Practical multivariate analysis

Contents......Page 6
Preface......Page 12
 Virginia A. Clark, Ph.D.,......Page 16
I Preparation for Analysis......Page 18
  1.2 Examples of multivariate analyses......Page 20
  1.4 Multivariate analyses discussed in this book......Page 23
  1.5 Organization and content of the book......Page 26
  2.2 Defining statistical variables......Page 28
  2.3 Stevens’s classification of variables......Page 29
  2.4 How variables are used in data analysis......Page 31
  2.8 Problems......Page 32
  3.1 Processing data so they can be analyzed......Page 34
  3.2 Choice of a statistical package......Page 35
  3.3 Techniques for data entry......Page 36
  3.4 Organizing the data......Page 40
  3.5 Reproducible research and literate programming Reproducibility......Page 46
  3.6 Example: depression study......Page 48
  3.8 Problems......Page 50
  4.1 Introduction......Page 54
  4.2 Univariate data......Page 55
  4.3 Bivariate data......Page 62
  4.4 Multivariate data......Page 67
  4.5 Discussion of computer programs......Page 69
  4.6 What to watch out for......Page 71
  4.8 Problems......Page 73
  5.2 Common transformations......Page 76
  5.3 Selecting appropriate transformations......Page 79
  5.4 Assessing independence......Page 86
  5.6 Summary......Page 88
  5.7 Problems......Page 89
  6.2 Why selection is often difficult......Page 92
  6.3 Appropriate statistical measures......Page 93
  6.4 Selecting appropriate multivariate analyses......Page 96
  6.6 Problems......Page 97
II Regression Analysis......Page 102
  7.2 When are regression and correlation used?......Page 104
  7.3 Data example......Page 105
  7.4 Regression methods: fixed-X case......Page 106
  7.6 Interpretation: fixed-X case......Page 110
  7.7 Interpretation: variable-X case......Page 112
  7.8 Other available computer output......Page 115
  7.9 Robustness and transformations for regression......Page 120
  7.10 Other types of regression......Page 122
  7.11 Special applications of regression......Page 124
  7.13 What to watch out for......Page 127
  7.15 Problems......Page 129
  8.2 When are regression and correlation used?......Page 132
  8.3 Data example......Page 133
  8.4 Regression methods: fixed-......Page 134
  8.5 Regression and correlation: variable-......Page 136
  8.6 Interpretation: fixed-X case......Page 141
  8.7 Interpretation: variable-X case......Page 143
  8.8 Regression diagnostics and transformations......Page 145
  8.9 Other options in computer programs......Page 149
  8.10 Discussion of computer programs......Page 153
  8.12 Summary......Page 157
  8.13 Problems......Page 158
  9.2 When are variable selection methods used?......Page 162
  9.3 Data example......Page 164
  9.4 Criteria for variable selection......Page 166
  9.5 A general......Page 169
  9.6 Stepwise regression......Page 170
  9.7 Lasso regression......Page 176
  9.8 Discussion of computer programs......Page 180
  9.9 Discussion of strategies......Page 181
  9.10 What to watch out for......Page 183
  9.11 Summary......Page 184
  9.12 Problems......Page 185
  10.2 Missing values in regression analysis......Page 188
  10.3 Dummy variables......Page 194
  10.4 Constraints on parameters......Page 201
  10.5 Regression analysis with multicollinearity......Page 203
  10.6 Ridge regression......Page 204
  10.7 Summary......Page 207
  10.8 Problems......Page 208
  11.2 When is discriminant analysis used? Discriminant analysis......Page 212
  11.3 Data example......Page 213
  11.4 Basic concepts of classification......Page 214
  11.5 Theoretical background......Page 219
  11.6 Interpretation......Page 221
  11.7 Adjusting the dividing point......Page 224
  11.8 How good is the discrimination?......Page 226
  11.9 Testing variable contributions......Page 227
  11.11 Discussion of computer programs......Page 228
  11.12 What to watch out for......Page 229
  11.14 Problems......Page 231
  12.2 When is logistic regression used?......Page 234
  12.3 Data example......Page 235
  12.4 Basic concepts of logistic regression......Page 236
  12.5 Interpretation: categorical variables......Page 237
  12.6 Interpretation: continuous variables......Page 239
  12.7 Interpretation: interactions......Page 240
  12.8 Refining and evaluating logistic regression......Page 246
  12.9 Nominal and ordinal logistic regression......Page 255
  12.10 Applications of logistic regression......Page 260
  12.11 Poisson regression......Page 263
  12.13 What to watch out for......Page 266
  12.14 Summary......Page 268
  12.15 Problems......Page 269
  13.2 When is survival analysis used?......Page 272
  13.4 Survival functions......Page 273
  13.6 Comparing survival among groups......Page 279
  13.7 The log-linear regression model......Page 281
  13.8 The Cox regression model......Page 283
  13.9 Comparing regression models......Page 291
  13.11 What to watch out for......Page 293
  13.13 Problems......Page 295
  14.2 When is principal components analysis used?......Page 298
  14.4 Basic concepts......Page 299
  14.5 Interpretation......Page 302
  14.6 Other uses......Page 309
  14.8 What to watch out for......Page 311
  14.9 Summary......Page 312
  14.10 Problems......Page 313
  15.2 When is factor analysis used? Factor analysis......Page 314
  15.4 Basic concepts......Page 315
  15.5 Initial extraction: principal components......Page 317
  15.6 Initial extraction: iterated components......Page 320
  15.7 Factor rotations......Page 322
  15.8 Assigning factor scores......Page 326
  15.10 Discussion of computer programs......Page 327
  15.11 What to watch out for......Page 329
  15.12 Summary......Page 330
  15.13 Problems......Page 331
  16.2 When is cluster analysis used? Cluster analysis......Page 334
  16.4 Basic concepts: initial analysis......Page 335
  16.5 Analytical clustering techniques......Page 341
  16.6 Cluster analysis for financial data set......Page 345
  16.7 Discussion of computer programs......Page 350
  16.10 Problems......Page 353
  17.2 When is log-linear analysis used?......Page 356
  17.4 Notation and sample considerations......Page 358
  17.5 Tests and models for two-way tables......Page 360
  17.6 Example of a two-way table......Page 362
  17.7 Models for multiway tables......Page 364
  17.8 Exploratory model building......Page 367
  17.9 Assessing specific models......Page 371
  17.10 Sample size issues......Page 372
  17.11 The logit model......Page 373
  17.13 What to watch out for......Page 375
  17.14 Summary......Page 376
  17.15 Problems......Page 377
  18.2 When is correlated outcomes regression used?......Page 378
  18.3 Data examples......Page 379
  18.4 Basic concepts......Page 381
  18.5 Regression of clustered data with a continuous outcome......Page 386
  18.6 Regression of clustered data with a binary outcome......Page 390
  18.7 Regression of longitudinal data......Page 392
  18.8 Generalized estimating equations analysis of correlated data......Page 396
  18.9 Discussion of computer programs......Page 400
  18.10 What to watch out for......Page 402
  18.12 Problems......Page 403
 A.4 Financial performance cluster–analysis data......Page 406
 A.7 Parental HIV data......Page 407
 A.10 Mice data......Page 408
Bibliography......Page 410
Index......Page 428