Current methods of estimating the random coefficients logit model employ simulations of the distribution of the taste parameters through pseudo-random sequences. These methods suffer from difficulties in estimating correlationsbetween parameters and computational limitations such as the curse of dimensionality. This paper provides a solution to these problems by approximating the integral expression of the expected choice probability using a multivariateextension of the Laplace approximation. Simulation results reveal that our method performs very well, both in terms of accuracy and computational time.
Using a Laplace approximation to estimate the random coefficients logit model by non-linear least squares
3 January 2006
Working Paper (CWP01/06)