Oh, I think I got it. Commercial packages limit the number of decimals
shown.
--
View this message in context:
http://r.789695.n4.nabble.com/Poor-performance-of-Optim-tp3862229p3864271.html
Sent from the R help mailing list archive at Nabble.com.
_
What I tried is just a simple binary probit model. Create a random data and
use "optim" to maximize the log-likelihood function to estimate the
coefficients. (e.g. u = 0.1+0.2*x + e, e is standard normal. And y = (u >
0), y indicating a binary choice variable)
If I estimate coefficient of "x
Thank you for your response!
But the problem is when I estimate a model without knowing the true
coefficients, how can I know which "reltol" is good enough? "1e-8" or
"1e-10"? Why can commercial packages automatically determine the right
"reltol" but R cannot?
--
View this message in context:
h
I used to consider using R and "Optim" to replace my commercial packages:
Gauss and Matlab. But it turns out that "Optim" does not converge
completely. The same data for Gauss and Matlab are converged very well. I
see that there are too many packages based on "optim" and really doubt if
they can
I know Matlab's M file can be converted to a stand-alone executable file. I
wonder if there is a project aimed at compiling R scripts into stand-alone
executable file. I think it will be very promising for R to be more widely
used in different fields.
--
View this message in context:
http://
I think I got it!
--
View this message in context:
http://r.789695.n4.nabble.com/How-to-setup-a-Rprofile-file-tp2326328p2326339.html
Sent from the R help mailing list archive at Nabble.com.
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mai
http://www.youtube.com/watch?v=zml4uXQDL4U
Could you take a look at the end of the video. He made a batch file to run
Rcdmr. I wonder how to setup Rprofile file to realize it. Thanks!!
--
View this message in context:
http://r.789695.n4.nabble.com/How-to-setup-a-Rprofile-file-tp2326328p2326
do you know how to increase the optimization level of gcc in R?
--
View this message in context:
http://n4.nabble.com/Efficiency-of-C-Compiler-in-R-CMD-SHLIB-tp1934429p2016646.html
Sent from the R help mailing list archive at Nabble.com.
__
R-help@r-p
Could you tell me a little more in details?
--
View this message in context:
http://n4.nabble.com/Efficiency-of-C-Compiler-in-R-CMD-SHLIB-tp1934429p2015006.html
Sent from the R help mailing list archive at Nabble.com.
__
R-help@r-project.org mailing l
I wonder how to further improve the optimization level of gcc. I thought
"O-3" has already been the best.
--
View this message in context:
http://n4.nabble.com/Efficiency-of-C-Compiler-in-R-CMD-SHLIB-tp1934429p2008994.html
Sent from the R help mailing list archive at Nabble.com.
Thank you very much for your kind explanation. I did find my DLL compiled
using either VC++ 6.0 or Intel Compiler (almost equally fast) is
significanlty faster than that compiled using gcc (55 seconds vs. 78
seconds), the default compiler in R. I did not choose "debug" mode when
using gcc so I s
I am using 32-bit Window XP.
--
View this message in context:
http://n4.nabble.com/Efficiency-of-C-Compiler-in-R-CMD-SHLIB-tp1934429p1934486.html
Sent from the R help mailing list archive at Nabble.com.
__
R-help@r-project.org mailing list
https://st
Thanks for your response. I found the folder to modify the compiler for C
source codes. C++ 6.0 is an old C programming environment (1994~1998) but
it is efficient. When compiling C source codes in C programming
environment, one needs to choose between "debug" or "release" modes.
"release" mo
Dear R experts:
I attempted to compile c source code into DLL using "R CMD SHLIB" but I
found the DLL run in R is almost twice slower than the codes compiled in C++
6.0 when I chose "release" option and is as fast as the situation where I
chose "debug" option in C++ 6.0. I wonder how to improve
Try using aggregate( )
--
View this message in context:
http://n4.nabble.com/counts-of-elements-in-vector-tp1704036p1710369.html
Sent from the R help mailing list archive at Nabble.com.
__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailma
Why does R need the concept of "Vector"? In my opinion, it is a useless and
confusing concept. A vector is simply a special case of a matrix whose row
or column number is equal to 1. When I take submatrix from one matrix and
if row or column number is 1, R will automatically convert it into a v
16 matches
Mail list logo