Elsevier S & T

Handbook of Longitudinal Research: Design, Measurement, and Analysis

Menard, Scott

In stock
No reviews
85.250 KD inc. VAT
License
Table of contents
  • Table of Contentsv
  • List of Contributorsix
  • Prefacexi
  • Part I Longitudinal Research Design1
  • Chapter 1 Introduction: Longitudinal research design and analysis3
  • 1 Longitudinal and cross-sectional designs for research3
  • 2 Designs for longitudinal research4
  • 3 Measurement issues in longitudinal research7
  • 4 Descriptive and causal analysis in longitudinal research8
  • 5 Description and measurement of qualitative change9
  • 6 Timing of qualitative change: event history analysis9
  • 7 Panel analysis, structural equation models, and multilevel models10
  • 8 Time series analysis and deterministic dynamic models11
  • 9 Conclusion11
  • References12
  • Chapter 2 Using national census data to study change13
  • 1 Introduction13
  • 2 Official uses of census information14
  • 3 Public and research use of census information14
  • 4 The census as a source for longitudinal analysis15
  • 5 Data availability15
  • 6 Aggregate and microdata15
  • 7 Questions20
  • 8 Uses of census data in research23
  • 9 The potential of longitudinal analysis of census data26
  • 10 Historical context and the politics of numbers27
  • 11 A final note29
  • References30
  • Chapter 3 Repeated cross-sectional research: the general social surveys33
  • 1 Introduction33
  • 2 Organization33
  • 3 Data collection: 1972–200433
  • 4 Publications by the user community41
  • 5 Teaching and other uses42
  • 6 Contributions to knowledge42
  • 7 Summary45
  • References46
  • Chapter 4 Structuring the National Crime Victim Survey for use in longitudinal analysis49
  • 1 Introduction49
  • 2 NCVS procedures49
  • 3 Individual-level longitudinal analyses using the NCVS50
  • 4 Example: Prediction of violent crime victimization59
  • 5 Summary and discussion63
  • Glossary64
  • References65
  • Chapter 5 The Millennium Cohort Study and mature national birth cohorts in Britain67
  • 1 Introduction67
  • 2 The heritage of birth cohort studies in Britain71
  • 3 The ESRC Millennium Cohort Study75
  • 4 Findings and scope for analysis of the Millennium Cohort81
  • 5 Conclusion82
  • Glossary83
  • References83
  • Chapter 6 Retrospective longitudinal research: the German Life History Study85
  • 1 Introduction and overview85
  • 2 Origins, goals and institutional contexts of the German Life History Study86
  • 3 Surveys and methods: sampling, data collection, data editing88
  • 4 Autobiographical memory and retrospective measurement96
  • 5 Substantive areas and major findings101
  • 6 Data access and documentation103
  • Acknowledgements103
  • Glossary103
  • References104
  • Part II Measurement Issues in Longitudinal Research107
  • Chapter 7 Respondent recall109
  • 1 Introduction109
  • 2 Respondent recall – issues of memory109
  • 3 Respondent recall – issues in longitudinal research design112
  • 4 Research evidence114
  • 5 Research techniques for improving respondent recall117
  • 6 Conclusion119
  • Glossary120
  • References120
  • Chapter 8 A review and summary of studies on panel conditioning123
  • 1 Introduction123
  • 2 Theoretical and analytic principles123
  • 3 Conditioning and changes in behavior125
  • 4 Conditioning and changes in the process for reporting behaviors126
  • 5 Conditioning and reports of attitudes, opinions and subjective phenomena129
  • 6 Summary and discussion132
  • References136
  • Chapter 9 Reliability issues in longitudinal research139
  • 1 Introduction139
  • 2 Reliability issues in longitudinal research139
  • 3 A framework for examining structural stability in longitudinal research141
  • 4 Regression to the mean146
  • 5 Unreliability of change scores and the regression fallacy148
  • 6 Concluding remarks150
  • References150
  • Chapter 10 Orderly change in a stable world: The antisocial trait as a chimera153
  • 1 Introduction153
  • 2 Stable but changing155
  • 3 Two developmental models156
  • 4 Analyses of qualitative shifts160
  • 5 The trait as a chimera163
  • 6 Implications164
  • Acknowledgments164
  • References164
  • Chapter 11 Minimizing panel attrition167
  • 1 Introduction167
  • 2 Longitudinal survey design and attrition168
  • 3 The process of attrition and techniques for maximizing response173
  • 4 The use of incentives to minimize attrition179
  • 5 Conclusion and best practice guidelines181
  • References182
  • Chapter 12 Nonignorable nonresponse in longitudinal studies185
  • 1 Introduction185
  • 2 MAR, pattern mixture and selection models186
  • 3 Empirical application: methods190
  • 4 Empirical applications: results191
  • 5 Discussion195
  • References195
  • Part III Descriptive and Causal Analysis in Longitudinal Research197
  • Chapter 13 Graphical techniques for exploratory and confirmatory analyses of longitudinal data199
  • 1 Introduction199
  • 2 Graphical exploration of longitudinal data200
  • 3 Graphical model-checking based on residuals204
  • 4 Conclusion215
  • Software216
  • Acknowledgements216
  • References216
  • Chapter 14 Separating age, period, and cohort effects in developmental and historical research219
  • 1 Age and period as alternative dimensions of time219
  • 2 Age, period, and cohort as explanatory variables220
  • 3 Cohort as a unit of analysis221
  • 4 Illustration of the dummy variable regression analysis of age, period, and cohort effects223
  • 5 Period effects: Changes over time226
  • 6 Age effects: life cycle and developmental changes227
  • 7 Conclusion229
  • Author’s note230
  • References230
  • Chapter 15 An introduction to pooling cross-sectional and time series data233
  • 1 Introduction233
  • 2 Three pooling problems233
  • 3 Fixed effects or random effects: three considerations234
  • 4 Estimation issues in fixed effects models236
  • 5 A practical example: welfare spending and crime239
  • 6 Simple extensions244
  • 7 Summary and additional readings247
  • References247
  • Chapter 16 Dynamic models and cross-sectional data: the consequences of dynamic misspecification249
  • 1 Introduction249
  • 2 General dynamic linear structural equation model250
  • 3 Quasi-dynamic model251
  • 4 Autocorrelated model251
  • 5 Dynamic autocorrelated model252
  • 6 A First-order dynamic model254
  • 7 Conclusion256
  • References257
  • Chapter 17 Causal analysis with nonexperimental panel data259
  • 1 Introduction259
  • 2 Causal analysis with panel data259
  • 3 Qualitative outcomes260
  • 4 Quantitative (interval-level) outcomes263
  • 5 Independent cross-sections276
  • 6 Software277
  • References277
  • Chapter 18 Causal inference in longitudinal experimental research279
  • 1 Introduction279
  • 2 Experimental research with only one follow-up measurement279
  • 3 Experimental research with more than one follow-up measurement283
  • 4 General recommendation292
  • References292
  • Part IV Description and Measurement of Qualitative Change295
  • Chapter 19 Analyzing longitudinal qualitative observational data297
  • 1 Analyzing longitudinal qualitative observational data297
  • 2 Final comments309
  • Glossary310
  • References310
  • Chapter 20 Configural frequency analysis of longitudinal data313
  • 1 Introduction313
  • 2 CFA—a tutorial313
  • 3 CFA of longitudinal data319
  • 4 CFA of symmetry patterns329
  • 5 Discussion330
  • References331
  • Chapter 21 Analysis of longitudinal categorical data using optimal scaling techniques333
  • 1 Introduction333
  • 2 Optimal scaling334
  • 3 Analyzing longitudinal data using optimal scaling techniques: two strategies342
  • 4 Example348
  • 5 Extensions353
  • 6 Software354
  • 7 Concluding remarks354
  • References355
  • Chapter 22 An introduction to latent class analysis357
  • 1 Introduction357
  • 2 Model for LCA358
  • 3 Model fit359
  • 4 Model comparisons361
  • 5 Unconstrained LCA362
  • 6 Multiple groups LCA365
  • 7 Scaling models367
  • 8 Covariate LCA368
  • 9 Software notes370
  • References370
  • Chapter 23 Latent class models in longitudinal research373
  • 1 Introduction373
  • 2 The mixture latent Markov model373
  • 3 The most important special cases376
  • 4 Application to NYS data379
  • 5 Discussion381
  • Appendix A: Baum-Welch algorithm for the mixture latent Markov model381
  • Appendix B: Examples of Latent GOLD syntax files383
  • References384
  • Part V Timing of Qualitative Change: Event History Analysis387
  • Chapter 24 Nonparametric methods for event history data: descriptive measures389
  • 1 Introduction389
  • 2 Single spell data with censoring390
  • 3 Single spell data with competing risks392
  • 4 Multistate data393
  • 5 Recurrent event data397
  • 6 Current status data on recurrent events398
  • 7 Backward recurrent times401
  • 8 Summary402
  • References402
  • Chapter 25 The Cox proportional hazards model, diagnostics, and extensions405
  • 1 Introduction405
  • 2 Cox proportional hazards model406
  • 3 Cox model residuals407
  • 4 Covariate functional form408
  • 5 Proportional hazards assumption410
  • 6 Other diagnostics412
  • 7 Interpreting a Cox model414
  • 8 Cox modeling extensions and sources of dependence415
  • 9 Conclusion418
  • References418
  • Chapter 26 Parametric event history analysis: an application to the analysis of recidivism421
  • 1 Introduction421
  • 2 Problems of conventional methods in the analysis of event history data: recidivism as an example422
  • 3 Parametric versus nonparametric event history methods423
  • 4 Multivariate prediction of survival time: an example of log-normal and log-logistic event history427
  • References438
  • Chapter 27 Discrete-time survival analysis: predicting whether, and if so when, an event occurs441
  • 1 Introduction441
  • 2 Measuring time and recording event occurrence443
  • 3 Descriptive analysis of discrete-time survival data444
  • 4 Modeling event occurrence as a function of predictors451
  • 5 Extensions of the basic discrete-time hazard model459
  • 6 Is survival analysis really necessary?461
  • Glossary462
  • References462
  • Part VI Panel Analysis, Structural Equation Models, and Multilevel Models465
  • Chapter 28 Generalized estimating equations for longitudinal panel analysis467
  • 1 Introduction467
  • 2 Generalized linear models467
  • 3 The independence model468
  • 4 Subject-specific (SS) versus population-averaged (PA) models469
  • 5 Estimating the working correlation matrix470
  • References474
  • Chapter 29 Linear panel analysis475
  • 1 Introduction475
  • 2 Unobserved heterogeneity models for linear panel analysis478
  • 3 Dynamic panel analysis486
  • 4 Structural equation panel models487
  • 5 Dynamic panel models with unobserved heterogeneity499
  • 6 Conclusion501
  • Acknowledgement502
  • Data and software502
  • References502
  • Chapter 30 Panel analysis with logistic regression505
  • 1 Measuring change in categorical dependent variables506
  • 2 Logistic regression for conditional and unconditional change in two-wave panel models508
  • 3 The subject-specific model for a two-wave panel511
  • 4 Estimation of the conditional logistic regression model512
  • 5 The fixed effects model using conditional logistic regression513
  • 6 Unconditional logistic regression for the unconditional change model514
  • 7 Logistic regression for the conditional change model517
  • 8 Extensions to polytomous dependent variables519
  • 9 Multiwave logistic regression panel models519
  • 10 Conclusion521
  • Software521
  • References521
  • Chapter 31 Latent growth curve models523
  • Author notes544
  • References544
  • Chapter 32 Multilevel growth curve analysis for quantitative outcomes545
  • 1 Introduction545
  • 2 Research design and data management546
  • 3 Building the multilevel growth model548
  • 4 Conclusion562
  • Software562
  • Glossary563
  • References563
  • Chapter 33 Multilevel analysis with categorical outcomes565
  • 1 Specifying the relationship between the categorical dependent variable and time566
  • 2 Multilevel logistic regression models for repeated measures data568
  • 3 Multilevel logistic regression for prevalence of marijuana use569
  • 4 The population averaged model for prevalence of marijuana use571
  • 5 The unit-specific model for prevalence of marijuana use572
  • 6 Extensions and contrasts574
  • 7 Conclusion: multilevel logistic regression for longitudinal data analysis575
  • Software575
  • References576
  • Part VII Time Series Analysis and Deterministic Dynamic Models577
  • Chapter 34 A brief introduction to time series analysis579
  • 1 Introduction579
  • 2 Describing or modeling the outcome as a function of time580
  • 3 Describing or modeling the outcome as a function of present and past random shocks583
  • 4 Describing or modeling the outcome as a function of past values of the outcome (plus at)584
  • 5 The ARIMA(p,d,q) model585
  • 6 Example: IBM stock prices586
  • 7 Example: homicides in three midwestern states589
  • 8 Extensions to the simple univariate model592
  • 9 Forecasting597
  • 10 Conclusion598
  • Software599
  • Bibliographic note600
  • References600
  • Chapter 35 Spectral analysis601
  • 1 Introduction601
  • 2 A simple periodic model and harmonic analysis602
  • 3 Periodogram analysis603
  • 4 Tests for hidden periodic components606
  • 5 The spectrum of time series and its estimation609
  • 6 Relationships between two times series and cross-spectrum615
  • 7 Some mathematical detail618
  • References619
  • Chapter 36 Time-series techniques for repeated cross-section data621
  • 1 The simple ordinary least squares (OLS) method621
  • 2 Autoregressive (maximum likelihood) models622
  • 3 The lagged endogenous variable OLS method623
  • 4 Box-Jenkins (ARIMA) methods624
  • 5 An application of different time series to the same set of data: or how different assumptions can629
  • 6 Which techniques? Assessing relative strengths and weaknesses632
  • 7 Conclusion635
  • Appendix: effects of differencing on two hypothetical time series636
  • References637
  • Chapter 37 Differential equation models for longitudinal data639
  • 1 Second order equations642
  • 2 Some methods for estimating parameters643
  • 3 Latent differential equations644
  • 4 Multivariate second order LDE648
  • 5 LDE model extensions650
  • 6 Limitations and recommendations650
  • 7 Conclusions651
  • Author note651
  • References651
  • Chapter 38 Nonlinear dynamics, chaos, and catastrophe theory653
  • 1 Nonlinear dynamics653
  • 2 Competition and cooperation656
  • 3 Chaos theory657
  • 4 Catastrophe theory660
  • 5 The future of nonlinear modeling in the social sciences663
  • Glossary663
  • References663
  • Index665
Book details
  • Vendor Elsevier S & T
  • SKU 9780123704818
  • ISBN-13 9780080554228
  • Author Menard, Scott
  • Category Social Science
  • Subject Statistics

Do you have questions about this book?

Ask an expert!

Description eBook delivery & access Reviews
Longitudinal research is a broad field in which substantial advances have been made over the past decade. Unlike many of the existing books that only address the analysis of information. The Handbook of Longitudinal Research covers design and measurement as well as the data analysis.

Designed for use by a wide-ranging audience, this Handbook not only includes perspective on the methodological and data analysis problems in longitudinal research but it also includes contributors' data sets that enable readers who lack sophisticated statistics skills to move from theories about longitudinal data into practice.

As the comprehensive reference, this Handbook has no direct competition as most books in this subject area are more narrowly specialized and are pitched at a high mathematical level.

*Contributors and subject areas are interdisciplinary to reach the broadest possible audience (i.e., psychology, epidemiology, and economics research fields)
*Summary material will be included for less sohisticated readers
*Extensive coverage is provided of traditional advanced topics