## Sequential analysis: a guide for behavioral researchers

Author: Gottman, John Mordechai ; Roy, Anup KumarPublisher: Cambridge University Press (CUP) 1990.Language: EnglishDescription: 275 p. : Graphs ; 24 cm.ISBN: 0521346657Type of document: BookBibliography/Index: Includes bibliographical references and indexItem type | Current location | Collection | Call number | Status | Date due | Barcode | Item holds |
---|---|---|---|---|---|---|---|

Europe Campus Main Collection |
HM251 .G68 1990
(Browse shelf) 001263053 |
Available | 001263053 |

Includes bibliographical references and index

Digitized

Sequential Analysis A Guide for Behavioral Researchers Contents Preface Reading this book quickly Part I: Introduction Chapter 1: Advertisement Chapter 2: History Chapter 3: The language of sequential analysis 3.1 The moving time window 3.2 Summary statistics 3.3 The base rate problem 3.4 The language of Markov chains 3.5 Markov models 3.6 Example 3.7 Higher-order Markov models 3.8 The odds ratio 3.9 Four indices of sequential connection 3.10 How children become friends 3.11 Discrete time semi-Markov models 3.12 Our overall plan Part II: Fitting the timetable Chapter 4: The order of the Markov chain 4.1 Shannon's approximations to English 4.2 Information 4.3 The plan of our discussion 4.4 Likelihood ratio chi-squared tests 4.5 Digram structure 35 35 37 37 38 40 3 9 15 16 16 17 18 19 20 21 24 25 30 30 31 xi xii 4.6 Contingency-style tables 4.7 Independence 4.8 Testing independence 4.9 Cellwise examination of contingency tables 4.10 Information theory 4.11 Reduction in uncertainty 4.12 Exercise 4.13 Use of the LRX2 to determine order 4.14 Order for specific sequences Appendix 4.1: Degrees of freedom for order of the Markov chain Appendix 4.2: LRX2 Chapter 5: Stationarity of the Markov chain 5.1 One dyad 5.2 Omnibus test for stationarity 5.3 Other reasons for dividing the data into segments 5.4 An alternative to the omnibus test Chapter 6: Homogeneity 6.1 Hirokawa (1980) 6.2 Sillars (1980) 6.3 Capella (1980) 6.4 Valentine and Fisher (1974) 6.5 Cline (1979) 6.6 Hawes and Foley (1973) 6.7 Lichtenberg and Hummel (1976) 6.8 Hawes and Foley (1976) 40 42 43 44 46 49 52 53 57 58 58 60 61 62 63 66 67 68 68 72 72 73 75 76 76 Chapter 7: Everyday computations of stationarity, order and homogeneity 77 7.1 The Arundale programs 77 7.2 Example 77 7.3 Stationarity 78 7.4 Order 80 7.5 Homogeneity 80 7.6 Homogeneity analyses as an opportunity for discovery 80 7.7 Setting alpha levels 83 Chapter 8: Sampling distributions 8.1 Binomial distribution 8.2 Poisson distribution 8.3 Negative binomial 8.4 Hypergeometric distribution 85 85 87 88 89 8.5 Multinomial distribution 8.6 Product multinomial distribution 8.7 Example Chapter 9: Lag sequential analysis 9.1 Deciding between z-scores: The type I error rate 9.2 Uses of lag sequential analysis 9.3 A new lag sequential analysis rule of thumb 9.4 Detecting cyclicity 9.5 Studying coalitions within groups 9.6 Examples 9.6.1 Ting-Toomey (1983) 9.6.2 Bakeman and Adamson (1983) 9.6.3 Margolin and Wampold (1981) 9.6.4 Cousins and Vincent (1983) 9.6.5 Revenstorf et al. (1981) 9.7 Independence assumption in computing z-scores Part III: The timetable and the contextual design Chapter 10: Log-linear models 10.1 Notation for log-linear models 10.2 Three-way classification 10.3 Playing with the notation 10.3.1 Case (1) 10.3.2 Case (2) 10.4 Hierarchical, non-hierarchical, and conditional nested models 10.5 Statistical tests 10.6 Getting expected counts 10.7 Model building and testing 10.8 Computing degrees of freedom 10.9 Model fitting step by step 10.10 Selecting a model by screening 10.11 Contrasts 10.12 The analysis of residuals 10.13 The homogeneity problem again Chapter 11: Log-linear models: review and examples 11.1 Model building and selection of categorical data models 11.2 Brown's measures of marginal and partial association 11.3 Standardized parameter estimates 11.4 Stepwise selection procedures 90 90 92 95 99 100 100 103 103 103 103 105 106 108 109 109 113 115 117 118 118 118 121 122 123 126 127 127 129 130 131 131 133 133 136 137 137 11.5 Examples 11.5.1 Brent and Sykes (1973) 11.5.2 Vuchinich (1984) 11.6 Nested hierarchical models 11.7 Worked example 11.7.1 Markov model omnibus test 11.7.2 Log-linear analyses Appendix 11.1: Likelihood ratio tests Appendix 11.2 Matrix formulation Appendix 11.3: The relationship between information theory and log-linear models (James T. Ringland) Appendix 11.4: Rationale for comparing models Chapter 12: A single case analysis of the timetable 12.1 A six-step procedure 12.2 Forming the timetable 12.3 Writing the models down 12.4 Preliminary consideration in comparing the models 12.5 Comparing models 12.5.1 Step 1: Markov model analysis 12.5.2 Step 2: Submodel fitting 12.5.3 Step 3: Residual examination and cell removal 12.5.4 Step 4: Check all reasonable submodels 12.5.5 Step 5: Check larger models 12.5.6 Step 6: Interpretation of the model Appendix 12.1: Freeman-Tukey deviates Chapter 13: Logit models and logistic regression 13.1 Introduction 13.2 Why we need the logit transformation 13.2.1 The difficulties of the standard regression model: "Linear probability model" 13.2.2 Transformation approaches 13.2.3 Probit transformation 13.2.4 Logit transformation 13.3 Logit analysis: grouping data across subjects within each cell 13.4 Logit analysis within grouping subjects: logistic regression 13.5 Polytomous variables: multiple choice models 13.6 Incomplete tables: problem of empty cells 13.7 Example 139 139 143 149 150 150 151 156 159 161 164 168 168 170 172 173 174 174 176 176 177 178 179 187 189 189 191 191 193 194 196 201 212 217 220 220 Appendix 13.1: The relationship between log-linear and logit models Appendix 13.2: Computer programs for data analysis Chapter 14: The problem of autocontingency and its solutions 14.1 The problem 14.2 Sackett's computational solution 14.3 The logit linear solution 14.3.1 Chi-squared test 143.2 Logit linear model 14.4 The Gardner-Hartmann correction 14.5 Untested suggestions 14.5.1 Binary time-sertes analysis solution 14.5.2 Controlling for autocontingency of more than one time lag Appendix 14.1: Sackett's computational correction Chapter 15: Recent advances: a brief overview 15.1 Introduction 15.2 Kraemer and Jacklin (1979); Mendoza and Graziano (1982); and lacobucci and Wasserman (1987) 15.3 Wampold and Margolin (1982) and Wampold (1984) 15.4 Dillon, Madden, and Kumar (1983) 15.5 Feick and Novak (1985) 15.6 Faraone and Dorfman (1987) 15.7 Budescu (1984) 15.8 Log-linear or logit-linear models? Chapter 16: A brief summary 16.1 The data 16.2 Forming the timetable: determining order and stationarity 16.3 Homogeneity: the decisions of how to best group subjects 16.4 Within-subject analyses 16.5 Pooting across subjects 16.6 Doing the minimum References Index 222 226 228 228 230 232 232 233 234 235 235 236 239 240 240 241 242 243 243 244 244 245 248 248 248 248 249 249 249 251 265

There are no comments for this item.