nsZINB: Neighborhood selection for zero-inflated negative binomial...
In yliu433/scZINB: Graphical model estimation for zero-inflated count data

Description Usage Arguments Value See Also

Estimate the moral graph using the penalized ZINB regression based on the zero-inflated count sample data

nsZINB(dat, filter = NULL, bic = "extBIC", unpenalizedx = NULL,
  unpenalizedz = NULL, lambdas = NULL, taus = NULL, nlambda = 30,
  ntau = 5, naPercent = 0.4, warmStart = "cond", bicgamma = NULL,
  maxOptimIT = 0, theta.st = NULL, oneTheta = FALSE, eps = 1e-05,
  start = "jumpstart")

`dat`	the zero-inflated count sample data with n observations and p variables
`filter`	a binary matrix indicating the initial filter prior to the variable selection in ZINB regression. Default is `NULL`, which uses all the covariates.
`bic`	the criterion used to create the graph, could be "BIC", "extBIC" or "extBICGG". Default is "extBIC".
`unpenalizedx, unpenalizedz`	Additional unpenalized covariates for negative binomial and logistic regression respectively. Default is `NULL`.
`lambdas, taus`	specific tuning parameter values you want to run the model with. Default is `NULL` where the function will auto-generate a tuning parameter search grid. If default is used, must have input for nlambda and ntau.
`nlambda, ntau`	number of unique lambda and tau values - default are 30 and 5.
`naPercent`	allowable percentage of observations with missing values - default is .4.
`warmStart`	default is 'cond', which resets the starting point to the original starting point when non-convergence happens. Other options are TRUE, which keeps previous estimates as starting points for estimation for the next tuning parameter; FALSE uses the same starting point for all tp.
`bicgamma`	the parameter used in the extended BIC. Default is `NULL`, which uses the log(the dimension)/log(the sample size).
`maxOptimIT`	maximum number of iterations for numerical optimization (BFGS) after the EM algorithm. By default is set to 50. Convergence time is long.
`eps`	threshold for convergence for the EM algorithm - default is 1e-5.
`start`	default is 'jumpstart', which estimates the starting coefficients from penalized negative binomial estimation and logistic regression based on the penalized library. If set to `NULL`, then set starting coefficients values to 0. Otherwise, can also take direct input for starting values. Must be in the form of list(betas = v1, gammas = v2), where v1 and v2 are vectors the length of the number of covariates in X.