Greene W.H. Econometric Analysis

Подождите немного. Документ загружается.

Index

1169

Frisch, R., 1, 2, 34

Frisch-Waugh-Lovell theorem, 33

Fry, J., 307n19

Fry, T., 307n19

full information estimator, 326

full information maximum

likelihood (FIML), 330, 333

endogenous variables/

participation, 828

nested logit models, 770

simultaneous equations models,

567–568

two-step MLE, 536

full rank, 19–20

full rank matrix, 985

full rank quadratic form, 118n1,

1045–1046

Fuller, W., 280n24, 375n15, 948, 949,

955, 957

function of one parameter,

1106–1107

function of two parameters,

1107–1108

functional form, 149–180

binary variable. See binary

variable

interaction effects, 161

intrinsically linear models,

165–167

loglinear model, 160

nonlinearity, 162–165

piecewise linear regression,

158–160

functionally independent, 114

fundamental probability transform,

437, 607

fuzzy design, 897

Gabrielsen, A., 326

Gallant, A., 318n37

Gallant, R., 318n37

gamma distribution, 460, 1024, 1107

gamma function, 1092

gamma regression model, 74–75

Garber, S., 159n4, 242n6

GARCH effects, 436

GARCH model, 22, 933–937

Garvin, S., 292n3

gasoline consumption functions, 172

gasoline market, 17

Gauss-Hermite quadrature, 582,

583, 1093

Gauss-Laguerre quadrature, 1093

Gauss-Markov theorem, 60, 61,

74, 265

Gauss-Newton method, 200

Gaussian copula, 438

Gaussian quadrature, 1093

GEE estimator, 716n27

Gelman, A., 656n2, 678

gender economics courses, 747

general linear hypothesis, 112–113

general nonlinear hypothesis,

113–114

general-to-simple approach to

model building, 138–143

generalized autoregressive

conditional

heteroscedasticity

(GARCH) model, 933–937

generalized Chebychev’s inequality,

1073

generalized Cobb-Douglas

function, 106, 124. See also

Cobb-Douglas production

function

generalized inverse (matrix),

1003–1004

generalized least squares

FGLS, 296, 374–376

random effects model, 373–374

SUR model, 293–295

generalized linear regression

model, 257

generalized method of moments

(GMM) estimation,

439–440, 468–506

asymptotic distribution, 477

counterparts to Wald, LM, and

LR tests, 480–482

dynamic panel data models,

496–506

generalizing the method of

moments, 470–472

local government expenditures,

503–506

maximum likelihood, 543

nonlinear regression model,

472–473

orthogonality conditions,

468–470

panel data sets, 408

properties, 474–478

serial correlation, 921–922

simultaneous equations models,

493–496

single-equation linear models,

482–488

single-equation nonlinear

models, 488–491

SUR model, 491–492

testing hypotheses, 479–482

validity of moment restrictions,

479–480

generalized mixed logit model,

772–773

generalized ordered choice models,

799–800

generalized regression model, 293

generalized residual, 691n9, 864

generalized sum of squares, 266, 552

generalized SUR model, 304–305

Gentle, J., 606, 607, 1089n2

George, E., 669

German labor market

interventions, 888

German money demand, 967–970

German Socioeconomic Panel

(GSOEP), 195, 344, 794

Geweke, J., 625, 628n7, 656, 716n27,

753n42, 1048n1

GHK simulator, 627–629

GHK smooth recursive

simulator, 628

Ghysels, E., 930

Giaccotto, C., 275n17

Gibbs sampler, 669–670, 672–674

Gilbert, R., 617n3

Gill, J., 656n2

GLAMM program, 642

GLIM/GEE treatment (binary

choice models), 707n21

global maximum, 1010

globally concave, 1010

globally convex, 1010

Gloeckler, L., 587n27

GMM estimation. See generalized

method of moments (GMM)

estimation

GNP deﬂator, 944, 945

Godfrey, L., 250, 524, 552, 617, 647,

858n12, 922

Godfrey statistic, 250

Goffe, W., 1094n13

Goldberger, A., 294n8, 307n20,

323n40, 332n47, 663n10,

851n11, 860n13, 892,

892n36, 894

golden section method, 1094n11

Goldfeld, S., 181n2, 1097, 1098,

1099n16, 1102n21

Goldfeld and Quandt’s mixture of

normals model, 459, 589

Gonzal´az, P., 348

Good, D., 153

goodness of ﬁt, 39–46, 701–703,

804–805

1170

Index

Gordin, M., 916n9

Gordin’s central limit theorem, 917

Gourieroux, C., 134n8, 135n10,

542n12, 545, 628n7, 631,

712n24, 858n12, 938

grade point average, 590, 593

gradient, 202, 1097

gradient methods, 1097–1099

gradient vector, 1008

Granger, C., 2, 134n9, 944, 945, 946,

959n12, 964, 965

Granger causality, 318

Granger representation theorem,

964n13

Gravelle, H., 173, 358, 362

Greenberg, E., 433, 678,

1077n4, 1082

Greene, W., 106, 107, 122, 147,

152n1, 153, 163, 164, 173,

199, 208, 211, 212, 218, 309,

311n27, 312n30, 341, 358,

365, 436, 445, 469n5, 586,

587, 591, 593, 596, 606, 619,

620, 621, 624, 652n10, 681n1,

683, 689n6, 699n13, 710, 711,

718, 720, 722, 729n34,

742n40, 747, 751, 753, 761,

770, 771, 772n6, 773, 781,

782, 785n8, 790, 791, 793,

794n10, 795, 798, 799, 800,

804n12, 807n14, 808, 809,

818, 820, 821, 823, 829,

839n6, 842, 843, 846, 848n10,

851, 851n11, 860, 868n19,

870, 876n28, 877n31, 878,

880, 881, 887, 895, 901,

1024n6, 1077n4, 1082,

1087n8

Grenander conditions, 65

grid search, 1094

grid search algorithm

(optimal prediction

interval), 87

Griesinger, H., 719

Grifﬁn, J., 284

Grifﬁn, W., 387

Grifﬁths, W., 416, 450n3

Griliches, Z., 94, 95n18, 242n6, 268,

342n50, 423, 617n3, 712,

717, 927

Grogger, J., 811

Gronau, R., 874n26

Groot, W., 787, 795, 799

group effects, 363

group means, 354

group means estimator, 358

growth model for developing

countries, 426

Grunfeld, Y., 342n50, 430

Gruvaeus, G., 1103n23, 1107n25

GSOEP, 195, 344, 794

Gudmundsson, M., 7n

Guilkey, D., 305n16, 312n29, 731n35

Gumbel model, 688

Gurmu, S., 92, 804n12, 805, 806

Haavelmo, T., 2

Hadamard product, 635

Hadri’s LM statistic, 971

Hahn, J., 249n10, 250, 328n42, 334,

728, 861

Hahn and Hausman test

statistic, 334

Haisken-DeNew, J., 794

Haitovsky, Y., 95n18

Hajivassiliou, A., 631

Hajivassiliou, V., 628n8, 753n42

Hakkio, C., 930

Hall, B., 522n4, 1089n1, 1100, 1103,

1103n22

Hall, R., 455, 456, 479, 480, 522n4,

1100, 1103

Hall’s permanent income model of

consumption, 455–456

Halton draw, 625–627

Hamilton, J., 916, 918, 948n9, 957,

959n12, 963, 964n13

Han, A., 871

Hansen, B., 140

Hansen, L., 232n1, 456, 465, 468n3,

471n7, 471n8, 472, 476,

480, 706, 707, 716n27,

720, 754

Hanushek, E., 3

Hardin, T., 742n40

Hardle, W., 203n10, 215, 444n2

Harris, M. N., 787, 823n16

Harvey, A., 280, 554, 555, 714,

934, 943n2

Harvey’s model of multiplicative

heteroscedasticity, 280,

554–557

Hashimoto, N., 295n9

Hastings, N., 1019n1

Hatanaka, M., 929

Hausman, J., 234, 235, 236, 237,

249n10, 250, 253, 323n40,

328n42, 334, 379, 379n20,

394, 395, 397, 407, 499,

522n4, 714n26, 723, 767, 768,

802, 805, 806, 815, 818, 819,

839n6, 869n21, 871, 883, 886,

887, 1100, 1103

Hausman and Taylor estimator,

394–397, 497, 499

Hausman speciﬁcation test,

234–237, 379–380, 397

Hausman statistic, 237

Hausman test (consumption

function), 237

Hayashi, F., 433n1, 453, 468n3, 474,

916n8, 918, 920n10, 1084n5

hazard function, 836, 864–866, 1029

hazard model, 861

hazard rate, 864

health care utilization, 411, 412,

596, 743–744

health expenditures, 393–394

Heaton, J., 471n7, 476

Heckman, J., 2, 3, 222, 251n12, 253,

536, 542, 587n28, 595, 619,

687n5, 692n11, 721, 726, 729,

731, 732, 736, 750, 839n5,

862n15, 869, 872n24, 874n26,

876, 892, 893n39, 895n40,

1025n7

Heckman’s model of labor supply,

2, 536

Heilbron, D., 821

Hendry, D., 138, 139, 317, 617,

968, 969

Hensher, D., 683, 683n2, 761, 769n5,

770, 771, 772n6, 782, 787, 798

Herbertsson, T. T., 7n

Hermite polynomial, 1090

Heshmati, A., 304

Hessian, 463, 517, 554, 586, 803

heterogeneity, 729

heterogeneity in parameter models,

416–426. See also random

parameter models

heteroscedastic extreme value

(HEV) model, 776, 777

heteroscedastic regression model,

268, 269

heteroscedastic 2SLS (H2SLS), 494

heteroscedasticity

ARCH, 930–938

binary choice, 714

censoring, 858–859

GARCH model, 933–937

HEV model, 776, 777

H2SLS, 494

linear regression model, 22

multiplicative, 280, 554–557, 858

random effects model, 387–388

HEV model, 776, 777

Index

1171

HHG model, 818

hierarchical linear models, 639–641

hierarchical model, 347

hierarchical ordered probit

(HOPIT) model, 800

hierarchical prior, 675

highest posterior density (HPD)

interval, 85, 665

Hildebrand, G., 124n4

Hildreth-Houck-Swamy

approach, 425

Hill, C., 91n14, 194n6, 280n25,

379n19, 450n3, 687n15, 1082

Hildreth, C., 417n27

Hilts, J., 173

Hinkley, D., 611n2

histogram, 445, 446, 1051

Hite, S., 95n16

Hoeting, J., 141

Hoffman, D., 702, 710, 751, 880

Hole, A., 610

Hollingshead scale of occupations,

765–766

Hollingsworth, J., 173

Holly, A., 318n37

Holt, M., 305n16

Holtz-Eakin, D., 502n18, 505

home prices, 640

homogeneity restriction, 297

homogeneous equation system, 990

homoscedasticity, 22, 1035

Honor´e, B., 211n16, 730, 861

HOPIT model, 800

Horn, A., 273n11

Horn, D. A., 273n11

Horowitz, J., 511, 611n2, 612, 693,

714n26, 858n12

hospital cost function, 466–468

hospital costs, 384–385

Hotz, J., 706, 707, 716n27, 720, 754

Houck, C., 417n27

hours worked, 851–852

Houthakker, H., 268n8

Howrey, E., 416

Hoxby, C., 3, 228, 253

HPD interval, 85, 665

Hsiao, C., 322n39, 344n2, 378,

379n19, 387, 401, 417n27,

418n29, 422, 425, 426,

497n14, 619, 721, 724n33,

729n34, 795

H2SLS, 494

Huang, D., 296n11, 342n251, 430

Huber, P., 71, 204, 542n12, 543

Hudak, S., 391

Huizinga, J., 468n3, 494

Hurd, M., 858

hurdle model, 443, 824–826

Hussain, 375n15

Hwang, H., 292n3

hyperplane, 983

hypothesis testing and model

selection, 108–148,

1062–1066

acceptance/rejection

methodology, 111

AIC/BIC, 139, 140

Bayesian estimation, 666–667

Bayesian model averaging,

141–143

Bayesian vs. classical testing, 112

binary choice, 703–706

consistency of the test, 111

encompassing model,

135–136

F statistic, 118–119, 143

ﬁt of the regression, 121–127

general linear hypothesis,

112–113

general nonlinear hypothesis,

113–114

general-to-simple approach to

model building, 138–143

GMM estimation, 479–482

J linear restrictions, 123

J test, 136–137, 140

Lagrange multiplier test, 131

large-sample test, 127–131

least squares discrepancy,

117–119

model building, 138–143

model selection, 140–143

nested models, 110

Neyman-Pearson

methodology, 111

nonlinear regression model,

189–191

nonlinear restrictions, 131–133

nonnormal disturbance, 127–131

nontested models, 134–137

null/alternative hypothesis,

109–110

power of the test, 111

RESET test, 137–138

restricted least squares estimator,

121–122

restrictions and hypotheses,

109–110

signiﬁcance of the regression, 126

size of the test, 111

speciﬁcation test, 137–138

SUR model, 296–297

t ratio, 116

Wald test, 115–121

hypothesis testing methodology,

108–112

Hyslop, D., 240n3, 731, 753

Ichimura, H., 895n40

Ichino, A., 895

idempotent matrix, 978–979, 1002

idempotent quadratic forms, 1006,

1043–1045

identical explanatory variable, 294

identical regressors, 295

identiﬁability of parameters,

450–451

identiﬁcation, 227, 241, 475,

484, 510

identiﬁcation condition, 19, 166, 188

identiﬁcation problem, 184,

321–326

identiﬁcation through functional

form, 800

identity matrix, 973

ignorable case, 94

IIA assumption, 767

Im, E., 292n3, 382n24, 410, 970, 971

Imbens, G., 240n3, 893n39

IMDb.com ratings, 786

Imhof, J., 924

impact of the treatment on the

treated, 15

improper prior, 675

“Incentive Effects in the Demand

for Health Care: A Bivariate

Panel Count Data

Estimation” (Riphahn

et al.), 195, 411

incidental parameters problem,

413, 588, 619–621

incidental truncation, 872. See also

sample selection

inclusion of superﬂuous (irrelevant)

variables, 58

inclusive value, 769

income elasticity (credit card

expenditure), 208–210

independence, 24

independence from irrelevant

alternatives (IIA)

assumption, 767

independence of linear and

quadratic forms, 1046–1047

independent variable, 12, 1007

index function model, 412, 581, 686

indicator, 243

1172

Index

indirect utility function, 183

individual effect, 345

individual effects models, 674–676

individual regression coefﬁcients, 34

inequalities for expectations, 1074

inestimable model, 19

inference, 434. See also estimation

and inference

inﬂuential observations, 100–101

information matrix, 1060

information matrix equality,

515, 517

informative prior, 659

informative prior density, 661–663

initial conditions, 729, 908

Inkmann, J., 720

innovation, 907

instrumental variable analysis, 228

Instrumental variable estimation.

See endogeneity and

instrumental variable

estimation

instrumental variable estimation

(labor supply equation),

232–233

instrumental variable in regression,

229–230

instrumental variables estimates

(consumption function),

248–249

instrumental variables estimator,

225–230

integral, 623

integrated hazard function, 864

integrated of order one, 943

integrated process and differencing,

942–943

intelligent draw, 625

intemporal labor force

participation equation, 731

intensity equation, 852

interaction effects, 161, 199,

699–701

interaction effects (loglinear model

for income), 195–199

interaction terms, 161, 199

interdependent, 316

interval estimate, 1055

interval estimation, 51, 75–80, 665,

1060–1062

intrinsic linearity, 166

intrinsically linear equation, 165

intrinsically linear models,

165–167

intrinsically linear regression, 166

invariance, 313, 521

invariance property, 165

invariant, 309

inverse function, 1014

inverse gamma distribution, 1024

inverse Gaussian (Wald)

distribution, 458

inverse matrix, 990–992

inverse Mills ratio, 836

inverse probability weighted (IPW)

estimator, 736, 738, 887

inverted gamma distribution, 659

inverted Wishart, 676

investment equation, 28–30

IPW estimator, 736, 738, 887

Irish, M., 691n9, 858n12, 864

iteration, 201, 202

iterative algorithm, 1095

IV analysis, 228

IV estimation. See endogeneity and

instrumental variable

estimation

IV estimator, 225–230, 242

J linear restrictions, 123

J test, 136–137, 140

jackknife technique, 274n15

Jackman, S., 729n34, 731

Jacobian, 189, 549, 1014

Jacobs, R., 173, 358, 362

Jaeger, D., 250

Jain, D., 771

Jakubson, G., 731

Jansen, E., 7n

Jarque, C., 277, 846, 858n12

Jayatissa, W., 171n15

Jenkins, G., 910n5, 925n14

Jenkins, S., 753

Jennrich, R. I., 181n2

Jensen, M., 562n20

Jensen’s inequality, 1019, 1074

Job Training Partnership Act

(JTPA), 221

Jobson, J., 280n24

Johansen, S., 964, 967

Johanssen, P., 820

Johansson, E., 503

Johnson, N., 692n11, 806, 821,

836n3, 873n25, 1019n1,

1024n3

Johnson, R., 93, 153, 299

Johnson, S., 194n6, 280n25, 379n19,

687n15, 1082

Johnston, J., 205, 328n42, 1087n8

joint distribution, 1030–1034

joint distribution function, 1030

joint modeling (pair of event

counts), 438–439

joint posterior distribution, 660

jointly dependent or

endogenous, 316

Jondrow, J., 841

Jones, A., 173, 222, 358, 362, 697,

698, 735, 736, 794, 795, 798,

884, 887

Jones, J., 730

Joreskog, K., 563n21, 1089n1,

1103n23, 1107n25

Jorgenson, D., 147, 183, 231,

307n20, 311n25, 311n26,

312n28, 312n29

JTPA, 221

Judd, K., 1089n2, 1093n7

Judge, C., 450n3

Judge, G., 65n3, 92, 186, 191n4,

266n5, 296n13, 297n14,

334n49, 373n13, 375n14,

379n19, 658n3, 663n9, 687n5,

932n19, 1048n1, 1097n15,

1101

Jung, B., 578

Juselius, K., 967

k class of estimators, 329

Kakwani, N., 296n12

Kalbﬂeisch, J., 860, 862n15, 865,

867, 868, 870

Kamlich, R., 176

Kang, H., 946n5

Kao, C., 410, 411, 971

Kaplan, E., 870

Kay, R., 701

Keane, M., 252n13, 252n14, 628n7,

628n8, 716n27, 731, 753n42,

773, 883

Kelejian, H., 392

Kemp, A., 1019n1

Kenkel, D., 883

Kennan, J., 865, 871

Kennedy, W., 1089n2

Kerman, S., 292n3

kernel density estimation, 445–447

kernel density estimator, 205, 1051

income, 196

least squares residuals, 73

kernel density methods, 442

kernel function, 213

kernel weighted regression

estimator, 214

kernels for density estimation, 447

Keuzenkamp, H., 6n2

Index

1173

Keynes’s consumption function, 4,

13–14

Khinchine’s weak law of large

numbers, 457, 1070

Kiefer, N., 277, 742n39, 862n15, 865,

868, 870, 871

Kim, I., 957

Kingdon, G., 587

kitchen sink regression, 139

Kiviet, J., 305n16, 400, 496n13,

497n15

Kleibergen, F., 249n10, 250, 254

Kleibergen’s method, 335

Kleidon, A., 416

Klein, L., 2, 532

Klein, R., 443

Klein’s model I, 332

Klepper, S., 242n6

KLIC, 535

Klugman, S., 436

Kmenta, J., 166, 167, 283, 298n15,

312n29, 553, 561, 562, 566,

617n3, 1087n9

Knapp, L., 714n26

Knight, F., 839

knots, 159

Kobayashi, M., 171

Koenker, R., 71, 203n10, 204,

205n12, 206, 276, 453

Koh, W., 391

Kolmogorov’s strong law of large

numbers, 1071

Koolman, X., 735, 736, 887

Koop, G., 50, 142, 145, 178, 625n5,

646, 656, 674, 676, 1048n1

Kotz, S., 692n11, 806, 821, 873n25,

1019n1

KPSS test of stationarity, 958–959

Kraft, D., 940

Krailo, M., 723n30

Kreuger, A., 3, 15, 219, 221, 224,

244, 251

Krinsky, I., 313n31, 609, 610, 749

Krinsky and Robb technique,

609–611

Krishnan, T., 1104

Kronecker product, 294, 635, 994

Kroner, K., 933

Krotzis, H. M., 139

Kruskal’s theorem, 287

Kuersteiner, G., 728, 861

Kuh, E., 90, 100, 101

Kulasi, F., 410

Kullback-Leibler information

criterion (KLIC), 535

Kumbhakar, S., 304, 593, 839n7, 843

kurtosis, 1018, 1049

Kwiatkowski, D., 958

Kyriazidou, E., 730, 861, 884,

886, 893

labor force participation model,

683, 715

labor supply, 874, 878–879

labor supply model, 232–233,

236–237, 708–709

lack of invariance, 133

LAD estimator/estimation,

203–206

Cobb-Douglas production

function, 205–206

computational complexity, 860

least squares, compared, 71–72

Powell’s censored LAD

estimator, 443

quantile regression, 441–442

Lagrange multiplier statistic,

1100–1101. See also

Lagrange multiplier test

GMM estimation, 481, 482

limiting distribution, 530

nonlinear regression model, 191

overdispersion, 806

SUR model, 564

zero correlation, 742

Lagrange multiplier test, 276. See

also Lagrange multiplier

statistic

autocorrelation, 922, 924

groupwise heteroscedasticity, 283

hypothesis testing, 131, 189,

190, 704

MLE, 529–530, 551

random effects, 376

SUR model, 297

Lagrangean problem, 84, 162

Lahiri, K., 344n2

Laird, N., 814, 1104, 1106

Laisney, F., 693

LaLonde, R., 155, 888, 895

Lambert, D., 589, 821, 823

Lancaster, T., 586, 588, 619, 656,

691n9, 721, 858n12, 862n15,

865, 868, 1048n1

Land, K., 652n10

Landers, A., 95n16

Landwehr, J., 730

large sample distribution theory,

1066–1089

asymptotic distribution,

1084–1088

asymptotic expectations,

1087–1088

central limit theorem, 1078–1083

convergence in distribution, 1076

convergence in probability,

1067–1070

convergence of functions,

1073–1074

convergence to a random

variable, 1074–1075

delta method, 1083–1084

law of large numbers, 1070–1072

limiting distribution, 1076–1078

sequence/order of sequence,

1088–1089

large sample properties, 63–75

large-sample test, 127–131

latent class linear regression

model, 592

latent class modeling, 588–598

latent class models, 650–652

latent regression model, 686–687

latent roots, 997

latent variable, 848

latent variable problem, 243n7

latent vector, 997

Lau, L., 147, 183, 307n20, 311n26,

312n29

Lauer, J., 173, 607

law of iterated expectations, 1035

law of large numbers, 1070–1072

Lawless, J., 870

Layson, K., 193n5

leading term approximation, 1088

Leamer, E., 142, 242n6, 656n2,

663n9, 1048n1

least absolute deviations

estimation. See LAD

estimator/estimation

least simulated sum of squares, 604

least simulated sum of squares

estimates of production

function model, 638–639

least squares, 27

least squares attenuation, 99,

240–242

least squares coefﬁcient vector,

27–28

least squares discrepancy, 117–119

least squares dummy variable

(LSDV) model, 360

least squares estimator/estimation,

51–107

assumptions of linear regression

model, 52

asymptotic distribution, 68–69

1174

Index

least squares estimator/estimation

(continued)

asymptotic efﬁciency, 69–70

asymptotic normality,

65–67

conﬁdence interval, 76–80

consistency, 63–65, 67–68

Cram´er-Rao bound, 73, 74

data imputation, 95–97

data problems, 88–102

delta method, 68–69

ﬁnite sample properties,

54–61, 63

ﬁxed effects model, 360–362

forecasting, 85–88

Gauss-Markov theorem, 60,

61, 74

inclusion of irrelevant

variables, 58

inﬂuential observations,

100–101

interval estimation, 75–80

large sample properties, 63–75

measurement error, 97–99

minimum means squared error

predictor, 53, 54

minimum variance linear

unbiased estimation, 54

missing values, 94–97

MLE, 75–75

multicollinearity, 89–91

omission of relevant variables,

56–58

outliers, 101–102

overview, 52–53

pooled regression model,

349–350

population orthagonality

conditions, 52–53

prediction, 80–87

pretest estimation, 91–92

principal components, 92–94

random effects model, 372–373

serial correlation, 918–921

smearing, 225

stochastic regressors, 60–61

system method of estimation, 330

unbiased estimation, 55–56

variance of least squares

estimator, 58–59, 61–62

least squares normal equation, 28

least squares problem, 987–989,

992, 1094

least squares regression, 26–32

algebraic aspects, 30–31

investment equation, 28–30

least squares coefﬁcient vector,

27–28

projection, 31–32

least variance ratio estimator, 328

LeCam, L., 520n3

Lechner, M., 651, 693, 706,

720, 753

L’Ecuyer, P., 606

Lee, K., 220, 422

Lee, L., 344n2, 437, 805, 858n12

Lee, M., 344n2, 860n13

Leff, N., 49

left truncation, 812

Leite, P., 79n11

Lerman, S., 701, 710

LeRoy, P., 315n34

Levi, M., 242n6

Levin, A., 410, 971

Levinsohn, J., 603, 771, 782

Levitt, S., 253

Lewbel, A., 442, 730

Lewis, H., 874n26

Li, M., 793

Li, P., 439

Li, Q., 215, 390, 444n2, 1051

Li, W., 930n16

Liang, P., 716n27

Liapounov central limit

theorem, 1082

life cycle consumption, 455–456

life expectancy, 174

likelihood equation, 513, 517, 691

likelihood function, 434,

509, 1058

likelihood inequality, 518

likelihood ratio, 526

likelihood ratio index, 533, 701

likelihood ratio statistic, 298,

480, 564

likelihood ratio test, 297,

526–527, 704

Lilen, D., 930, 932

LIMDEP/NLOGIT, 642

limited dependent variables,

833–902. See also

microeconometric methods

limited information estimator, 326

limited information maximum

likelihood (LIML)

estimator, 327, 328,

567–568

limited information two-step

maximum likelihood

approach, 770

limiting distribution, 226, 1023,

1076–1078

limiting mean and variance, 1077

limiting normal distribution

function, 1083

set of functions, 1084

LIML estimator, 327, 328,

567–568

Lin, C., 410, 971

Lindeberg-Feller central limit

theorem, 66, 1079

Lindeberg-Levy central limit

theorem, 457, 462, 519,

1079, 1080

line search, 1095, 1096

linear approximation, 1007

linear dependence/

independence, 982

linear estimator, 59

linear independence, 24

linear instrumental variables

estimation, 252

linear least squares, 6

linear probability model, 687

linear random effects model,

574–576

linear regression and

homoscedasticity, 1037

linear regression model, 11–25. See

regression modeling

assumptions, listed, 16

classical regression model, 25

data generation, 23

exogeneity of independent

variables, 16

full rank, 19–20

general form, 12

heteroscedasticity, 22

homoscedasticity, 22

how used, 12, 14

independence, 24

linearity, 15–18

MLE, 568–571

normality, 23–24

spherical disturbance, 21–23

zero overall mean assumption,

20–21

linear Taylor series approach, 68

linear unbiased estimator, 54

linear unobserved effects

model, 381

linearity, 15–18

linearized regression model,

200–202

linearly transformed regression,

46–47

Ling, S., 930n16

Little, R., 94

Index

1175

Little, S., 701

Liu, T., 124n4

Ljung’s reﬁnement (Q test), 923

LM statistic. See Lagrange

multiplier statistic

LM test. See Lagrange multiplier

test

Lo, A., 3

local government expenditures,

503–506

local maximum, 1010

local optimum, 1010

locally weighted smoothed

regression estimator, 213

loess estimator, 213

Loeve, M., 1080

log-likehihood function, 436, 510,

517, 570, 595

log-odds, 764

log-quadratic cost function, 165

logistic distribution, 1025

logistic kernel, 213

logistic probability model, 540

logit model

basic form, 688

conditional, 730, 766–767

ﬁxed effects, 726–727

generalized mixed, 772–773

mixed, 771–772

multnomial, 763–766

nested, 768–770

structural break, 705

loglinear conditional mean, 569

loglinear model, 17, 160, 196, 803

loglinear regression model,

568–569

lognormal mean, 627

Long, S., 755n8, 791, 794

long run elasticities, 610

long-run elasticity, 422

long-run marginal propensity to

consume, 132–133

long-run multiplier, 422, 423

longitudinal data sets. See models

for panel data

Longley, J., 90

loss function, 665

Louviere, J., 761, 769n5

Lovell, K., 124n4, 312n29, 833, 839,

839n7, 840, 841, 843

Lovell, M., 33n3

Low, S., 702, 710, 751, 880

lower triangular matrix, 973

lowess estimator, 213

LSVD model, 360

Lucas, R., 309n23, 968

M estimator, 449, 452, 543

M-H algorithm, 677, 678

MA(1) process, 910

Maassen van den Brink, H., 787,

795, 799

MacKinlay, A., 3

MacKinnon, J., 135, 136, 181n2, 185,

186, 189, 216, 236, 248,

273n11, 274, 294n7, 318n37,

327, 329, 449, 450, 453,

468n3, 494, 515, 521, 552,

558, 567, 612, 613, 704,

713n25, 714, 914, 916, 918,

927, 936, 943n2, 946n3

macroeconometric methods,

903–972

nonstationary data. See

nonstationary data

serial correlation. See serial

correlation

macroeconometrics, 3

MaCurdy, T., 499, 687n5, 721, 731

Maddala, G., 95n17, 344n2, 375n14,

376n16, 378, 410, 423, 586,

658n3, 683, 689n6, 692n10,

701n14, 721, 746, 751, 770,

845n, 858, 873n25, 879,

947n7, 957, 971, 1019n1,

1077n3, 1087n6

Madigan, D., 141

magazine prices, 726–727

Magee, L., 793

Magnac, T., 730

Magnus, J., 6n2, 416

major derogatory reports (MDRs),

812–813, 824

Malinvaud, E., 181n2, 465, 471n8

Maloney, W., 348

Mandy, D., 304

Mankiw, G., 480

Mann, H., 913, 948

Manpower Development and

Training Act (MDTA), 156

Manski, C., 469, 683, 710, 730,

872n24, 892, 893n39

Manski’s maximum score

estimator, 730

MAR, 95

Marcus, A., 790

marginal and conditional normal

distributions, 1041–1042

marginal distribution, 1030

marginal effect, 161, 690

marginal effects, 693–694

marginal probability density,

1030

marginal propensity to consume

(MPC), 132–133, 664

Mariano, R., 329, 331

Mariel boatlift, 157–158

market equilibrium model, 314

Markov chain, 606

Markov-Chain Monte Carlo

(MCMC), 642, 670

Markov’s inequality, 1068

Markov’s strong law of large

numbers, 1072

Marsaglia, G., 607

Marsaglia-Bray generator, 607

Marsh, T., 416

Martingale difference central limit

theorem, 916

Martingale difference

sequence, 916

Martingale difference series, 476

Martingale sequence, 915

Martins, M., 892

Martins-Filho, C., 304

matching estimator, 895

Materov, I., 841

matrix. See also matrix algebra

asymptotic covariance, 226, 235,

262, 279, 1085

autocorrelation, 909

autocovariance, 909

block-diagonal, 993

contiguity, 390

correlation, 1039, 1049

covariance, 257, 1039, 1049

deﬁned, 973

deﬁnite, 1001–1002, 1004–1006

dimensions, 973

idempotent, 979, 1002

information, 1060

inverse, 990–992

nonsingular, 991

partitioned, 992–995

positive deﬁnite, 257

precision, 667

projection, 31

square, 973

transpose, 974

weighting, 265, 486

zero, 974

matrix algebra, 973–1015. See also

matrix

addition/subtraction, 975

basis vectors, 981, 983

characteristic roots/vectors,

995, 1001

column space/rank, 984, 985

comparing matrices, 1006–1007

1176

Index

matrix algebra (continued)

condition number, 999

constrained optimization,

1012–1013

deﬁnite matrixratic forms,

1001–1002, 1004–1006

determinant, 986–987, 1000

diagonalization, 997

differentiation, 1007–1008

equality of matrices, 973

factoring, 1002–1003

generalized inverse, 1003–1004

idempotent matrix, 978–979, 1002

idempotent quadratic forms, 1006

inverse matrix, 990–992

least squares problem,

987–989, 992

linear dependence/

independence, 982

multiplication, 975–977

notational conventions, 975

optimization, 1010–1013

partitioned matrix, 992–995

powers, 1000–1002

quadratic forms, 1004–1006

rank, 984–986, 997–999

scalar multiplication, 976

spectral decomposition, 997

sums of values, 977–978

subspace, 983

terminology, 973

trace, 999–1000

transformations, 1014–1015

transposition, 974

vector multiplication, 975

vector spaces, 979–980

matrix product rule, 1074

matrix reverse rule, 1074

matrix weighted average, 358

Matyas, L., 344n2, 468n3

maximum empirical likelihood

estimation, 440–441

maximum entropy estimator, 441

maximum likelihood, 309

maximum likelihood estimation

(MLE), 435, 509–602,

1031–1032

asymptotic properties, 517–521

asymptotic variance, 520, 521–522

BHHH estimator, 522

binary choice, 739–741

cluster estimator, 546–547

duration models, 866–867

ﬁnite mixture model, 589–590

ﬁxed effects in nonlinear models,

584–588

generalized regression model,

552–560

GMM estimation, 543

identiﬁcation of parameters,

510–511

information matrix equality, 517

KLIC, 535

latent class modeling, 588–598

least squares estimator, 73–76

likelihood equation, 513, 517

likelihood function, 509

likelihood inequality, 518

likelihood ratio, 526

likelihood ratio statistic, 564

likelihood ratio test, 526–527

linear random effects model,

574–576

LM test, 529–530

M estimation, 543–544

nested random effects, 576–580

nonlinear regression models,

568–571

normal linear regression model,

548–552

panel data applications, 573–588,

595–598

principle of maximum likelihood,

511–513

properties, 513–523

pseudo-MLE, 547, 548

pseudo R

, 533

quadrature, 580–584

regularity conditions, 514–515

sandwich estimator, 545

simultaneous equations models,

567–568

SUR model, 560–567

two-step MLE, 536–542

Vuong’s test, 534–536

Wald test, 527–529

maximum score estimator, 730

maximum simulated likelihood

(MSL), 603, 605, 630,

631–, 653

binary choice, 651–652, 733

hierarchical linear model of

home prices, 640

random effects linear regression

model, 633

random parameters production

function model, 638

Mazodier, P., 387

Mazzeo, M., 590, 673, 694

, 642, 670

McAleer, M., 134n8, 137n12,

930n16

MCAR, 94, 735

McCallum, B., 67n6, 243

McConnell, K., 810

McCoskey, S., 410, 970, 971

McCullagh, P., 805, 832

McCulloch, R., 656n2

McCullough, B., 87, 201, 930n16,

932n19, 938n28

McDonald, J., 204n11, 850

McFadden, D., 2, 449, 453, 468n3,

474, 481n10, 524, 533, 628,

683, 701, 761, 767, 768n4,

770, 772

McGuire, T., 309n23

McKelvey, W., 701n14, 787, 829

McKenzie, C., 701

McLachlan, G., 593, 595,

596, 1104

McLaren, K., 305n16, 307n19

MCMC, 642, 670

MDE, 248, 383, 421, 463–468

MDRs, 812–813, 824

MDTA, 156

Mead, R., 1094n12

mean, 1017, 1048

mean absolute error, 88

mean independence, 24, 346

mean independence

assumption, 885

mean square convergence, 68

mean squared error, 1057

mean value theorem, 477

mean vector, 1038

mean vs. median, 616

measurement error, 97–99,

221, 355

measures of central tendency,

1017, 1048

median, 1017, 1048

median regression, 203, 204

median v. mean, 616

Medical Expenditure Panel Survey

(MEPS), 344

Meier, P., 870

Melenberg, B., 204n11, 443, 846,

853, 858n12, 860

MELO estimator, 665

MEPS, 344

Merton, R., 932

Messer, K., 274n14

method of instrumental variables,

222. See also endogeneity

and instrumental variable

estimation

method of moment generating

functions, 459

Index

1177

method of moments, 99, 436,

456–463. See also

generalized method of

moments (GMM) estimation

asymptotic properties, 461–463

basis of, 456

data generating process, 463

estimating parameters of

distributions, 457–461

random sampling, 457–461

method of moments estimator, 458

method of scoring, 555,

692, 1100

method of simulated moments, 784

methodological dilemma, 655

Metropolis-Hastings (M-H)

algorithm, 677, 678

Meyer, B., 871

MGF, 1029

Michigan Panel Study of Income

Dynamics (PSID), 344

microeconometric methods,

681–902

binary choice. See binary choice

censoring. See censoring

discrete choice, 681–832

duration models, 861–862

event counts. See models for

counts of events

limited dependent variables,

833–902

multinomial choice. See

multinomial choice

ordered choice models. See

ordered choice models

sample selection. See sample

selection

treatment effects, 888–898

truncation, 833–845

microeconometrics, 2–3

migration equation, 879–880

Miller, R., 142

Million, A., 3, 195, 345, 411, 540,

569, 571, 705, 735, 794,

807n14, 809, 820, 826, 827

Mills, T., 930n16

Min, C., 142

minimal sufﬁcient statistic, 722

minimization, 247

minimum distance estimator

(MDE), 248, 383, 421,

463–468

minimum expected loss (MELO)

estimator, 665

minimum means squared error

predictor, 53, 54

minimum variance linear unbiased

estimation, 54

minimum variance linear unbiased

estimator (MVLUE), 1060

minimum variance

unbiasedness, 1057

minor, 987

missing at random (MAR), 95

missing completely at random

(MCAR), 94, 735

missing data model, 1104

missing values, 94–97

Mittelhammer, R., 188, 191n4, 433,

474, 542n12, 658n3

mixed estimator, 663n10

mixed ﬁxed growth model for

developing countries, 426

mixed-ﬁxed model, 425

mixed linear model for wages,

646–649

mixed logit model, 771–772

mixed model, 639, 650

mixed (random parameters)

multinomial logit model,

677n19

mixtures of normal

distributions, 459

Mizon, G., 135, 305, 906

MLE, 75–75. See maximum

likelihood estimation (MLE)

MLWin, 642, 655n1

MNL model, 770

MNP model, 770–771

mode, 1017

model building, 138–143

model selection, 140–143

models for counts of events, 682,

760, 802–829

censoring, 811, 813

doctor visits.

See doctor visits

endogenous

variables/endogenous

participation, 826–829

ﬁxed effects, 817–818

functional forms, 807–809

goodness of ﬁt, 804–805

hurdle model, 824–826

negative binomial regression

model, 806–807

overdispersion, 805–806

panel data models, 815–821

Poisson regression model,

803–804

pooled estimator, 816–817

random effects, 818–821

truncation, 810–812

two-part models, 821–826

zero inﬂation models,

821–824, 825

models for panel data, 343–431

advantage of, 426

Anderson and Hsiao’s IV

estimator, 398–400

Arellano and Bond estimator,

400–409

autocorrelation, 388

balanced/unbalanced panels, 348

Bayesian estimation, 674–676

binary choice, 716–738, 744–745

censoring, 860–861

dynamic panel data models,

398–409, 421–426

endogeneity, 394–411

error components model, 371

event counts, 815–821

extensions, 347

FEVD, 365–368

ﬁxed effects model. See ﬁxed

effects model

general modeling framework,

345–346

Hausman and Taylor’s estimator,

394–397

incidental parameters

problem, 413

literature, 344n2

LSVD model, 360

MLE, 573–588, 595–598

model structure, 346–347

multinomial choice, 781–782

nonlinear regression, 411–415

nonspherical disturbances and

robust covariance

estimation, 385–389

nonstationary data, 410–411,

970–971

ordered choice models, 794–798

overview, 343

parameter heterogeneity,

416–426

pooled regression model. See

pooled regression model

random coefﬁcients model,

417–420

random effects model. See

random effects model

sample selection, 883

spatial correlation, 389–394

studies, 344

well-behaved panel data,

348–349

modiﬁed zero-order regression, 95

1178

Index

Mofﬁtt, R., 687n5, 773, 850,

858n, 883

Mohanty, M., 880

moment, 1038–1039

censored normal variable, 847

central, 459, 1018

conditional moment tests, 860

derivatives of log-likelihood, 515

incidentally truncated

distribution, 873

linear regression, 1036

method of moments. See method

of moments

population moment

equation, 483

truncated distribution, 835–837

uncentered, 457

moment equations, 227, 238, 458

moment-free LIML estimator, 250

moment generating function

(MGF), 1029

Mona Lisa (da Vinci), 109

money demand equation, 559–560,

903

Monfort, A., 134n8, 135n10,

542n12, 545, 628n7, 631,

712n24, 858n12, 938

Monte Carlo integration,

623–633

Monte Carlo studies, 615–621

incidental parameters problem,

619–621

least squares vs. LAD, 71–72

mean vs. median, 616

test statistic, 617–618

Moon, H., 410

Moore-Penrose generalized

inverse, 237, 1003, 1004

Moran, P., 391

Moro, D., 305n16

Moshino, G., 305n16

most powerful test, 1063

Mouchart, M., 862n15

Mount, T., 378, 1024n5

mover-stayer model for migration,

879–880

movie box ofﬁce receipts, 152

movie ratings, 786

movie success, 93

moving average form, 911

moving average process, 910

MPC, 132–133, 664

Mroz, T., 116, 708, 878

MSL. See maximum simulated

likelihood (MSL)

Muelbauer, J., 307n19, 311n26

Mullahy, J., 443, 687n5, 821, 824,

825, 826

Muller, M., 607

multicollinearity, 51, 89–91

multinomial choice, 681–682,

761–784

aggregated market share data,

782–784

BLP random parameters model,

782–784

conditional logit model, 766–767

generalized mixed logit model,

772–773

IIA assumption, 767

mixed logit model, 771–772

multinomial logit model, 763–766

multinomial probit model,

770–771

nested logit model, 768–770

panel data, 781–782

stated choice experiment, 782

studies, 761

travel mode choice, 773–779

willingness to pay (WTP),

779–781

multinomial logit model, 763–766

multinomial probit model, 770–771

multiple correlation, 44

multiple equations models. See

systems of equations

multiple equations regression

model, 291

multiple imputation, 96–97

multiple linear regression model,

12. See also linear regression

model

multiple regression, 30

multiplicative heteroscedasticity,

280, 554–557, 858

multivariate distribution,

1038–1040

multivariate Lindeberg-Fuller

central limit theorem, 1083

multivariate Lindeberg-Levy

central limit theorem, 1082

multivariate normal distribution,

1041–1047

multivariate normal population, 608

multivariate normal probability,

627–629

multivariate probit model, 752–755

multivariate regression model,

293, 307

multivariate standard normal

distribution, 1041

multivariate t distribution, 661

Mundlak, Y., 371n11, 381, 382, 727,

798, 860

Mundlak’s approach, 381, 727

Munell’s production model for

gross state product, 418

Munkin, M., 437, 439, 888

Munnell, A., 290, 300, 579

Murdoch, J., 640

Murphy, K., 537, 710, 793, 854,

877n31

Murray, C., 173, 607

MVLUE, 1060

Nagin, D., 652n10, 714n26

Nair-Reichert, U., 290, 426

Nakamura, A., 848n10

Nakamura, M., 848n10

Nakosteen, R., 685, 879

National Institute of Standards and

Technology (NIST), 217

National Longitudinal Survey of

Labor Market Experience

(NLS), 344

natural experiment, 157–158

natural experiments literature,

232, 254

Navy recruits, 790

NB1 form, 808

NB2 form, 808

NBP model, 808

nearest neighbor, 212

negative autocorrelation (Phillips

curve), 904

negative binomial model, 439

negative binomial regression

model, 806–807

negative duration dependence, 865

Negbin 1 (NB1) form, 808

Negbin 2 (NB2) form, 808

Negbin P (NBP) model, 808

neighborhood, 213

Nelder, J., 805, 832, 1094n12

Nelson, C., 295n9, 946n5, 947n6

Nelson, F., 848n10, 858, 858n12

Nelson, R., 204n11

Nerlove, M., 107, 162, 164, 211, 309,

344n2, 373n12, 378, 379n19,

422, 497n14, 763, 901, 923n13

nested logit model, 768–770

nested models, 110

nested random effects, 576–580

Netﬂix, 784

netting out, 34

Neumann, G., 858n12

Newbold, P., 944, 945, 946