getBeta: Beta optimization routing

In gldrm: Generalized Linear Density Ratio Models

Beta optimization routing

Description

Beta optimization routing

Usage

getBeta(
  x,
  y,
  spt,
  ySptIndex,
  f0,
  linkinv,
  mu.eta,
  offset,
  sampprobs,
  betaStart,
  thStart,
  thetaControl = theta.control(),
  betaControl = beta.control()
)

Arguments

x	Covariate matrix.
y	Response vector.
spt	Vector of unique observed support points in the response.
ySptIndex	Index of each y value within the spt vector.
f0	Current values of f0.
linkinv	Inverse link function.
mu.eta	Derivative of inverse link function.
offset	Vector of known offset values to be added to the linear combination (x' beta) for each observation. Mostly intended for likelihood ratio and score confidence intervals.
sampprobs	Optional matrix of sampling probabilities.
betaStart	Starting values for beta (typically the estimates from the previous iteration).
thStart	Starting theta values. Needs to be a list of values matching the output of the getTheta function.
thetaControl	A "thetaControl" object returned from the theta.control function.
betaControl	A "betaControl" object returned from the beta.control function.

Value

A list containing the following:

• beta Updated values.

• mu Updated mean for each observation.

• th Updated list returned from the getTheta function.

• llik Updated log-likelihood.

• iter Number of iterations until convergence. (Will always be one unless maxiter is increased to something greater than one using the betaControl argument.)

• conv Convergence indicator. (Will always be FALSE unless maxiter is increased to something greater than one using the betaControl argument.)

gldrm documentation built on May 29, 2024, 4:28 a.m.