Muutke küpsiste eelistusi

Microeconometrics Using Stata [Pehme köide]

4.41/5 (128 hinnangut Goodreads-ist)
(Indiana University, Bloomington, Indiana, USA), (University of California, Davis, USA)
  • Formaat: Paperback / softback, 692 pages, kõrgus x laius: 216x216 mm, kaal: 1452 g
  • Ilmumisaeg: 01-Dec-2008
  • Kirjastus: Stata Press
  • ISBN-10: 1597180483
  • ISBN-13: 9781597180481
Teised raamatud teemal:
  • Pehme köide
  • Hind: 86,94 €*
  • * saadame teile pakkumise kasutatud raamatule, mille hind võib erineda kodulehel olevast hinnast
  • See raamat on trükist otsas, kuid me saadame teile pakkumise kasutatud raamatule.
  • Kogus:
  • Lisa ostukorvi
  • Tasuta tarne
  • Lisa soovinimekirja
Microeconometrics Using StataSuurem pilt
  • Formaat: Paperback / softback, 692 pages, kõrgus x laius: 216x216 mm, kaal: 1452 g
  • Ilmumisaeg: 01-Dec-2008
  • Kirjastus: Stata Press
  • ISBN-10: 1597180483
  • ISBN-13: 9781597180481
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9781597180481.html
Märksõnad:

An outstanding introduction to microeconometrics and how to do microeconometric research using Stata, this book covers topics often left out of microeconometrics textbooks and omitted from basic introductions to Stata. Cameron and Trivedi provide the most complete and up-to-date survey of microeconometric methods available in Stata. They begin by introducing simulation methods and then use them to illustrate features of the estimators and tests described in the rest of the book. They address each topic with an in-depth Stata example and demonstrate how to use Stata’s programming features to implement methods for which Stata does not have a specific command.

List of tables
xxxv
List of figures
xxxvii
Preface xxxix
Stata basics
1(28)
Interactive use
1(1)
Documentation
2(3)
Stata manuals
2(1)
Additional Stata resources
3(1)
The help command
3(1)
The search, findit, and hsearch commands
4(1)
Command syntax and operators
5(5)
Basic command syntax
5(1)
Example: The summarize command
6(1)
Example: The regress command
7(2)
Abbreviations, case sensitivity, and wildcards
9(1)
Arithmetic, relational, and logical operators
9(1)
Error messages
10(1)
Do-files and log files
10(5)
Writing a do-file
10(1)
Running do-files
11(1)
Log files
12(1)
A three-step process
13(1)
Comments and long lines
13(1)
Different implementations of Stata
14(1)
Scalars and matrices
15(1)
Scalars
15(1)
Matrices
15(1)
Using results from Stata commands
16(3)
Using results from the r-class command summarize
16(1)
Using results from the e-class command regress
17(2)
Global and local macros
19(3)
Global macros
19(1)
Local macros
20(1)
Scalar or macro?
21(1)
Looping commands
22(2)
The foreach loop
23(1)
The forvalues loop
23(1)
The while loop
24(1)
The continue command
24(1)
Some useful commands
24(1)
Template do-file
25(1)
User-written commands
25(1)
Stata resources
26(1)
Exercises
26(3)
Data management and graphics
29(42)
Introduction
29(1)
Types of data
29(3)
Text or ASCII data
30(1)
Internal numeric data
30(1)
String data
31(1)
Formats for displaying numeric data
31(1)
Inputting data
32(6)
General principles
32(1)
Inputting data already in Stata format
33(1)
Inputting data from the keyboard
34(1)
Inputting nontext data
34(1)
Inputting text data from a spreadsheet
35(1)
Inputting text data in free format
36(1)
Inputting text data in fixed format
36(1)
Dictionary files
37(1)
Common pitfalls
37(1)
Data management
38(15)
PSID example
38(3)
Naming and labeling variables
41(1)
Viewing data
42(1)
Using original documentation
43(1)
Missing values
43(2)
Imputing missing data
45(1)
Transforming data (generate, replace, egen, recode)
45(1)
The generate and replace commands
46(1)
The egen command
46(1)
The recode command
47(1)
The by prefix
47(1)
Indicator variables
47(1)
Set of indicator variables
48(1)
Interactions
49(1)
Demeaning
50(1)
Saving data
51(1)
Selecting the sample
51(2)
Manipulating datasets
53(4)
Ordering observations and variables
53(1)
Preserving and restoring a dataset
53(1)
Wide and long forms for a dataset
54(1)
Merging datasets
54(2)
Appending datasets
56(1)
Graphical display of data
57(11)
Stata graph commands
57(1)
Example graph commands
57(1)
Saving and exporting graphs
58(1)
Learning how to use graph commands
59(1)
Box-and-whisker plot
60(1)
Histogram
61(1)
Kernel density plot
62(2)
Twoway scatterplots and fitted lines
64(1)
Lowess, kernel, local linear, and nearest-neighbor regression
65(2)
Multiple scatterplots
67(1)
Stata resources
68(1)
Exercises
68(3)
Linear regression basics
71(42)
Introduction
71(1)
Data and data summary
71(8)
Data description
71(1)
Variable description
72(1)
Summary statistics
73(1)
More-detailed summary statistics
74(1)
Tables for data
75(3)
Statistical tests
78(1)
Data plots
78(1)
Regression in levels and logs
79(5)
Basic regression theory
79(1)
OLS regression and matrix algebra
80(1)
Properties of the OLS estimator
81(1)
Heteroskedasticity-robust standard errors
82(1)
Cluster-robust standard errors
82(1)
Regression in logs
83(1)
Basic regression analysis
84(6)
Correlations
84(1)
The regress command
85(1)
Hypothesis tests
86(1)
Tables of output from several regressions
87(1)
Even better tables of regression output
88(2)
Specification analysis
90(10)
Specification tests and model diagnostics
90(1)
Residual diagnostic plots
91(1)
Influential observations
92(1)
Specification tests
93(1)
Test of omitted variables
93(1)
Test of the Box-Cox model
94(1)
Test of the functional form of the conditional mean
95(1)
Heteroskedasticity test
96(1)
Omnibus test
97(1)
Tests have power in more than one direction
98(2)
Prediction
100(5)
In-sample prediction
100(2)
Marginal effects
102(1)
Prediction in logs: The retransformation problem
103(1)
Prediction exercise
104(1)
Sampling weights
105(4)
Weights
106(1)
Weighted mean
106(1)
Weighted regression
107(2)
Weighted prediction and MEs
109(1)
OLS using Mata
109(2)
Stata resources
111(1)
Exercises
111(2)
Simulation
113(34)
Introduction
113(1)
Pseudorandom-number generators: Introduction
114(7)
Uniform random-number generation
114(2)
Draws from normal
116(1)
Draws from t, chi-squared, F, gamma, and beta
117(1)
Draws from binomial, Poisson, and negative binomial
118(1)
Independent (but not identically distributed) draws from binomial
118(1)
Independent (but not identically distributed) draws from Poisson
119(1)
Histograms and density plots
120(1)
Distribution of the sample mean
121(4)
Stata program
122(1)
The simulate command
123(1)
Central limit theorem simulation
123(1)
The postfile command
124(1)
Alternative central limit theorem simulation
125(1)
Pseudorandom-number generators: Further details
125(7)
Inverse-probability transformation
126(1)
Direct transformation
127(1)
Other methods
127(1)
Draws from truncated normal
128(1)
Draws from multivariate normal
129(1)
Direct draws from multivariate normal
129(1)
Transformation using Cholesky decomposition
130(1)
Draws using Markov chain Monte Carlo method
130(2)
Computing integrals
132(3)
Quadrature
133(1)
Monte Carlo integration
133(1)
Monte Carlo integration using different S
134(1)
Simulation for regression: Introduction
135(9)
Simulation example: OLS with X2 errors
135(3)
Interpreting simulation output
138(1)
Unbiasedness of estimator
138(1)
Standard errors
138(1)
t statistic
138(1)
Test size
139(1)
Number of simulations
140(1)
Variations
140(1)
Different sample size and number of simulations
140(1)
Test power
140(1)
Different error distributions
141(1)
Estimator inconsistency
141(1)
Simulation with endogenous regressors
142(2)
Stata resources
144(1)
Exercises
144(3)
GLS regression
147(24)
Introduction
147(1)
GLS and FGLS regression
147(3)
GLS for heteroskedastic errors
147(1)
GLS and FGLS
148(1)
Weighted least squares and robust standard errors
149(1)
Leading examples
149(1)
Modeling heteroskedastic data
150(6)
Simulated dataset
150(1)
OLS estimation
151(1)
Detecting heteroskedasticity
152(2)
FGLS estimation
154(2)
WLS estimation
156(1)
System of linear regressions
156(7)
SUR model
156(1)
The sureg command
157(1)
Application to two categories of expenditures
158(2)
Robust standard errors
160(1)
Testing cross-equation constraints
161(1)
Imposing cross-equation constraints
162(1)
Survey data: Weighting, clustering, and stratification
163(6)
Survey design
164(3)
Survey mean estimation
167(1)
Survey linear regression
167(2)
Stata resources
169(1)
Exercises
169(2)
Linear instrumental-variables regression
171(34)
Introduction
171(1)
IV estimation
171(6)
Basic IV theory
171(2)
Model setup
173(1)
IV estimators: IV, 2SLS, and GMM
174(1)
Instrument validity and relevance
175(1)
Robust standard-error estimates
176(1)
IV example
177(11)
The ivregress command
177(1)
Medical expenditures with one endogenous regressor
178(1)
Available instruments
179(1)
IV estimation of an exactly identified model
180(1)
IV estimation of an overidentified model
181(1)
Testing for regressor endogeneity
182(3)
Tests of overidentifying restrictions
185(1)
IV estimation with a binary endogenous regressor
186(2)
Weak instruments
188(9)
Finite-sample properties of IV estimators
188(1)
Weak instruments
189(1)
Diagnostics for weak instruments
189(1)
Formal tests for weak instruments
190(1)
The estat firststage command
191(1)
Just-identified model
191(2)
Overidentified model
193(2)
More than one endogenous regressor
195(1)
Sensitivity to choice of instruments
195(2)
Better inference with weak instruments
197(4)
Conditional tests and confidence intervals
197(2)
LIML estimator
199(1)
Jackknife IV estimator
199(1)
Comparison of 2SLS, LIML, JIVE, and GMM
200(1)
3SLS systems estimation
201(2)
Stata resources
203(1)
Exercises
203(2)
Quantile regression
205(24)
Introduction
205(1)
QR
205(3)
Conditional quantiles
206(1)
Computation of QR estimates and standard errors
207(1)
The qreg, bsqreg, and sqreg commands
207(1)
QR for medical expenditures data
208(8)
Data summary
208(1)
QR estimates
209(1)
Interpretation of conditional quantile coefficients
210(1)
Retransformation
211(1)
Comparison of estimates at different quantiles
212(1)
Heteroskedasticity test
213(1)
Hypothesis tests
214(1)
Graphical display of coefficients over quantiles
215(1)
QR for generated heteroskedastic data
216(4)
Simulated dataset
216(3)
QR estimates
219(1)
QR for count data
220(6)
Quantile count regression
221(1)
The qcount command
222(1)
Summary of doctor visits data
222(2)
Results from QCR
224(2)
Stata resources
226(1)
Exercises
226(3)
Linear panel-data models: Basics
229(52)
Introduction
229(1)
Panel-data methods overview
229(5)
Some basic considerations
230(1)
Some basic panel models
231(1)
Individual-effects model
231(1)
Fixed-effects model
231(1)
Random-effects model
232(1)
Pooled model or population-averaged model
232(1)
Two-way-effects model
232(1)
Mixed linear models
233(1)
Cluster-robust inference
233(1)
The xtreg command
233(1)
Stata linear panel-data commands
234(1)
Panel-data summary
234(14)
Data description and summary statistics
234(2)
Panel-data organization
236(1)
Panel-data description
237(1)
Within and between variation
238(3)
Time-series plots for each individual
241(1)
Overall scatterplot
242(1)
Within scatterplot
243(1)
Pooled OLS regression with cluster-robust standard errors
244(1)
Time-series autocorrelations for panel data
245(2)
Error correlation in the RE model
247(1)
Pooled or population-averaged estimators
248(3)
Pooled OLS estimator
248(1)
Pooled FGLS estimator or population-averaged estimator
248(1)
The xtreg, pa command
249(1)
Application of the xtreg, pa command
250(1)
Within estimator
251(3)
Within estimator
251(1)
The xtreg, fe command
251(1)
Application of the xtreg, fe command
252(1)
Least-squares dummy-variables regression
253(1)
Between estimator
254(1)
Between estimator
254(1)
Application of the xtreg, be command
255(1)
RE estimator
255(2)
RE estimator
255(1)
The xtreg, re command
256(1)
Application of the xtreg, re command
256(1)
Comparison of estimators
257(6)
Estimates of variance components
257(1)
Within and between R-squared
258(1)
Estimator comparison
258(1)
Fixed effects versus random effects
259(1)
Hausman test for fixed effects
260(1)
The hausman command
260(1)
Robust Hausman test
261(1)
Prediction
262(1)
First-difference estimator
263(2)
First-difference estimator
263(1)
Strict and weak exogeneity
264(1)
Long panels
265(9)
Long-panel dataset
265(1)
Pooled OLS and PFGLS
266(1)
The xtpcse and xtgls commands
267(1)
Application of the xtgls, xtpcse, and xtscc commands
268(2)
Separate regressions
270(1)
FE and RE models
271(1)
Unit roots and cointegration
272(2)
Panel-data management
274(4)
Wide-form data
274(1)
Convert wide form to long form
274(1)
Convert long form to wide form
275(1)
An alternative wide-form data
276(2)
Stata resources
278(1)
Exercises
278(3)
Linear panel-data models: Extensions
281(32)
Introduction
281(1)
Panel IV estimation
281(3)
Panel IV
281(1)
The xtivreg command
282(1)
Application of the xtivreg command
282(2)
Panel IV extensions
284(1)
Hausman-Taylor estimator
284(3)
Hausman-Taylor estimator
284(1)
The xthtaylor command
285(1)
Application of the xthtaylor command
285(2)
Arellano-Bond estimator
287(11)
Dynamic model
287(1)
IV estimation in the FD model
288(1)
The xtabond command
289(1)
Arellano-Bond estimator: Pure time series
290(2)
Arellano-Bond estimator: Additional regressors
292(2)
Specification tests
294(1)
The xtdpdsys command
295(2)
The xtdpd command
297(1)
Mixed linear models
298(8)
Mixed linear model
298(1)
The xtmixed command
299(1)
Random-intercept model
300(1)
Cluster-robust standard errors
301(1)
Random-slopes model
302(1)
Random-coefficients model
303(1)
Two-way random-effects model
304(2)
Clustered data
306(5)
Clustered dataset
306(1)
Clustered data using nonpanel commands
306(1)
Clustered data using panel commands
307(3)
Hierarchical linear models
310(1)
Stata resources
311(1)
Exercises
311(2)
Nonlinear regression methods
313(38)
Introduction
313(1)
Nonlinear example: Doctor visits
314(2)
Data description
314(1)
Poisson model description
315(1)
Nonlinear regression methods
316(7)
MLE
316(1)
The poisson command
317(1)
Postestimation commands
318(1)
NLS
319(1)
The nl command
319(2)
GLM
321(1)
The glm command
321(1)
Other estimators
322(1)
Different estimates of the VCE
323(6)
General framework
323(1)
The vce() option
324(1)
Application of the vce() option
324(2)
Default estimate of the VCE
326(1)
Robust estimate of the VCE
326(1)
Cluster---robust estimate of the VCE
327(1)
Heteroskedasticity- and autocorrelation-consistent estimate of the VCE
328(1)
Bootstrap standard errors
328(1)
Statistical inference
329(1)
Prediction
329(4)
The predict and predictnl commands
329(1)
Application of predict and predictnl
330(1)
Out-of-sample prediction
331(1)
Prediction at a specified value of one of the regressors
332(1)
Prediction at a specified value of all the regressors
332(1)
Prediction of other quantities
333(1)
Marginal effects
333(12)
Calculus and finite-difference methods
334(1)
MEs estimates AME, MEM, and MER
334(1)
Elasticities and semielasticities
335(1)
Simple interpretations of coefficients in single-index models
336(1)
The mfx command
337(1)
MEM: Marginal effect at mean
337(1)
Comparison of calculus and finite-difference methods
338(1)
MER: Marginal effect at representative value
338(1)
AME: Average marginal effect
339(1)
Elasticities and semielasticities
340(2)
AME computed manually
342(1)
Polynomial regressors
343(1)
Interacted regressors
344(1)
Complex interactions and nonlinearities
344(1)
Model diagnostics
345(4)
Goodness-of-fit measures
345(1)
Information criteria for model comparison
346(1)
Residuals
347(1)
Model-specification tests
348(1)
Stata resources
349(1)
Exercises
349(2)
Nonlinear optimization methods
351(34)
Introduction
351(1)
Newton-Raphson method
351(4)
NR method
351(1)
NR method for Poisson
352(1)
Poisson NR example using Mata
353(1)
Core Mata code for Poisson NR iterations
353(1)
Complete Stata and Mata code for Poisson NR iterations
353(2)
Gradient methods
355(4)
Maximization options
355(1)
Gradient methods
356(1)
Messages during iterations
357(1)
Stopping criteria
357(1)
Multiple maximums
357(1)
Numerical derivatives
358(1)
The ml command: If method
359(5)
The ml command
360(1)
The If method
360(1)
Poisson example: Single-index model
361(1)
Negative binomial example: Two-index model
362(1)
NLS example: Nonlikelihood model
363(1)
Checking the program
364(7)
Program debugging using ml check and ml trace
365(1)
Getting the program to run
366(1)
Checking the data
366(1)
Multicollinearity and near collinearity
367(1)
Multiple optimums
368(1)
Checking parameter estimation
369(1)
Checking standard-error estimation
370(1)
The ml command: d0, d1, and d2 methods
371(5)
Evaluator functions
371(2)
The d0 method
373(1)
The d1 method
374(1)
The d1 method with the robust estimate of the VCE
374(1)
The d2 method
375(1)
The Mata optimize() function
376(3)
Type d and v evaluators
376(1)
Optimize functions
377(1)
Poisson example
377(1)
Evaluator program for Poisson MLE
377(1)
The optimize() function for Poisson MLE
378(1)
Generalized method of moments
379(4)
Definition
380(1)
Nonlinear IV example
380(1)
GMM using the Mata optimize() function
381(2)
Stata resources
383(1)
Exercises
383(2)
Testing methods
385(30)
Introduction
385(1)
Critical values and p-values
385(4)
Standard normal compared with Student's t
386(1)
Chi-squared compared with F
386(1)
Plotting densities
386(2)
Computing p-values and critical values
388(1)
Which distributions does Stata use?
389(1)
Wald tests and confidence intervals
389(10)
Wald test of linear hypotheses
389(2)
The test command
391(1)
Test single coefficient
392(1)
Test several hypotheses
392(1)
Test of overall significance
393(1)
Test calculated from retrieved coefficients and VCE
393(1)
One-sided Wald tests
394(1)
Wald test of nonlinear hypotheses (delta method)
395(1)
The testnl command
395(1)
Wald confidence intervals
396(1)
The lincom command
396(1)
The nlcom command (delta method)
397(1)
Asymmetric confidence intervals
398(1)
Likelihood-ratio tests
399(3)
Likelihood-ratio tests
399(2)
The Irtest command
401(1)
Direct computation of LR tests
401(1)
Lagrange multiplier test (or score test)
402(3)
LM tests
402(1)
The estat command
403(1)
LM test by auxiliary regression
403(2)
Test size and power
405(6)
Simulation DGP: OLS with chi-squared errors
405(1)
Test size
406(1)
Test power
407(3)
Asymptotic test power
410(1)
Specification tests
411(2)
Moment-based tests
411(1)
Information matrix test
411(1)
Chi-squared goodness-of-fit test
412(1)
Overidentifying restrictions test
412(1)
Hausman test
412(1)
Other tests
413(1)
Stata resources
413(1)
Exercises
413(2)
Bootstrap methods
415(30)
Introduction
415(1)
Bootstrap methods
415(2)
Bootstrap estimate of standard error
415(1)
Bootstrap methods
416(1)
Asymptotic refinement
416(1)
Use the bootstrap with caution
416(1)
Bootstrap pairs using the vce(bootstrap) option
417(7)
Bootstrap-pairs method to estimate VCE
417(1)
The vce(bootstrap) option
418(1)
Bootstrap standard-errors example
418(1)
How many bootstraps?
419(1)
Clustered bootstraps
420(1)
Bootstrap confidence intervals
421(1)
The postestimation estat bootstrap command
422(1)
Bootstrap confidence-intervals example
423(1)
Bootstrap estimate of bias
423(1)
Bootstrap pairs using the bootstrap command
424(7)
The bootstrap command
424(1)
Bootstrap parameter estimate from a Stata estimation command
425(1)
Bootstrap standard error from a Stata estimation command
426(1)
Bootstrap standard error from a user-written estimation command
426(1)
Bootstrap two-step estimator
427(2)
Bootstrap Hausman test
429(1)
Bootstrap standard error of the coefficient of variation
430(1)
Bootstraps with asymptotic refinement
431(3)
Percentile-t method
431(1)
Percentile-t Wald test
432(1)
Percentile-t Wald confidence interval
433(1)
Bootstrap pairs using bsample and simulate
434(2)
The bsample command
434(1)
The bsample command with simulate
434(2)
Bootstrap Monte Carlo exercise
436(1)
Alternative resampling schemes
436(5)
Bootstrap pairs
437(1)
Parametric bootstrap
437(2)
Residual bootstrap
439(1)
Wild bootstrap
440(1)
Subsampling
441(1)
The jackknife
441(1)
Jackknife method
441(1)
The vce(jackknife) option and the jackknife command
442(1)
Stata resources
442(1)
Exercises
442(3)
Binary outcome models
445(32)
Introduction
445(1)
Some parametric models
445(1)
Basic model
445(1)
Logit, probit, linear probability, and clog-log models
446(1)
Estimation
446(3)
Latent-variable interpretation and identification
447(1)
ML estimation
447(1)
The logit and probit commands
448(1)
Robust estimate of the VCE
448(1)
OLS estimation of LPM
448(1)
Example
449(3)
Data description
449(1)
Logit regression
450(1)
Comparison of binary models and parameter estimates
451(1)
Hypothesis and specification tests
452(5)
Wald tests
453(1)
Likelihood-ratio tests
453(1)
Additional model-specification tests
454(1)
Lagrange multiplier test of generalized logit
454(1)
Heteroskedastic probit regression
455(1)
Model comparison
456(1)
Goodness of fit and prediction
457(5)
Pseudo-R2 measure
457(1)
Comparing predicted probabilities with sample frequencies
457(2)
Comparing predicted outcomes with actual outcomes
459(1)
The predict command for fitted probabilities
460(1)
The prvalue command for fitted probabilities
461(1)
Marginal effects
462(3)
Marginal effect at a representative value (MER)
462(1)
Marginal effect at the mean (MEM)
463(1)
Average marginal effect (AME)
464(1)
The prchange command
464(1)
Endogenous regressors
465(7)
Example
465(1)
Model assumptions
466(1)
Structural-model approach
467(1)
The ivprobit command
467(1)
Maximum likelihood estimates
468(1)
Two-step sequential estimates
469(2)
IVs approach
471(1)
Grouped data
472(3)
Estimation with aggregate data
473(1)
Grouped-data application
473(2)
Stata resources
475(1)
Exercises
475(2)
Multinomial models
477(44)
Introduction
477(1)
Multinomial models overview
477(3)
Probabilities and MEs
477(1)
Maximum likelihood estimation
478(1)
Case-specific and alternative-specific regressors
479(1)
Additive random-utility model
479(1)
Stata multinomial model commands
480(1)
Multinomial example: Choice of fishing mode
480(4)
Data description
480(3)
Case-specific regressors
483(1)
Alternative-specific regressors
483(1)
Multinomial logit model
484(5)
The mlogit command
484(1)
Application of the mlogit command
485(1)
Coefficient interpretation
486(1)
Predicted probabilities
487(1)
MEs
488(1)
Conditional logit model
489(7)
Creating long-form data from wide-form data
489(2)
The asclogit command
491(1)
The clogit command
491(1)
Application of the asclogit command
492(1)
Relationship to multinomial logit model
493(1)
Coefficient interpretation
493(1)
Predicted probabilities
494(1)
MEs
494(2)
Nested logit model
496(7)
Relaxing the independence of irrelevant alternatives assumption
497(1)
NL model
497(1)
The nlogit command
498(1)
Model estimates
499(2)
Predicted probabilities
501(1)
MEs
501(1)
Comparison of logit models
502(1)
Multinomial probit model
503(5)
MNP
503(1)
The mprobit command
503(1)
Maximum simulated likelihood
504(1)
The asmprobit command
505(1)
Application of the asmprobit command
505(2)
Predicted probabilities and MEs
507(1)
Random-parameters logit
508(2)
Random-parameters logit
508(1)
The mixlogit command
508(1)
Data preparation for mixlogit
509(1)
Application of the mixlogit command
509(1)
Ordered outcome models
510(4)
Data summary
511(1)
Ordered outcomes
512(1)
Application of the ologit command
512(1)
Predicted probabilities
513(1)
MEs
513(1)
Other ordered models
514(1)
Multivariate outcomes
514(4)
Bivariate probit
515(2)
Nonlinear SUR
517(1)
Stata resources
518(1)
Exercises
518(3)
Tobit and selection models
521(32)
Introduction
521(1)
Tobit model
521(3)
Regression with censored data
521(1)
Tobit model setup
522(1)
Unknown censoring point
523(1)
Tobit estimation
523(1)
ML estimation in Stata
524(1)
Tobit model example
524(7)
Data summary
524(1)
Tobit analysis
525(1)
Prediction after tobit
526(1)
Marginal effects
527(1)
Left-truncated, left-censored, and right-truncated examples
527(1)
Left-censored case computed directly
528(1)
Marginal impact on probabilities
529(1)
The ivtobit command
530(1)
Additional commands for censored regression
530(1)
Tobit for lognormal data
531(7)
Data example
531(1)
Setting the censoring point for data in logs
532(1)
Results
533(1)
Two-limit tobit
534(1)
Model diagnostics
534(1)
Tests of normality and homoskedasticity
535(1)
Generalized residuals and scores
535(1)
Test of normality
536(1)
Test of homoskedasticity
537(1)
Next step?
538(1)
Two-part model in logs
538(3)
Model structure
538(1)
Part 1 specification
539(1)
Part 2 of the two-part model
540(1)
Selection model
541(6)
Model structure and assumptions
541(2)
ML estimation of the sample-selection model
543(1)
Estimation without exclusion restrictions
543(2)
Two-step estimation
545(1)
Estimation with exclusion restrictions
546(1)
Prediction from models with outcome in logs
547(3)
Predictions from tobit
548(1)
Predictions from two-part model
548(1)
Predictions from selection model
549(1)
Stata resources
550(1)
Exercises
550(3)
Count-data models
553(48)
Introduction
553(1)
Features of count data
553(4)
Generated Poisson data
554(1)
Overdispersion and negative binomial data
555(1)
Modeling strategies
556(1)
Estimation methods
557(1)
Empirical example 1
557(28)
Data summary
557(1)
Poisson model
558(1)
Poisson model results
559(1)
Robust estimate of VCE for Poisson MLE
560(1)
Test of overdispersion
561(1)
Coefficient interpretation and marginal effects
562(1)
NB2 model
562(1)
NB2 model results
563(2)
Fitted probabilities for Poisson and NB2 models
565(1)
The countfit command
565(2)
The prvalue command
567(1)
Discussion
567(1)
Generalized NB model
567(1)
Nonlinear least-squares estimation
568(1)
Hurdle model
569(2)
Variants of the hurdle model
571(1)
Application of the hurdle model
571(4)
Finite-mixture models
575(1)
FMM specification
575(1)
Simulated FMM sample with comparisons
575(2)
ML estimation of the FMM
577(1)
The fmm command
578(1)
Application: Poisson finite-mixture model
578(1)
Interpretation
579(1)
Comparing marginal effects
580(2)
Application: NB finite-mixture model
582(2)
Model selection
584(1)
Cautionary note
585(1)
Empirical example 2
585(6)
Zero-inflated data
585(1)
Models for zero-inflated data
586(1)
Results for the NB2 model
587(1)
The prcouuts command
588(1)
Results for ZINB
589(1)
Model comparison
590(1)
The countfit command
590(1)
Model comparison using countfit
590(1)
Models with endogenous regressors
591(7)
Structural-model approach
592(1)
Model and assumptions
592(1)
Two-step estimation
593(1)
Application
593(3)
Nonlinear IV method
596(2)
Stata resources
598(1)
Exercises
598(3)
Nonlinear panel models
601(30)
Introduction
601(1)
Nonlinear panel-data overview
601(3)
Some basic nonlinear panel models
601(1)
FE models
602(1)
RE models
602(1)
Pooled models or population-averaged models
602(1)
Comparison of models
603(1)
Dynamic models
603(1)
Stata nonlinear panel commands
603(1)
Nonlinear panel-data example
604(3)
Data description and summary statistics
604(2)
Panel-data organization
606(1)
Within and between variation
606(1)
FE or RE model for these data?
607(1)
Binary outcome models
607(10)
Panel summary of the dependent variable
607(1)
Pooled logit estimator
608(1)
The xtlogit command
609(1)
The xtgee command
610(1)
PA logit estimator
610(1)
RE logit estimator
611(2)
FE logit estimator
613(2)
Panel logit estimator comparison
615(1)
Prediction and marginal effects
616(1)
Mixed-effects logit estimator
616(1)
Tobit model
617(2)
Panel summary of the dependent variable
617(1)
RE tobit model
617(1)
Generalized tobit models
618(1)
Parametric nonlinear panel models
619(1)
Count-data models
619(9)
The xtpoisson command
619(1)
Panel summary of the dependent variable
620(1)
Pooled Poisson estimator
620(1)
PA Poisson estimator
621(1)
RE Poisson estimators
622(2)
FE Poisson estimator
624(2)
Panel Poisson estimators comparison
626(1)
Negative binomial estimators
627(1)
Stata resources
628(1)
Exercises
629(2)
Programming in Stata
631(16)
Stata matrix commands
631(6)
Stata matrix overview
631(1)
Stata matrix input and output
631(1)
Matrix input by hand
631(1)
Matrix input from Stata estimation results
632(1)
Stata matrix subscripts and combining matrices
633(1)
Matrix operators
634(1)
Matrix functions
634(1)
Matrix accumulation commands
635(1)
OLS using Stata matrix commands
636(1)
Programs
637(6)
Simple programs (no arguments or access to results)
637(1)
Modifying a program
638(1)
Programs with positional arguments
638(1)
Temporary variables
639(1)
Programs with named positional arguments
639(1)
Storing and retrieving program results
640(1)
Programs with arguments using standard Stata syntax
641(1)
Ado-files
642(1)
Program debugging
643(4)
Some simple tips
644(1)
Error messages and return code
644(1)
Trace
645(2)
Mata
647(14)
How to run Mata
647(2)
Mata commands in Mata
647(1)
Mata commands in Stata
648(1)
Stata commands in Mata
648(1)
Interactive versus batch use
648(1)
Mata help
648(1)
Mata matrix commands
649(9)
Mata matrix input
649(1)
Matrix input by hand
649(1)
Identity matrices, unit vectors, and matrices of constants
650(1)
Matrix input from Stata data
651(1)
Matrix input from Stata matrix
651(1)
Stata interface functions
652(1)
Mata matrix operators
652(1)
Element-by-element operators
652(1)
Mata functions
653(1)
Scalar and matrix functions
653(1)
Matrix inversion
654(1)
Mata cross products
655(1)
Mata matrix subscripts and combining matrices
655(2)
Transferring Mata data and matrices to Stata
657(1)
Creating Stata matrices from Mata matrices
657(1)
Creating Stata data from a Mata vector
657(1)
Programming in Mata
658(3)
Declarations
658(1)
Mata program
658(1)
Mata program with results output to Stata
659(1)
Stata program that calls a Mata program
659(1)
Using Mata in ado-files
660(1)
Glossary of abbreviations 661(4)
References 665(8)
Author index 673(4)
Subject index 677
University of California, California, USA Indiana University, Bloomington, Indiana, USA