gbnlpolyit1

Usage

Overview

Non linear polyit estimation. Minimize the negative log-likelihood

sum_{h=0}^{L-1} log(A+h) - sum_{l=1}^L sum_{h=0}^{n_l-1} log(a_l+h)

for the Polya specification or

L log(A) - sum_{l=1}^L n_l log(a_l)

for the multinomial specification, where A = sum_{l=1}^L a_l and L is the number of alternatives. The input data file should contain L rows, one for each alternative, of the type n x1 ... XN. The first column contains the dependent variable (# of observations) and the other columns the independent variables. The model is specified by a function a_l=g(x1,x2...) where x1,.. XN stands for the first, second .. N-th column of independent variables.

Options

-O

type of output (default 0)

-F

input fields separators (default " \t")

-V

standard errors and p-scores of diff. from zero using bootstrap

-r

number of replicas (default 20)

-v

verbosity level (default 0)

-R

set the rng seed (default 0)

-M

set the model to use (default 0) |

-A

MLL optimization options (default 0.01,0.1,100,1e-6,1e-6,5) fields are step,tol,iter,eps,msize,algo. Empty fields for default

step

initial step size of the searching algorithm

tol

line search tolerance iter: maximum number of iterations

eps

gradient tolerance : stopping criteria ||gradient||<eps

algo

optimization methods: 0 Fletcher-Reeves, 1 Polak-Ribiere, 2 Broyden-Fletcher-Goldfarb-Shanno, 3 Steepest descent, 4 simplex, 5 Broyden-Fletcher-Goldfarb-Shanno-2