.

0 (hodnocen0 x )

BK

1st ed.

College Station : Stata Press, 2012

xxviii, 558 s. : il. ; 24 cm

ISBN 978-1-59718-107-5 (brož.) ISBN !1-59718-107-2 (chyb.)

Obsahuje bibliografii na s. [545]-547 a rejstříky

000246903

Contents // List of tables xv // List of figures xvii // Preface xxvii // Acknowledgments xxix // 1 Introduction 1 // 1.1 Overview of the book... 1 // 1.2 Getting the most out of this book... 3 // 1.3 Downloading the example datasets and programs... 4 // 1.4 The GSS dataset... 4 // 1.4.1 Income... 5 // 1.4.2 Age... 6 // 1.4.3 Education... 10 // 1.4.4 Gender... 12 // 1.5 The pain datasets... 12 // 1.6 The optimism datasets... 12 // 1.7 The school datasets... 13 // 1.8 The sleep datasets... 13 // 1 Continuous predictors 15 // 2 Continuous predictors: Linear 17 // 2.1 Chapter overview... 17 // 2.2 Simple linear regression ... 17 // 2.2.1 Computing predicted means using the margins command . . 20 // 2.2.2 Graphing predicted means using the marginsplot command 22 // 2.3 Multiple regression... 25 // vi Contents // 2.3.1 Computing adjusted means using the margins command . . 26 // 2.3.2 Some technical details about adjusted means... 28 // 2.3.3 Graphing adjusted means using the marginsplot command . 29 // 2.4 Checking for nonlinearity graphically... 30 // 2.4.1 Using scatterplots to check for nonlinearity... 31 // 2.4.2 Checking for nonlinearity using residuals... 31 // 2.4.3 Checking for nonlinearity using locally weighted smoother . 33 // 2.4.4 Graphing outcome mean at each level of predictor... 34 // 2.4.5 Summary ... 37 // 2.5 Checking for nonlinearity analytically ... 37 // 2.5.1 Adding power terms ... 38 // 2.5.2 Using factor variables... 39 // 2.6 Summary... 43 // 3 Continuous

predictors: Polynomials 45 // 3.1 Chapter overview... 45 // 3.2 Quadratic (squared) terms... 45 // 3.2.1 Overview... 45 // 3.2.2 Examples ... 49 // 3.3 Cubic (third power) terms... 55 // 3.3.1 Overview... 55 // 3.3.2 Examples ... 56 // 3.4 Fractional polynomial regression ... 62 // 3.4.1 Overview... 62 // 3.4.2 Example using fractional polynomial regression... 66 // 3.5 Main effects with polynomial terms... 75 // 3.6 Summary... 77 // 4 Continuous predictors: Piecewise models 79 // 4.1 Chapter overview... 79 // 4.2 Introduction to piecewise regression models... 80 // 4.3 Piecewise with one known knot... 82 // Contents v“ // 4.3.1 Overview... 82 // 4.3.2 Examples using the GSS... 83 // 4.4 Piecewise with two known knots ... 91 // 4.4.1 Overview... 91 // 4.4.2 Examples using the GSS... 91 // 4.5 Piecewise with one knot and one jump... 96 // 4.5.1 Overview... 96 // 4.5.2 Examples using the GSS... 97 // 4.6 Piecewise with two knots and two jumps... 102 // 4.6.1 Overview... 102 // 4.6.2 Examples using the GSS... 102 // 4.7 Piecewise with an unknown knot... 109 // 4.8 Piecewise model with multiple unknown knots... 113 // 4.9 Piecewise models and the marginsplot command ... 120 // 4.10 Automating graphs of piecewise models ... 123 // 4.11 Summary... 126 // 5 Continuous by continuous interactions 127 // 5.1 Chapter overview... 127 // 5.2 Linear by linear interactions... 127 // 5.2.1 Overview... 127 // 5.2.2 Example using GSS data... 132 // 5.2.3 Interpreting the interaction in terms

of age... 133 // 5.2.4 Interpreting the interaction in terms of education... 135 // 5.2.5 Interpreting the interaction in terms of age slope... 137 // 5.2.6 Interpreting the interaction in terms of the educ slope . . . 138 // 5.3 Linear by quadratic interactions... 140 // 5.3.1 Overview... 140 // 5.3.2 Example using GSS data... 143 // 5.4 Summary... 148 // viii Contents // 6 Continuous by continuous by continuous interactions 149 // 6.1 Chapter overview... 149 // 6.2 Overview ... 149 // 6.3 Examples using the GSS data... 154 // 6.3.1 A model without a three-way interaction... 154 // 6.3.2 A three-way interaction model... 158 // 6.4 Summary... 164 // II Categorical predictors 165 // 7 Categorical predictors 167 // 7.1 Chapter overview... 167 // 7.2 Comparing two groups using a t test... 168 // 7.3 More groups and more predictors... 169 // 7.4 Overview of contrast operators... 175 // 7.5 Compare each group against a reference group... 176 // 7.5.1 Selecting a specific contrast... 177 // 7.5.2 Selecting a different reference group... 178 // 7.5.3 Selecting a contrast and reference group... 179 // 7.6 Compare each group against the grand mean ... 179 // 7.6.1 Selecting a specific contrast... 181 // 7.7 Compare adjacent means... 182 // 7.7.1 Reverse adjacent contrasts... 185 // 7.7.2 Selecting a specific contrast... 186 // 7.8 Comparing the mean of subsequent or previous levels... 187 // 7.8.1 Comparing the mean of previous levels... 191 // 7.8.2 Selecting a specific contrast... 192

// 7.9 Polynomial contrasts... 193 // 7.10 Custom contrasts... 195 // 7.11 Weighted contrasts... 198 // 7.12 Pairwise comparisons... 200 // Contents 1X // 7.13 Interpreting confidence intervals... 202 // 7.14 Testing categorical variables using regression ... 205 // 7.15 Summary...208 // 8 Categorical by categorical interactions 209 // 8.1 Chapter overview...209 // 8.2 Two by two models: Example 1... 211 // 8.2.1 Simple effects... 215 // 8.2.2 Estimating the size of the interaction... 216 // 8.2.3 More about interaction... 217 // 8.2.4 Summary ... 218 // 8.3 Two by three models... 218 // 8.3.1 Example 2... 218 // 8.3.2 Example 3... 223 // 8.3.3 Summary ... 228 // 8.4 Three by three models: Example 4... 228 // 8.4.1 Simple effects... 230 // 8.4.2 Simple contrasts... 231 // 8.4.3 Partial interaction ... 233 // 8.4.4 Interaction contrasts... 234 // 8.4.5 Summary ...236 // 8.5 Unbalanced designs... 236 // 8.6 Main effects with interactions: anova versus regress... 241 // 8.7 Interpreting confidence intervals... 244 // 8.8 Summary... 246 // 9 Categorical by categorical by categorical interactions 249 // 9.1 Chapter overview...249 // 9.2 Two by two by two models ... 250 // 9.2.1 Simple interactions by season... 252 // 9.2.2 Simple interactions by depression status... 253 // 9.2.3 Simple effects... 255 // x Contents // 9.3 Two by two by three models... 255 // 9.3.1 Simple interactions by depression status... 258 // 9.3.2 Simple partial interaction by depression status... 258 // 9.3.3

Simple contrasts... 260 // 9.3.4 Partial interactions... 260 // 9.4 Three by three by three models and beyond... 262 // 9.4.1 Partial interactions and interaction contrasts... 264 // 9.4.2 Simple interactions... 268 // 9.4.3 Simple effects and simple comparisons... 271 // 9.5 Summary... 272 // III Continuous and categorical predictors 273 // 10 Linear by categorical interactions 275 // 10.1 Chapter overview... 275 // 10.2 Linear and two-level categorical: No interaction... 275 // 10.2.1 Overview... 275 // 10.2.2 Examples using the GSS... 278 // 10.3 Linear by two-level categorical interactions...283 // 10.3.1 Overview...283 // 10.3.2 Examples using the GSS... 285 // 10.4 Linear by three-level categorical interactions... 290 // 10.4.1 Overview... 290 // 10.4.2 Examples using the GSS... 293 // 10.5 Summary... 299 // 11 Polynomial by categorical interactions 301 // 11.1 Chapter overview... 301 // 11.2 Quadratic by categorical interactions... 301 // 11.2.1 Overview... 302 // 11.2.2 Quadratic by two-level categorical... 305 // 11.2.3 Quadratic by three-level categorical... 312 // xi // 318 // 323 // 325 // 325 // 328 // 332 // 333 // 333 // 334 // 334 // 337 // 341 // 346 // 347 // 348 // 349 // 350 // 351 // 354 // 356 // 356 // 358 // 360 // 361 // 363 // 364 // 365 // 365 // 366 // 366 // Contents // 11.3 Cubic by categorical interactions... // 11.4 Summary... // 12 Piecewise by categorical interactions // 12.1 Chapter overview... // 12.2 One knot and one jump... // 12.2.1 Comparing

slopes across gender... // 12.2.2 Comparing slopes across education... // 12.2.3 Difference in differences of slopes... // 12.2.4 Comparing changes in intercepts ... // 12.2.5 Computing and comparing adjusted means . . // 12.2.6 Graphing adjusted means ... // 12.3 Two knots and two jumps... // 12.3.1 Comparing slopes across gender... // 12.3.2 Comparing slopes across education... // 12.3.3 Difference in differences of slopes... // 12.3.4 Comparing changes in intercepts by gender . // 12.3.5 Comparing changes in intercepts by education // 12.3.6 Computing and comparing adjusted means . . // 12.3.7 Graphing adjusted means ... // 12.4 Comparing coding schemes ... // 12.4.1 Coding scheme #1... // 12.4.2 Coding scheme #2... // 12.4.3 Coding scheme #3... // 12.4.4 Coding scheme #4... // 12.4.5 Choosing coding schemes... // 12.5 Summary... // 13 Continuous by continuous by categorical interactions // 13.1 Chapter overview... // 13.2 Linear by linear by categorical interactions... // 13.2.1 Fitting separate models for males and females // xii Contents // 13.2.2 Fitting a combined model for males and females...368 // 13.2.3 Interpreting the interaction focusing in the age slope ... 370 // 13.2.4 Interpreting the interaction focusing on the educ slope . . . 372 // 13.2.5 Estimating and comparing adjusted means by gender ... 374 // 13.3 Linear by quadratic by categorical interactions ...376 // 13.3.1 Fitting separate models for males and females...376 // 13.3.2 Fitting a common model for

males and females...378 // 13.3.3 Interpreting the interaction ...379 // 13.3.4 Estimating and comparing adjusted means by gender ... 380 // 13.4 Summary...382 // 14 Continuous by categorical by categorical interactions 383 // 14.1 Chapter overview...383 // 14.2 Simple effects of gender on the age slope...387 // 14.3 Simple effects of education on the age slope...388 // 14.4 Simple contrasts on education for the age slope...389 // 14.5 Partial interaction on education for the age slope...389 // 14.6 Summary...390 // IV Beyond ordinary linear regression 391 // 15 Multilevel models 393 // 15.1 Chapter overview...393 // 15.2 Example 1: Continuous by continuous interaction...394 // 15.3 Example 2: Continuous by categorical interaction...397 // 15.4 Example 3: Categorical by continuous interaction...401 // 15.5 Example 4: Categorical by categorical interaction...404 // 15.6 Summary...408 // 16 Time as a continuous predictor 411 // 16.1 Chapter overview...411 // 16.2 Example 1: Linear effect of time ...412 // 16.3 Example 2: Linear effect of time by a categorical predictor...416 // Contents xiii // 16.4 Example 3: Piecewise modeling of time... 421 // 16.5 Example 4: Piecewise effects of time by a categorical predictor . . . 426 // 16.5.1 Baseline slopes ...430 // 16.5.2 Change in slopes: Treatment versus baseline... 431 // 16.5.3 Jump at treatment...432 // 16.5.4 Comparisons among groups... 433 // 16.6 Summary... 434 // 17 Time as a categorical predictor 437 // 17.1 Chapter overview...437

// 17.2 Example 1: Time treated as a categorical variable... 438 // 17.3 Example 2: Time (categorical) by two groups...443 // 17.4 Example 3: Time (categorical) by three groups...447 // 17.5 Comparing models with different residual covariance structures . . . 452 // 17.6 Summary... 454 // 18 Nonlinear models 455 // 18.1 Chapter overview...455 // 18.2 Binary logistic regression... 456 // 18.2.1 A logistic model with one categorical predictor ...456 // 18.2.2 A logistic model with one continuous predictor ...463 // 18.2.3 A logistic model with covariates...465 // 18.3 Multinomial logistic regression ...470 // 18.4 Ordinal logistic regression... 475 // 18.5 Poisson regression... 478 // 18.6 More applications of nonlinear models...481 // 18.6.1 Categorical by categorical interaction...481 // 18.6.2 Categorical by continuous interaction...487 // 18.6.3 Piecewise modeling...492 // 18.7 Summary...498 // 19 Complex survey data 499 // xiv Contents // V Appendices 505 // A The margins command 507 // A.l The prediet() and expression() options... 507 // A.2 The at() option... 510 // A.3 Margins with factor variables... 513 // A.4 Margins with factor variables and the at() option... 517 // A.5 The dydx() and related options... 519 // В The marginsplot command 523 // С The contrast command 535 // D The pwcompare command 539 // References 545 // Author index 549 // Subject index 551