← Back to Search

# Likelihood Approximation By Numerical Integration On Sparse Grids

Florian Heiss, Viktor Winschel

Published 2008 · Mathematics

The calculation of likelihood functions of many econometric models requires the evaluation of integrals without analytical solutions. Approaches for extending Gaussian quadrature to multiple dimensions discussed in the literature are either very specific or suffer from exponentially rising computational costs in the number of dimensions. We propose an extension that is very general and easily implemented, and does not suffer from the curse of dimensionality. Monte Carlo experiments for the mixed logit model indicate the superior performance of the proposed method over simulation techniques.

This paper references

10.1007/s002110200401

Smolyak cubature of given polynomial degree with few nodes for increasing dimension

K. Petras (2003)

10.1016/J.JECONOM.2006.10.012

Masking Identification of Discrete Choice Models Under Simulation Methods

L. Chiou (2007)

Numerical recipes in C

W. Press (2002)

10.2307/2288607

Methods of Numerical Integration

P. Davis (1967)

10.1016/0304-4076(88)90029-2

Econometric illustrations of novel numerical integration strategies for Bayesian inference

J. C. Naylor (1988)

10.1016/J.JECONOM.2007.02.007

Efficient high-dimensional importance sampling

J. Richard (2007)

10.1016/S0165-1889(03)00111-8

Computing equilibrium in OLG models with stochastic production

D. Krüger (2004)

10.2307/2951573

A Method for Smoothing Simulated Moments of Discrete Probabilities in Multinomial Probit Models

Steven Stern (1992)

Classical estimation methods using simulation

V. Hajivassiliou (1994)

10.1016/0885-064X(92)90001-R

Average case complexity of linear multivariate problems I. Theory

H. Wozniakowski (1992)

10.1002/JAE.719

Discrete choice methods with simulation, Kenneth E. Train, Cambridge University Press, 2003, ISBN: 0-521-81696-3, pp. 334

M. Weeks (2003)

10.1016/S0304-4076(99)00032-9

A numerically stable quadrature procedure for the one-factor random-component discrete choice model

L. Lee (2000)

10.1016/S0191-2615(00)00014-X

Quasi-random maximum simulated likelihood estimation of the mixed multinomial logit model

C. Bhat (2000)

Numerical Recipes in C, 2nd Edition

W. Press (1992)

10.1016/S0885-064X(03)00011-6

An encyclopaedia of cubature formulas

R. Cools (2003)

10.1016/S0304-4076(97)00005-5

Statistical inference in the multinomial multiperiod probit model

J. Geweke (1994)

10.1016/0377-0427(95)00232-4

Fully symmetric interpolatory rules for multiple integrals over infinite regions with Gaussian weight

A. Genz (1996)

10.1007/BF01525334

Zur mechanischen Kubatur

Johann Radon (1948)

Quadrature and interpolation formulas for tensor products of certain classes of functions

S. A. Smolyak (1963)

10.1016/s0898-1221(03)90177-5

Applied Computational Economics and Finance

M. Miranda (2002)

10.1016/S0304-4076(98)00057-8

Forecasting new product penetration with flexible substitution patterns

D. Brownstone (1998)

10.1016/S0304-4076(03)00212-4

Alternative sampling methods for estimating multivariate normal probabilities

Z. Sándor (2003)

10.1016/J.JECONOM.2004.08.017

Maximum likelihood estimation of limited and discrete dependent variable models with nested random effects

S. Rabe-Hesketh (2005)

10.1016/S1574-0021(96)01017-9

Monte carlo simulation and numerical integration

J. Geweke (1995)

10.1162/003465398557735

Mixed Logit with Repeated Choices: Households' Choices of Appliance Efficiency Level

David Revelt (1998)

10.1016/J.TRB.2004.10.005

On the use of a Modified Latin Hypercube Sampling (MLHS) method in the estimation of a Mixed Logit Model for vehicle choice

S. Hess (2006)

10.1006/jcom.1995.1001

Explicit Cost Bounds of Algorithms for Multivariate Tensor Product Problems

G. Wasilkowski (1995)

10.1016/0304-4076(93)90049-B

Smooth unbiased multivariate probability simulators for maximum likelihood estimation of limited dependent variable models

A. Boersch-Supan (1993)

10.1016/S0304-4076(97)00014-6

Simulated Maximum Likelihood Estimation of Dynamic Discrete Choice Statistical Models Some Monte Carlo Results

Lung-fei Lee (1997)

10.2307/1912613

A COMPUTATIONALLY EFFICIENT QUADRATURE PROCEDURE FOR THE ONE-FACTOR MULTINOMIAL PROBIT MODEL

J. S. Butler (1982)

10.1090/S0025-5718-68-99866-9

The optimum addition of points to quadrature formulae.

T. Patterson (1968)

10.2307/1913621

A Method of Simulated Moments for Estimation of Discrete Response Models Without Numerical Integration

D. Mcfadden (1989)

Sparse grids.

Bungartz (2004)

10.1002/1099-1255(200009/10)15:5<447::AID-JAE570>3.0.CO;2-1

MIXED MNL MODELS FOR DISCRETE RESPONSE

D. Mcfadden (2000)

10.1093/BIOMET/81.3.624

A note on Gauss—Hermite quadrature

Q. Liu (1994)

Numerical methods in economics

K. Judd (1998)

10.1017/CBO9780511753930

Discrete Choice Methods with Simulation by Kenneth E. Train

K. Train (2003)

10.2307/2005635

Approximate calculation of multiple integrals

A. Stroud (1973)

10.1007/s00607-003-0015-5

Dimension–Adaptive Tensor–Product Quadrature

T. Gerstner (2003)

10.2139/SSRN.758364

Solving, Estimating and Selecting Nonlinear Dynamic Economic Models Without the Curse of Dimensionality

Viktor Winschel (2005)

This paper is referenced by

10.1109/TAES.2013.6558008

Sparse-Grid Quadrature $H_\infty $ Filter for Discrete-Time Systems with Uncertain Noise Statistics

B. Jia (2013)

ONLINE APPENDIX: Vertical Integration and Exclusivity in Platform and Two-Sided Markets

R. Lee (2013)

10.1016/J.PHOTONICS.2011.10.003

Design of robust and efficient photonic switches using topology optimization

Y. Elesin (2012)

10.1561/0800000022

The Composite Marginal Likelihood (CML) Inference Approach with Applications to Discrete and Mixed Dependent Variable Models

C. Bhat (2014)

A Constrained Conditional Likelihood Approach for Estimating the Means of Selected Populations

C. Fuentes (2017)

10.1890/09-1903.1

Individual heterogeneity in studies on marked animals using numerical integration: capture-recapture mixed models.

O. Gimenez (2010)

10.1016/j.jbiomech.2015.11.013

Uncertainty quantification for personalized analyses of human proximal femurs.

H. Wille (2016)

10.2514/6.2013-4947

Sparse-Grid Quadrature H-infinity Filter for Discrete-time Systems with Uncertain Noise Statistics

Bin Jia (2013)

10.1109/I2MTC.2013.6555643

Sparse-grid Quadrature Kalman Filter based on the Kronrod-Patterson rule

Cheng Xiang-hong (2013)

Sparse Grids One-dimensional Multilevel Basis

(2008)

Stability of Controllers for Gaussian Process Forward Models

Julia Vinogradska (2016)

10.2514/6.2010-7588

Sparse Gauss-Hermite Quadrature Filter for Orbit Estimation

B. Jia (2010)

10.1016/J.STRUSAFE.2018.06.007

Reliability-based lifecycle management for corroding pipelines

Mihir A. Mishra (2019)

10.1002/sta4.156

Frequentist and Bayesian inference for Gaussian-log-Gaussian wavelet trees, and statistical signal processing applications

R. Jacobsen (2014)

10.1109/ACC.2010.5531487

Sparse Gauss-Hermite Quadrature filter for spacecraft attitude estimation

Bin Jia (2010)

10.1002/9781118287798.CH11

The Sigma Point Class: The Gauss–Hermite Kalman Filter

Anton J. Haug (2012)

10.1109/ACC.2014.6859199

Gaussian mixture model based high dimensional SLAM utilizing sparse grid quadrature

Matthew R. Turnowicz (2014)

10.3850/978-981-11-2724-3_0827-cd

Probabilistic Modelling for Frequency Response Functions and Transmissibility Functions with Complex Ratio Statistics

Meng-Yun Zhao (2019)

10.1016/J.CMA.2018.03.027

Uncertainty quantification guided robust design for nanoparticles’ morphology

Y. He (2018)

10.1007/978-3-642-16004-2_4

Sparse Grid Quadrature

M. Holtz (2011)

10.1109/ACC.2011.5990851

Salient point quadrature nonlinear filtering

B. Jia (2011)

10.1016/J.JOCM.2013.04.006

The composite marginal likelihood (CML) estimation of panel ordered-response models

Rajesh Paleti (2013)

10.4208/CICP.260111.230911A

A Numerical Comparison Between Quasi-Monte Carlo and Sparse Grid Stochastic Collocation Methods

Juarez S. Azevedo (2012)

10.1063/1.4903729

Maximum entropy analysis of hydraulic pipe networks

Steven H. Waldrip (2014)

10.1063/1.4999153

Computing vibrational energy levels of CH4 with a Smolyak collocation method.

Gustavo Avila (2017)

10.1049/IET-SMT.2019.0317

MASGQF with application to SINS alignment

Chen Qian (2020)

10.1111/biom.12124

Estimating marginal properties of quantitative real-time PCR data using nonlinear mixed models.

D. Gerhard (2014)

Slow Exponential Growth for Clenshaw Curtis Sparse Grids

J. Burkardt (2014)

10.1109/TMTT.2020.2988458

Uncertainty Quantification of Waveguide Dispersion Using Sparse Grid Stochastic Testing

M. Gossye (2020)

Macro-modeling of electromagnetic domains exhibiting geometric and material uncertainty

J. Ochoa (2012)

10.2514/6.2016-0433

Sparse polynomial surrogates for aerodynamic computations with random inputs

E. Savin (2016)

State Space Modelling of Dynamic Choice Behavior with Habit Persistence

Kang Bok Lee (2014)

See more