Skip to content

Commit

Permalink
fix link in manual + corrections
Browse files Browse the repository at this point in the history
  • Loading branch information
mayrandy committed Jan 27, 2017
1 parent 01ab296 commit 2a15e88
Show file tree
Hide file tree
Showing 2 changed files with 3 additions and 5 deletions.
5 changes: 2 additions & 3 deletions man/Family.Rd
Original file line number Diff line number Diff line change
Expand Up @@ -234,9 +234,8 @@ distribution approximation used in Ma and Huang (2005).
}
\section{Warning}{
The coefficients resulting from boosting with family
\code{Binomial} are \eqn{1/2} of the coefficients of a logit model
obtained via \code{\link{glm}}. This is due to the internal recoding
of the response to \eqn{-1} and \eqn{+1} (see above).
\code{Binomial(link = "logit")} are \eqn{1/2} of the coefficients of a logit model
obtained via \code{\link{glm}} (see above).
For \code{AUC()}, variables should be centered and scaled and observations with weight > 0 must not contain missing values.
The estimated coefficients for \code{AUC()} have no probabilistic interpretation.
Expand Down
3 changes: 1 addition & 2 deletions man/methods.Rd
Original file line number Diff line number Diff line change
Expand Up @@ -310,8 +310,7 @@ mstop(x) <- value
}
\section{Warning}{
The coefficients resulting from boosting with family
\code{\link{Binomial(type = "adaboost", link = "logit")}} are \eqn{1/2} of the coefficients of a logit model obtained via \code{\link{glm}} (see
\code{\link{Binomial}}).
\code{Binomial(link = "logit")} are \eqn{1/2} of the coefficients of a logit model obtained via \code{\link{glm}} (see \code{\link{Binomial}}).
}
\references{
Expand Down

0 comments on commit 2a15e88

Please sign in to comment.