Solving Finite Mixture Models: Efficient Computation in Economics Under Serial and Parallel Execution

Many economic models are completed by finding a parameter vector θ that optimizes a function f(θ), a task that can only be accomplished by iterating from a starting vector θ0. Use of a generic iterative optimizer to carry out this task can waste enormous amounts of computation when applied to a class of problems defined here as finite mixture models. The finite mixture class is large and important in economics and eliminating wasted computations requires only limited changes to standard code. Further, the approach described here greatly increases gains from parallel execution and opens possibilities for re-writing objective functions to make further efficiency gains.

[1]  N. Shephard,et al.  Computationally intensive econometrics using a distributed matrix-programming language , 2002, Philosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[2]  Gerard Debreu,et al.  A Social Equilibrium Existence Theorem* , 1952, Proceedings of the National Academy of Sciences.

[3]  William H. Press,et al.  Numerical recipes in C. The art of scientific computing , 1987 .

[4]  Christopher A. Swann,et al.  Maximum Likelihood Estimation Using Parallel Computing: An Introduction to MPI , 2002 .

[5]  A. E. Fincham,et al.  Parallel Computation , 1999, Algorithms and Theory of Computation Handbook.

[6]  Anna Nagurney,et al.  Chapter 7 Parallel computation , 1996 .

[7]  V. J. Hotz,et al.  Conditional Choice Probabilities and the Estimation of Dynamic Models , 1993 .

[8]  Zvi Eckstein,et al.  ESTIMATING A MARKET EQUILIBRIUM SEARCH MODEL FROM PANEL DATA ON INDIVIDUALS , 1990 .

[9]  Christopher A. Swann,et al.  Software for parallel computing: the LAM implementation of MPI , 2001 .

[10]  D. McFadden,et al.  MIXED MNL MODELS FOR DISCRETE RESPONSE , 2000 .

[11]  W. Press,et al.  Numerical Recipes: The Art of Scientific Computing , 1987 .

[12]  S. Goldfeld,et al.  Maximization by Quadratic Hill-Climbing , 1966 .

[13]  J. Heckman,et al.  A Method for Minimizing the Impact of Distributional Assumptions in Econometric Models for Duration Data , 1984 .

[14]  Donghoon Lee,et al.  An Estimable Dynamic General Equilibrium Model of Work, Schooling, and Occupational Choice , 2005 .

[15]  K. Judd.  Numerical methods in economics , 1998 .

[16]  Andrew T. Ching,et al.  Bayesian Estimation of Dynamic Discrete Choice Models , 2009 .

[17]  Victor Aguirregabiria,et al.  Swapping the Nested Fixed-Point Algorithm: a Class of Estimators for Discrete Markov Decision Models , 2002 .

[18]  Peter Arcidiacono,et al.  Finite Mixture Distributions, Sequential Likelihood and the EM Algorithm , 2003 .

[19]  Jose V Rios-Rul,et al.  Computation of Equilibria in Heterogenous Agent Models: An Introduction , 1999 .

[20]  Gerard Debreu.  Mathematical Economics: A social equilibrium existence theorem , 1983 .

[21]  K Schittkowski.  NLPQLP : A New Fortran Implementation of a Sequential Quadratic Programming Algorithm for Parallel Computing , 2001 .