Skip to content


Subversion checkout URL

You can clone with
Download ZIP
branch: master
Fetching contributors…

Cannot retrieve contributors at this time

26 lines (19 sloc) 2.493 kB

Random Scale

The RandomScale package provides R code to fit a random scale half-normal detection function to line transect sampling data. The package also contains R code to use AD Model Builder with the R package R2admb to fit mixed-effects models with known covariate values and a random component. The ADMB TPL files are contained in the Inst directory. Example AMDB DAT files are contained in the Inst/Data directory. Version 11 of ADMB is required for the TPL files as distributed but you can modify them by replacing instances of PI with the value 3.141592654.

Executable versions are also provided if you download the Windows binary. In that case you do not need ADMB but the R2admb package is required because it is used to extract results from the output file. The R2admb package should be installed separately.

Examples from Oedekoven et al can be found in the package. To run the hp and simulation example, you'll need to install the mrds package from CRAN. In turn it needs several other packages to be installed manually. See ?RandomScale for links to the examples.

To install ADMB, you need to install a C++ compiler as well as ADMB. We suggest that you install gcc. To use the built-in links, ADMB-11 should be installed to c:\admb and gcc compiler should be installed to c:\mingw. To use different locations you'll need to change function prepare_admb. prepare_admb() must be run prior to using ADMB without downloaded executables.

For other operating systems see ( and ( Note that prepare_admb() only works for Windows.

Download Windows package binary. From link, browse to RandomScale and then click on the version of the package you want. You should see a listing of the package contents as files. Select File/Download. To install in R, from the R menu, use Packages\Install from Local Zip file and browse to location of downloaded zip.

Jump to Line
Something went wrong with that request. Please try again.