Removed check for stability in df2lambda. Closes #26.

R/AAA.R

@@ -19,9 +19,7 @@
             mboost_dftraceS = FALSE,  ### df = trace(S) or df = trace(2 S - StS)
             mboost_lambdaMax = 1e+15,### maximum value for lambda as used in df2lambda
             mboost_Xmonotone = FALSE,### don't force monotonicity in %X%
-            mboost_eps = 10e-10, ### factor for dmat in df2lambda
-            mboost_check_df2lambda = TRUE) ### check if max(abs(X)) > 10 in df2lambda
-                                 ### as this might take a while experts can skip this check
+            mboost_eps = 10e-10) ### factor for dmat in df2lambda
 }
 
 .onUnload <- function(libpath) {

R/bl.R

@@ -20,16 +20,6 @@ df2lambda <- function(X, df = 4, lambda = NULL, dmat = NULL, weights,
         if (lambda == 0)
             return(c(df = rankMatrix(X), lambda = 0))
 
-    ## check for possible instability
-    if (options("mboost_check_df2lambda")[[1]] && max(abs(X)) > 10)
-        warning("Some absolute values in design matrix are greater 10. Hence, ",
-                sQuote("df2lambda"), " might be numerically instable.\n  ",
-                "See documentation of argument ", sQuote("by"),
-                " in ?bbs for further information.",
-                immediate. = TRUE)
-    ## instable df2lambda might for example occure if one uses bbs(x, by = z)
-    ## with large values of z
-
     # Demmler-Reinsch Orthogonalization (cf. Ruppert et al., 2003,
     # Semiparametric Regression, Appendix B.1.1).
 

inst/NEWS.Rd

@@ -18,6 +18,10 @@
         without base-learners.
         Fixes \href{https://github.com/boost-R/mboost/issues/64}{#64} and 
         \href{https://github.com/boost-R/mboost/issues/66}{#66}.
+      \item Removed check if \code{df2lambda} is stable. Hence,  
+        \code{options(mboost_check_df2lambda)} (introduced in mboost 2.5-0) 
+        is no longer used. 
+        Closes \href{https://github.com/boost-R/mboost/issues/26}{#26}.
     }
   }
   \subsection{Miscellaneous}{