이미지 검색을 사용해 보세요
검색창 이전화면 이전화면
최근 검색어
인기 검색어

가격
174,570
10 157,110
YES포인트?
7,860원 (5%) 마니아추가적립
5만원 이상 구매 시 2천원 추가 적립
결제혜택
최대 2,000원 즉시할인

이 분야의 이벤트

책소개

목차

Acronyms
Symbols
Useful R packages
Preface
I Introduction
1 Motivations for Statistical Models
1.1 Data and statistical models
1.2 Why linear models?
2 Ordinary Least Squares with a Univariate Covariate
2.1 Ordinary least squares with a univariate covariate
2.2 Final comments
2.3 Homework problems
II Ordinary Least Squares and Statistical Inference
3 Ordinary Least Squares with Multiple Covariates
3.1 The OLS formula
3.2 The geometry of OLS . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
3.3 The projection matrix from OLS . . . . . . . . . . . . . . . . . . . . . . . . 19
3.4 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20
4 Gauss–Markov Model and Gauss–Markov Theorem 25
4.1 Gauss–Markov model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25
4.2 Properties of the OLS estimator . . . . . . . . . . . . . . . . . . . . . . . . 26
4.3 Variance estimation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28
4.4 Gauss–Markov Theorem . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28
4.5 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31
5 Normal Linear Model: Inference and Prediction 35
5.1 Joint distribution of the OLS coefficient and variance estimator . . . . . . . 36
5.2 Pivotal quantities and statistical inference . . . . . . . . . . . . . . . . . . . 37
5.2.1 Scalar parameters . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37
5.2.2 Vector parameters . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38
5.3 Prediction based on pivotal quantities . . . . . . . . . . . . . . . . . . . . . 40
5.4 Examples . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41
5.4.1 Univariate regression . . . . . . . . . . . . . . . . . . . . . . . . . . . 41
5.4.2 Anscombe’s Quartet: the importance of graphical diagnostics . . . . 42
5.4.3 Multivariate regression . . . . . . . . . . . . . . . . . . . . . . . . . . 45
5.5 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 47
6 Asymptotic Inference in OLS: Eicker–Huber–White (EHW) robust standard
error 51
6.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 51
6.1.1 Numerical examples . . . . . . . . . . . . . . . . . . . . . . . . . . . 51
6.1.2 Goal of this chapter . . . . . . . . . . . . . . . . . . . . . . . . . . . 52
6.2 Consistency of OLS . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 54
6.3 Asymptotic Normality of the OLS estimator . . . . . . . . . . . . . . . . . . 55
6.4 Eicker–Huber–White standard error . . . . . . . . . . . . . . . . . . . . . . 56
6.4.1 Sandwich variance estimator . . . . . . . . . . . . . . . . . . . . . . 56
6.4.2 Other heteroskedasticity-consistent (HC) standard errors . . . . . . 58
6.4.3 Special case with homoskedasticity . . . . . . . . . . . . . . . . . . . 59
6.5 Examples . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 60
6.5.1 LaLonde experimental data . . . . . . . . . . . . . . . . . . . . . . . 60
6.5.2 Data from King and Roberts (2015) . . . . . . . . . . . . . . . . . . 60
6.5.3 Boston housing data . . . . . . . . . . . . . . . . . . . . . . . . . . . 62
6.6 Final remarks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 64
6.7 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 64
III Interpretation of Ordinary Least Squares Based on Partial
Regressions 67
7 Frisch–Waugh–Lovell Theorem 69
7.1 Long and short regressions . . . . . . . . . . . . . . . . . . . . . . . . . . . . 69
7.2 FWL Theorem for the regression coefficients . . . . . . . . . . . . . . . . . . 70
7.3 FWL Theorem for standard errors . . . . . . . . . . . . . . . . . . . . . . . 72
7.4 Gram–Schmidt orthogonalization, QR decomposition, and computation of
OLS . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 73
7.5 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 76
8 Applications of the Frisch–Waugh–Lovell Theorem 79
8.1 Centering regressors . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 79
8.1.1 Intercept and centering regressors . . . . . . . . . . . . . . . . . . . 79
8.1.2 Dummy variables and centering regressors within groups . . . . . . . 81
8.2 Partial correlation coefficient and Simpson’s paradox . . . . . . . . . . . . . 81
8.3 Hypothesis testing and analysis of variance . . . . . . . . . . . . . . . . . . 84
8.4 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 88
9 Cochran’s Formula and Omitted-Variable Bias 93
9.1 Cochran’s formula . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 93
9.2 Omitted-variable bias . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 95
9.3 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 96
IV Model Fitting, Checking, and Misspecification 99
10 Multiple Correlation Coefficient 101
10.1 Equivalent definitions of the multiple correlation coefficient . . . . . . . . . 101
10.2 The multiple correlation coefficient and F statistic . . . . . . . . . . . . . . 102
10.3 Numerical examples . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 103
10.4 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 104
11 Leverage Scores and Leave-One-Out Formulas 107
11.1 Leverage scores . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 107
11.1.1 The average leverage score equals p/n . . . . . . . . . . . . . . . . . 107
11.1.2 The leverage scores are all bounded between 0 and 1 . . . . . . . . . 108
11.1.3 The ith leverage score measures the impact of the ith observation in
prediction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 108
11.1.4 The ith leverage score measures whether xi is an outlier compared
with other covariates . . . . . . . . . . . . . . . . . . . . . . . . . . . 109
11.1.5 Other properties of the leverage scores . . . . . . . . . . . . . . . . . 109
11.2 Leave-one-out formulas . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 110
11.3 Applications of the leave-one-out formulas . . . . . . . . . . . . . . . . . . . 112
11.3.1 Gauss updating formula . . . . . . . . . . . . . . . . . . . . . . . . . 112
11.3.2 Outlier detection based on residuals . . . . . . . . . . . . . . . . . . 113
11.3.3 Jackknife . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 114
11.4 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 117
12 Population Ordinary Least Squares and Misspecified Linear Model 119
12.1 Population OLS . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 119
12.2 Population FWL Theorem and Cochran’s formula . . . . . . . . . . . . . . 121
12.3 Population R2 and partial correlation coefficient . . . . . . . . . . . . . . . 123
12.4 Inference for the population OLS . . . . . . . . . . . . . . . . . . . . . . . . 125
12.4.1 Inference with the Eicker–Huber–White standard errors . . . . . . . 125
12.5 To model or not to model? . . . . . . . . . . . . . . . . . . . . . . . . . . . 125
12.5.1 Population OLS and the restricted mean model . . . . . . . . . . . . 125
12.5.2 More on residual plots . . . . . . . . . . . . . . . . . . . . . . . . . . 127
12.6 Conformal prediction based on exchangeability . . . . . . . . . . . . . . . . 130
12.7 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 133
V Overfitting, Regularization, and Model Selection 139
13 Perils of Overfitting 141
13.1 David Freedman’s simulation . . . . . . . . . . . . . . . . . . . . . . . . . . 141
13.2 Variance inflation factor . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 143
13.3 Bias-variance trade-off . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 144
13.4 Model selection criteria . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 146
13.4.1 RSS, R-squared and adjusted R-squared . . . . . . . . . . . . . . . . 146
13.4.2 Information criteria . . . . . . . . . . . . . . . . . . . . . . . . . . . 148
13.4.3 Cross-validation (CV) . . . . . . . . . . . . . . . . . . . . . . . . . . 148
13.5 Best subset and forward/backward selection . . . . . . . . . . . . . . . . . . 149
13.6 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 151
14 Ridge Regression 153
14.1 Introduction to ridge regression . . . . . . . . . . . . . . . . . . . . . . . . . 153
14.2 Ridge regression via the SVD of the covariate matrix . . . . . . . . . . . . . 155
14.3 Statistical properties . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 156
14.4 Selection of the tuning parameter . . . . . . . . . . . . . . . . . . . . . . . . 158
14.4.1 Based on parameter estimation . . . . . . . . . . . . . . . . . . . . . 158
14.4.2 Based on prediction . . . . . . . . . . . . . . . . . . . . . . . . . . . 158
14.5 Computation of ridge regression . . . . . . . . . . . . . . . . . . . . . . . . . 159
14.6 Numerical examples . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 160
14.6.1 Uncorrelated covariates . . . . . . . . . . . . . . . . . . . . . . . . . 160
14.6.2 Correlated covariates . . . . . . . . . . . . . . . . . . . . . . . . . . . 161
14.7 Further commments on OLS, ridge, and PCR based on PCA . . . . . . . . 162
14.8 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 164
15 Lasso 169
15.1 Introduction to the lasso . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 169
15.2 Comparing the lasso and ridge: a geometric perspective . . . . . . . . . . . 170
15.3 Computing the lasso coefficients via coordinate descent . . . . . . . . . . . . 172
15.3.1 The soft-thresholding lemma . . . . . . . . . . . . . . . . . . . . . . 172
15.3.2 Coordinate descent for the lasso . . . . . . . . . . . . . . . . . . . . 172
15.4 Example: comparing OLS, ridge and lasso . . . . . . . . . . . . . . . . . . . 174
15.5 Other shrinkage estimators . . . . . . . . . . . . . . . . . . . . . . . . . . . 176
15.5.1 Bridge estimator . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 176
15.5.2 Elastic net . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 176
15.6 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 177
VI Transformation and Weighting 181
16 Transformations in OLS 183
16.1 Transformation of the outcome . . . . . . . . . . . . . . . . . . . . . . . . . 183
16.1.1 Log transformation . . . . . . . . . . . . . . . . . . . . . . . . . . . . 183
16.1.2 Box–Cox transformation . . . . . . . . . . . . . . . . . . . . . . . . . 184
16.2 Transformation of the covariates . . . . . . . . . . . . . . . . . . . . . . . . 186
16.2.1 Polynomial, basis expansion, and generalized additive model . . . . 186
16.2.2 Regression discontinuity and regression kink . . . . . . . . . . . . . . 188
16.3 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 191
17 Interactions in OLS 193
17.1 Two binary covariates interact . . . . . . . . . . . . . . . . . . . . . . . . . 193
17.2 A binary covariate interacts with a general covariate . . . . . . . . . . . . . 194
17.2.1 Treatment effect heterogeneity . . . . . . . . . . . . . . . . . . . . . 194
17.2.2 Johnson–Neyman technique . . . . . . . . . . . . . . . . . . . . . . . 194
17.2.3 Blinder–Oaxaca decomposition . . . . . . . . . . . . . . . . . . . . . 194
17.2.4 Chow test . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 196
17.3 Difficulties of interaction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 196
17.3.1 Removable interaction . . . . . . . . . . . . . . . . . . . . . . . . . . 196
17.3.2 Main effect in the presence of interaction . . . . . . . . . . . . . . . 197
17.3.3 Power . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 198
17.4 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 199
18 Restricted OLS 201
18.1 Examples . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 201
18.2 Algebraic properties . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 202
18.3 Statistical inference . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 203
18.4 Final remarks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 204
18.5 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 204
19 Weighted Least Squares 209
19.1 Generalized least squares . . . . . . . . . . . . . . . . . . . . . . . . . . . . 209
19.2 Weighted least squares . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 211
19.3 WLS motivated by heteroskedasticity . . . . . . . . . . . . . . . . . . . . . . 212
19.3.1 Feasible generalized least squares . . . . . . . . . . . . . . . . . . . . 212
19.3.2 Aggregate data and ecological regression . . . . . . . . . . . . . . . . 214
19.4 WLS Motivated by Survey Weights . . . . . . . . . . . . . . . . . . . . . . . 216
19.5 WLS as a Building Block for Local linear regression . . . . . . . . . . . . . 218
19.6 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 220
VII Generalized Linear Models 225
20 Logistic Regression for Binary Outcomes 227
20.1 Regression with binary outcomes . . . . . . . . . . . . . . . . . . . . . . . . 227
20.1.1 Linear probability model . . . . . . . . . . . . . . . . . . . . . . . . . 227
20.1.2 General link functions . . . . . . . . . . . . . . . . . . . . . . . . . . 228
20.2 Maximum likelihood estimator of the logistic model . . . . . . . . . . . . . 230
20.3 Statistics with the logit model . . . . . . . . . . . . . . . . . . . . . . . . . . 232
20.3.1 Inference . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 232
20.3.2 Prediction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 234
20.4 More on the interpretations of the coefficients . . . . . . . . . . . . . . . . . 235
20.5 Does the link function matter? . . . . . . . . . . . . . . . . . . . . . . . . . 236
20.6 Extensions of the logistic regression . . . . . . . . . . . . . . . . . . . . . . . 239
20.6.1 Penalized logistic regression . . . . . . . . . . . . . . . . . . . . . . . 239
20.6.2 Case-control study . . . . . . . . . . . . . . . . . . . . . . . . . . . . 239
20.7 Other model formulations . . . . . . . . . . . . . . . . . . . . . . . . . . . . 241
20.7.1 Latent linear model . . . . . . . . . . . . . . . . . . . . . . . . . . . 241
20.7.2 Inverse model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 241
20.8 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 243
21 Logistic Regressions for Categorical Outcomes 247
21.1 Multinomial distribution . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 247
21.2 Multinomial logistic model for nominal outcomes . . . . . . . . . . . . . . . 248
21.2.1 Modeling . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 248
21.2.2 MLE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 249
21.3 A latent variable representation for the multinomial logistic regression . . . 251
21.4 Proportional odds model for ordinal outcomes . . . . . . . . . . . . . . . . . 252
21.5 A case study . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 254
21.5.1 Binary logistic for the treatment . . . . . . . . . . . . . . . . . . . . 255
21.5.2 Binary logistic for the outcome . . . . . . . . . . . . . . . . . . . . . 256
21.5.3 Multinomial logistic for the outcome . . . . . . . . . . . . . . . . . . 256
21.5.4 Proportional odds logistic for the outcome . . . . . . . . . . . . . . . 257
21.6 Discrete choice models . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 259
21.6.1 Model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 259
21.6.2 MLE . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 260
21.6.3 Example . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 260
21.6.4 More comments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 263
21.7 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 263
22 Regression Models for Count Outcomes 265
22.1 Some random variables for counts . . . . . . . . . . . . . . . . . . . . . . . . 265
22.1.1 Poisson . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 265
22.1.2 Negative-Binomial . . . . . . . . . . . . . . . . . . . . . . . . . . . . 266
22.1.3 Zero-inflated count distributions . . . . . . . . . . . . . . . . . . . . 267
22.2 Regression models for counts . . . . . . . . . . . . . . . . . . . . . . . . . . 268
22.2.1 Poisson regression . . . . . . . . . . . . . . . . . . . . . . . . . . . . 268
22.2.2 Negative-Binomial regression . . . . . . . . . . . . . . . . . . . . . . 270
22.2.3 Zero-inflated regressions . . . . . . . . . . . . . . . . . . . . . . . . . 271
22.3 A case study . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 272
22.3.1 Linear, Poisson, and Negative-Binomial regressions . . . . . . . . . . 272
22.3.2 Zero-inflated regressions . . . . . . . . . . . . . . . . . . . . . . . . . 273
22.4 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 276
23 Generalized Linear Models: A Unification 279
23.1 Generalized Linear Models . . . . . . . . . . . . . . . . . . . . . . . . . . . . 279
23.1.1 Exponential family . . . . . . . . . . . . . . . . . . . . . . . . . . . . 279
23.1.2 Generalized linear model . . . . . . . . . . . . . . . . . . . . . . . . . 281
23.2 MLE for GLM . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 282
23.3 Other GLMs . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 284
23.4 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 286
24 Misspecified Generalized Linear Models: Restricted Mean Models and
Sandwich Covariance Matrix 289
24.1 Restricted mean model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 289
24.2 Sandwich covariance matrix . . . . . . . . . . . . . . . . . . . . . . . . . . . 290
24.3 Applications of the sandwich standard errors . . . . . . . . . . . . . . . . . 292
24.3.1 Linear regression . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 292
24.3.2 Logistic regression . . . . . . . . . . . . . . . . . . . . . . . . . . . . 293
24.3.2.1 An application . . . . . . . . . . . . . . . . . . . . . . . . . 293
24.3.2.2 A misspecified logistic regression . . . . . . . . . . . . . . . 294
24.3.3 Poisson regression . . . . . . . . . . . . . . . . . . . . . . . . . . . . 294
24.3.3.1 A correctly specified Poisson regression . . . . . . . . . . . 294
24.3.3.2 A Negative-Binomial regression model . . . . . . . . . . . . 295
24.3.3.3 Misspecification of the conditional mean . . . . . . . . . . . 295
24.3.4 How robust are the robust standard errors? . . . . . . . . . . . . . . 296
24.4 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 296
25 Generalized Estimating Equation for Correlated Multivariate Data 299
25.1 Examples of correlated data . . . . . . . . . . . . . . . . . . . . . . . . . . . 299
25.1.1 Longitudinal data . . . . . . . . . . . . . . . . . . . . . . . . . . . . 299
25.1.2 Clustered data: a neuroscience experiment . . . . . . . . . . . . . . . 299
25.1.3 Clustered data: a public health intervention . . . . . . . . . . . . . . 300
25.2 Marginal model and the generalized estimating equation . . . . . . . . . . . 301
25.3 Statistical inference with GEE . . . . . . . . . . . . . . . . . . . . . . . . . 303
25.3.1 Computation using the Gauss–Newton method . . . . . . . . . . . . 303
25.3.2 Asymptotic inference . . . . . . . . . . . . . . . . . . . . . . . . . . . 303
25.3.3 Implementation: choice of the working covariance matrix . . . . . . . 304
25.4 A special case: cluster-robust standard error . . . . . . . . . . . . . . . . . . 305
25.4.1 OLS . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 305
25.4.2 Logistic regression . . . . . . . . . . . . . . . . . . . . . . . . . . . . 306
25.5 Application . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 307
25.5.1 Clustered data: a neuroscience experiment . . . . . . . . . . . . . . . 307
25.5.2 Clustered data: a public health intervention . . . . . . . . . . . . . . 308
25.5.3 Longitudinal data . . . . . . . . . . . . . . . . . . . . . . . . . . . . 309
25.6 Critiques on the key assumptions . . . . . . . . . . . . . . . . . . . . . . . . 310
25.6.1 Assumption (25.4) . . . . . . . . . . . . . . . . . . . . . . . . . . . . 310
25.6.2 Assumption (25.5) . . . . . . . . . . . . . . . . . . . . . . . . . . . . 312
25.7 Final comments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 313
25.7.1 Explanation versus prediction . . . . . . . . . . . . . . . . . . . . . . 313
25.7.2 Small number of clusters . . . . . . . . . . . . . . . . . . . . . . . . . 313
25.8 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 313
VIII Beyond Modeling the Conditional Mean 315
26 Quantile Regression 317
26.1 From the mean to the quantile . . . . . . . . . . . . . . . . . . . . . . . . . 317
26.2 From the conditional mean to conditional quantile . . . . . . . . . . . . . . 320
26.3 Sample regression quantiles . . . . . . . . . . . . . . . . . . . . . . . . . . . 322
26.3.1 Computation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 322
26.3.2 Asymptotic inference . . . . . . . . . . . . . . . . . . . . . . . . . . . 323
26.4 Numerical examples . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 324
26.4.1 Sample quantiles . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 324
26.4.2 OLS versus LAD . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 325
26.5 Application . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 327
26.5.1 Parents’ and children’s heights . . . . . . . . . . . . . . . . . . . . . 327
26.5.2 U.S. wage structure . . . . . . . . . . . . . . . . . . . . . . . . . . . 327
26.6 Extensions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 328
26.6.1 Cluster-robust standard error for quantile regression . . . . . . . . . 328
26.6.2 High-dimensional quantile regression . . . . . . . . . . . . . . . . . . 329
26.7 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 329
27 Modeling Time-to-Event Outcomes 331
27.1 Examples . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 331
27.1.1 Survival analysis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 331
27.1.2 Duration analysis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 332
27.2 Time-to-event data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 333
27.3 Some examples of random variables for time to event . . . . . . . . . . . . . 334
27.4 Kaplan–Meier survival curve . . . . . . . . . . . . . . . . . . . . . . . . . . 336
27.5 Cox model for time-to-event outcome . . . . . . . . . . . . . . . . . . . . . . 339
27.5.1 Cox model and its interpretation . . . . . . . . . . . . . . . . . . . . 341
27.5.2 Partial likelihood . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 342
27.5.3 Examples . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 344
27.5.4 Log-rank test as a score test from Cox model . . . . . . . . . . . . . 347
27.6 Extensions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 350
27.6.1 Stratified Cox proportional hazards model . . . . . . . . . . . . . . . 350
27.6.2 Clustered Cox model . . . . . . . . . . . . . . . . . . . . . . . . . . . 351
27.6.3 Penalized Cox model . . . . . . . . . . . . . . . . . . . . . . . . . . . 352
27.7 Critiques on survival analysis . . . . . . . . . . . . . . . . . . . . . . . . . . 352
27.8 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 353
IX Appendices 355
A Linear Algebra 357
A.1 Basics of vectors and matrices . . . . . . . . . . . . . . . . . . . . . . . . . . 357
A.2 Vector calculus . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 366
A.3 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 368
B Random Variables 371
B.1 Some important univariate random variables . . . . . . . . . . . . . . . . . 371
B.1.1 Normal, chi-squared, t and F . . . . . . . . . . . . . . . . . . . . . . 371
B.1.2 Beta–Gamma duality . . . . . . . . . . . . . . . . . . . . . . . . . . 372
B.1.3 Exponential, Laplace, and Gumbel distributions . . . . . . . . . . . 373
B.2 Multivariate distributions . . . . . . . . . . . . . . . . . . . . . . . . . . . . 374
B.3 Multivariate Normal and its properties . . . . . . . . . . . . . . . . . . . . . 376
B.4 Quadratic forms of random vectors . . . . . . . . . . . . . . . . . . . . . . . 377
B.5 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 379
C Limiting Theorems and Basic Asymptotics 383
C.1 Convergence in probability . . . . . . . . . . . . . . . . . . . . . . . . . . . 383
C.2 Convergence in distribution . . . . . . . . . . . . . . . . . . . . . . . . . . . 384
C.3 Tools for proving convergence in probability and distribution . . . . . . . . 387
D M-Estimation and MLE 389
D.1 M-estimation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 389
D.2 Maximum likelihood estimator . . . . . . . . . . . . . . . . . . . . . . . . . 392
D.3 Homework problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 396
Bibliography 397

품목정보

발행 예정일
미정
쪽수, 무게, 크기
434쪽 | 180*250mm
ISBN13
9781032825502

리뷰/한줄평0

리뷰

첫번째 리뷰어가 되어주세요.

한줄평

첫번째 한줄평을 남겨주세요.

상품정보안내

직수입외서의 경우, 해외거래처에서 제공하는 정보가 부족하여 제목, 표지, 가격, 유통상태 등의 정보가 미비하거나 변경되는 경우가 있습니다. 정확한 확인을 원하시는 경우, 일대일 상담으로 문의하여 주시면 답변 드리겠습니다.
(판형과 판수 등이 다양한 도서는 찾으시는 도서의 ISBN을 알려 주시면 보다 빠르고 정확한 안내가 가능합니다.)

해외거래처에서 품절인 경우, 2차 거래선을 통해 유럽과 미국 출판사로 직접 수입이 진행될 수 있습니다.
수입 진행 시점으로 부터 2~3주가 추가로 소요되며, 해외에서도 유통이 원활하지 않은 도서는 품절 안내가 지연될 수 있습니다.
해당 경우, 문자와 메일로 별도 안내를 드리고 있사오니 마이페이지에서 휴대전화번호와 메일주소를 다시 한번 확인해주시기 바랍니다.