Abstract
An accurate and efficient numerical approximation of the multivariate normal (MVN) distribution function is necessary for obtaining maximum likelihood estimates for models involving the MVN distribution. Numerical integration through simulation (Monte Carlo) or number-theoretic (quasi-Monte Carlo) techniques is one way to accomplish this task. One popular simulation technique is the Geweke–Hajivassiliou–Keane MVN simulator. This paper reviews this technique and introduces a Mata function that implements it. It also computes analytical first-order derivatives of the simulated probability with respect to the variables and the variance–covariance parameters.
Keywords
References
1.
Bolduc
D.
1999 . A practical technique to estimate multinomial probit models in transportation . Transportation Research, Part B 33 : 63 –79 .
2.
Cappellari
L.
, and
Jenkins
S. P.
2003 . Multivariate probit regression using simulated maximum likelihood . Stata Journal 3 : 278 –294 .
3.
Cappellari
L.
2005 . Software update: st0045_1: Multivariate probit regression using simulated maximum likelihood . Stata Journal 5 : 285 .
4.
Cappellari
L.
2006 . Software update: st0045_2: Multivariate probit regression using simulated maximum likelihood . Stata Journal 6 : 284 .
5.
Fang
K.-T.
, and
Wang
Y.
1994 . Number-theoretic Methods in Statistics. London : Chapman & Hall.
6.
Genz
A.
1992 . Numerical computation of multivariate normal probabilities . Journal of Computational and Graphical Statistics 1 : 141 –149 .
7.
Geweke
J.
1989 . Bayesian inference in econometric models using Monte Carlo integration . Econometrica 57 : 1317 –1339 .
8.
Hajivassiliou
V.
, and
McFadden
D.
1998 . The method of simulated scores for the estimation of LDV models . Econometrica 66 : 863 –896 .
9.
Johnson
N. L.
,
Kotz
S.
, and
Balakrishnan
N.
1994 . Continuous Univariate Distributions , vol. 1 . 2nd ed. New York : Wiley.
10.
Keane
M. P.
1994 . A computationally practical simulation estimator for panel data . Econometrica 62 : 95 –116 .
11.
Lütkepohl
H.
1996 . Handbook of Matrices. Chichester, UK : Wiley.
12.
Magnus
J. R.
, and
Neudecker
H.
1988 . Matrix Differential Calculus with Applications in Statistics and Econometrics. Chichester, UK : Wiley.
13.
Niederreiter
H.
1992 . Random Number Generation and Quasi-Monte Carlo Methods. Philadelphia : SIAM.
14.
Train
K.
2003 . Discrete Choice Methods with Simulation. Cambridge : Cambridge University Press.