bias_correction: Corrects given estimates for publication bias
In t-sager/pubias: Identification & Correction for Publication Bias

Description Usage Arguments Value

View source: R/bias_correction.R

Check package vignette for further information.

bias_correction(
  X,
  sigma,
  result,
  cutoffs,
  symmetric,
  identificationapproach,
  GMM
)

`X`	In the case of a meta study, a `n x 1` matrix containing the estimates, where `n` is the number of estimates. In the case of a replication study, a `n x 2` matrix where the first (second) column contains the standardized original estimates (replication estimates), where `n` is the number of estimates.
`sigma`	A `n x 1` matrix containing the standard errors of the estimates, where `n` is the number of estimates.
`result`	List obJect which contains the results (`Psihat`, `Varhat`, `se_robust`) of the publication probability estimation.
`cutoffs`	A matrix containing the thresholds for the steps of the publication probability. Should be strictly increasing column vector of size `k x 1` where `k` is the number of cutoffs.
`symmetric`	If set to TRUE, the publication probability is assumed to be symmetric around zero. If set to FALSE, asymmetry is allowed.
`identificationapproach`	Indication if we are dealing with replication studies (== 1) or a met analysis (== 2).
`GMM`	If set to TRUE, the publication probability will be estimated via GMM. Setting it to FALSE uses the MLE method for estimation.

Returns a list containing the original estimates with the adjusted 95% confidence bonds (original, adj_L, adj_U) as well as the corrected estimates (adj_estimates) and in addition the Bonferroni corrected 95% confidence bonds (adj_LB, adj_UB).