Calculate gradients and the inverse of the Hessian matrix of the loglikelihood.
grad.hessinv(theta, p, r)Initial value for proportionality parameter \(\theta\).
Initial value for probability masses \(p_1,\ldots,p_N\) of the discretized baseline distribution \(F\).
vector of ranks of \(y_1,\ldots,y_n\) in the pooled sample \(x_1,\ldots,x_m, y_1,\ldots,y_n\)
gradients of the loglikelihood
the inverse of the Hessian matrix
See the reference below.
Zhong Guan and Cheng Peng (2011), "A rank-based empirical likelihood approach to two-sample proportional odds model and its goodness-of-fit", Journal of Nonparametric Statistics, to appear.