Using penalized likelihood to select parameters in a random coefficients multinomial logit model

This paper is about estimating a random coefficients logit model in which the distribution of each coefficient characterized by finitely many parameters, some may be zero. The gives conditions under which, with probability approaching 1 as sample size increases, penalized maximum likelihood (PML) estimation adaptive LASSO (AL) penalty distinguishes correctly between zero and non-zero parameters. also PML reduces asymptotic mean-square error any continuously differentiable function model’s describes method for computing estimates presents results Monte Carlo experiments that illustrate their performance. It choice among brands butter margarine British groceries market.