardization3. The Psychometric principlesReliabilityTest-retest reliabilityParallel-forms reliabilitySplit-half reliabilityInterrater reliabilityInternal consistencyThe standard error of measurement (SEM)Comparing test reliabilitiesRestriction of range ValidityFace validityContent validityPredictive validityConcurrent validityConstruct validityDifferential validity StandardizationNorm referencingCriterion referencing EquivalenceDifferential item functioningMeasurement invarianceAdverse impact Summary4. Psychometric measurementTrue-score theoryIdentification of latent traits with factor analysisSpearman’s two-factor theoryVector algebra and factor rotationMoving into more dimensionsMultidimensional scaling Application of factor analysis to test constructionEigenvalues Identifying the number of factors to extract using the Kaiser criterion Identifying the number of factors to extract using the Cattell scree test Other techniques for identifying the number of factors to extract Factor rotation Rotation to simple structure Orthogonal rotation Oblique rotation Limitations of the classical factor-analystic approachCriticisms of psychometric measurement theoryThe Platonic true scorePsychological vs. physical true scoresFunctional assessment and competency testingMachine learning and the black box Summary5. Item response theory and computer adaptive testingIntroductionItem banksThe Rasch modelAssessment of educational standardsThe Birnbaum model The evolution of modern psychometricsComputer adaptive testingItem equatingPolytomous IRT An intuitive graphical description of item tesponse theoryLimitations of classical test theory A graphical Introduction to item response theoryThe logistic curve3PL-model: difficulty parameter3PL model: discrimination parameter3PL model: guessing parameterThe Fisher information functionThe test information function and its relationship to the standard error of measurementHow to score an IRT test Principles of computer adaptive testingSummary of item response theoryConfirmatory factor analysis6. Personality theoryTheories of personalityPsychoanalytic theoryHumanistic theorySocial learning theoryBehavioral geneticsType and trait theories Different approaches to personality assessment Self-report techniques and personality profilesReports by othersOnline digital footprintsSituational assessmentsProjective measuresObservations of behaviorTask performance methodsPolygraph methodsRepertory grids Sources and management of biasSelf-report techniques and personality profilesReports by othersOnline digital footprintsSituational assessmentsProjective measuresObservations of behaviorTask performance methodsPolygraph methodsRepertory grids Informal methods of personality assessmentState versus trait measuresIpsative scalingSpurious validity and the Barnum EffectSummary7. Personality assessment in the workplacePrediction of successful employment outcomesValidation of personality questionnaires previously used in employmentHistorical antecedents to the five-factor modelStability of the five-factor modelCross-cultural aspects of the five-factor modelScale independence and the role of facetsChallenges to scale construction for the five-factor modelImpression managementAcquiescenceResponse bias and factor structureDevelopment of the five OBPI personality scales Assessing counterproductive behavior at workThe impact of behaviorismPrepsychological theories of integrityModern integrity testingPsychiatry and the medical modelThe dysfunctional tendenciesThe dark triadAssessing integrity at workThe OBPI integrity scales Conclusion8. Employing digital footprints in psychometricsIntroductionTypes of digital footprintUsage logsLanguage dataMobile sensorsImages and audiovisual data Typical applications of digital footprints in psychometricsReplacing and complimenting traditional measuresNew contexts and new constructsPredicting future behaviorStudying human behaviorSupporting the development of traditional measures Advantages and challenges of employing digital footprints in psychometricsHigh ecological validityGreater detail and longitudeLess control over the assessment environmentGreater speed and unobtrusivenessLess privacy and controlNo anonymityBiasEnrichment of existing constructsDeveloping digital-footprint-based psychometric measuresCollecting digital footprints How much data is needed? Preparing digital footprints for analysisRespondent-footprint matrixData sparsity Reducing the dimensionality of the respondent-footprint matrixSingular value decompositionLatent Dirichlet allocation Building prediction models9. Psychometrics in the era of the intelligent machineHistory of computerization in psychometricsComputerized statisticsComputerized item banksComputerized item generationAutomated advice and report systems The evolution of AI in psychometricsExpert systemsNeural networks (machine learning)Parallel processingPredicting with statistics and machine learningExplainability Psychometrics in cyberspaceWhat and where is cyberspace?The medium is the message Moral development in AIKohlberg’s theory of moral developmentDo machines have morals?The laws of roboticsArtificial general intelligence Conclusion