draw.sv.init {depCensoring} | R Documentation |
Draw initial set of starting values for optimizing the expected improvement.
Description
Used in the M-step (get.starting.values.R). ToDo: Adapt this code so as to also perform sample space contractions as in the MatLab implementation of Bei (2024).
Usage
draw.sv.init(theta.hash, dir, hyperparams, EI.fun)
Arguments
theta.hash |
Tentative optimal value for theta, i.e., the largest or smallest feasible value for theta (if dir = 1 or dir = -1, respectively). A 'feasible value' is one that satisfies all moment restrictions. |
dir |
Search direction. |
hyperparams |
List of hyperparameters. |
EI.fun |
Function used to compute the expected improvement. See also
|
Value
Initial set of starting values.
References
Bei, X. (2024). Local linearieation based subvector inference in moment inequality models. Journal of Econometrics. 238:105549-
[Package depCensoring version 0.1.7 Index]