lph: Compute solution path for l_infinity or l1 constraints

Description Usage Arguments Details References

View source: R/gmminf.R

Description

Computes the vector of optimal sensitivities at each knot of the solution path that traces out the optimal bias-variance frontier when the set C takes the form c=B*gamma with the lp norm of gamma is bounded by a constant, for p=1, or p=Inf. This path is used as an input to OptEstimator.

Usage

1
lph(eo, B, p = Inf)

Arguments

eo

List containing initial estimates with the following components:

Sig

Estimate of variance of the moment condition, matrix with dimension d_g by d_g, where d_g is the number of moments

G

Estimate of derivative of the moment condition, matrix with dimension d_g by d_theta, where d_theta is the dimension of theta

H

Estimate of derivative of h(theta). A vector of length d_theta

n

sample size

h_init

Estimate of h(theta)

k_init

Initial sensitivity

g_init

Moment condition evaluated at initial estimate

B

matrix B with full rank and dimension d_g by d_gamma that determines the set C, where d_gamma is the number of invalid moments, and d_g is the number of moments

p

Parameter determining which ell_p norm to use, one of 1, or Inf.

Details

The algorithm is described in Appendix A of Armstrong and Kolesár (2018)

References

Armstrong, T. B., and M. Kolesár (2018): Sensitivity Analysis Using Approximate Moment Condition Models, Unpublished manuscript


kolesarm/GMMSensitivity documentation built on Jan. 17, 2019, 12:44 a.m.