Re: [R] glm.fit to use LAPACK instead of LINPACK

2009-10-22 Thread Ted
Hi, I understand that the glm.fit calls LINPACK fortran routines instead of LAPACK because it can handle the 'rank deficiency problem'. If my data matrix is not rank deficient, would a glm.fit function which runs on LAPACK be faster? Would this be worthwhile to convert glm.fit to use LAPACK?

Re: [R] glm.fit to use LAPACK instead of LINPACK

2009-10-22 Thread Ravi Varadhan
: Thursday, October 22, 2009 10:53 am Subject: Re: [R] glm.fit to use LAPACK instead of LINPACK To: r-help@R-project.org r-help@r-project.org Hi, I understand that the glm.fit calls LINPACK fortran routines instead of LAPACK because it can handle the 'rank deficiency problem'. If my data

Re: [R] glm.fit to use LAPACK instead of LINPACK

2009-10-22 Thread Douglas Bates
of calls to pmin and pmax. Before trying to change very tricky Fortran code you owe it to yourself to check that the potential gains would be. - Original Message - From: Ted tchi...@sickkids.ca Date: Thursday, October 22, 2009 10:53 am Subject: Re: [R] glm.fit to use LAPACK instead

Re: [R] glm.fit to use LAPACK instead of LINPACK

2009-10-22 Thread Ted
] glm.fit to use LAPACK instead of LINPACK To: r-help@R-project.org r-help@r-project.org Hi, I understand that the glm.fit calls LINPACK fortran routines instead of LAPACK because it can handle the 'rank deficiency problem'.  If my data matrix is not rank deficient, would a glm.fit function which runs

[R] glm.fit to use LAPACK instead of LINPACK

2009-10-20 Thread Ted
Hi, I understand that the glm.fit calls LINPACK fortran routines instead of LAPACK because it can handle the 'rank deficiency problem'. If my data matrix is not rank deficient, would a glm.fit function which runs on LAPACK be faster? Would this be worthwhile to convert glm.fit to use