|
real(dp) function, dimension(:), allocatable | mo_kernel::kernel_cumdensity_1d_dp (ix, h, silverman, xout, romberg, nintegrate, epsint, mask, nodata) |
|
real(sp) function, dimension(:), allocatable | mo_kernel::kernel_cumdensity_1d_sp (ix, h, silverman, xout, romberg, nintegrate, epsint, mask, nodata) |
|
real(dp) function, dimension(:), allocatable | mo_kernel::kernel_density_1d_dp (ix, h, silverman, xout, mask, nodata) |
|
real(sp) function, dimension(:), allocatable | mo_kernel::kernel_density_1d_sp (ix, h, silverman, xout, mask, nodata) |
|
real(dp) function | mo_kernel::kernel_density_h_1d_dp (ix, silverman, mask) |
|
real(sp) function | mo_kernel::kernel_density_h_1d_sp (ix, silverman, mask) |
|
real(dp) function, dimension(:), allocatable | mo_kernel::kernel_regression_1d_dp (ix, iy, h, silverman, xout, mask, nodata) |
|
real(sp) function, dimension(:), allocatable | mo_kernel::kernel_regression_1d_sp (ix, iy, h, silverman, xout, mask, nodata) |
|
real(dp) function, dimension(:), allocatable | mo_kernel::kernel_regression_2d_dp (ix, iy, h, silverman, xout, mask, nodata) |
|
real(sp) function, dimension(:), allocatable | mo_kernel::kernel_regression_2d_sp (ix, iy, h, silverman, xout, mask, nodata) |
|
real(dp) function | mo_kernel::kernel_regression_h_1d_dp (ix, iy, silverman, mask) |
|
real(sp) function | mo_kernel::kernel_regression_h_1d_sp (ix, iy, silverman, mask) |
|
real(dp) function, dimension(size(ix, 2)) | mo_kernel::kernel_regression_h_2d_dp (ix, iy, silverman, mask) |
|
real(sp) function, dimension(size(ix, 2)) | mo_kernel::kernel_regression_h_2d_sp (ix, iy, silverman, mask) |
|
real(dp) function | mo_kernel::nadaraya_watson_1d_dp (z, y, mask, valid) |
|
real(sp) function | mo_kernel::nadaraya_watson_1d_sp (z, y, mask, valid) |
|
real(dp) function | mo_kernel::nadaraya_watson_2d_dp (z, y, mask, valid) |
|
real(sp) function | mo_kernel::nadaraya_watson_2d_sp (z, y, mask, valid) |
|
real(dp) function | mo_kernel::cross_valid_regression_dp (h) |
|
real(sp) function | mo_kernel::cross_valid_regression_sp (h) |
|
real(dp) function | mo_kernel::cross_valid_density_1d_dp (h) |
|
real(sp) function | mo_kernel::cross_valid_density_1d_sp (h) |
|
subroutine | mo_kernel::allocate_globals_1d_dp (x, y, xout) |
|
subroutine | mo_kernel::allocate_globals_1d_sp (x, y, xout) |
|
subroutine | mo_kernel::allocate_globals_2d_dp (x, y, xout) |
|
subroutine | mo_kernel::allocate_globals_2d_sp (x, y, xout) |
|
subroutine | mo_kernel::deallocate_globals () |
|
real(sp) function | mo_kernel::golden_sp (ax, bx, cx, func, tol, xmin) |
|
subroutine | shft2 (a, b, c) |
|
subroutine | shft3 (a, b, c, d) |
|
real(dp) function | mo_kernel::golden_dp (ax, bx, cx, func, tol, xmin) |
|
subroutine | shft2 (a, b, c) |
|
subroutine | shft3 (a, b, c, d) |
|
real(dp) function, dimension(n) | mo_kernel::mesh_dp (start, end, n, delta) |
|
real(sp) function, dimension(n) | mo_kernel::mesh_sp (start, end, n, delta) |
|
subroutine | mo_kernel::trapzd_dp (kernel, x, h, a, b, res, n) |
|
subroutine | mo_kernel::trapzd_sp (kernel, x, h, a, b, res, n) |
|
subroutine | mo_kernel::polint_dp (xa, ya, x, y, dy) |
|
subroutine | mo_kernel::polint_sp (xa, ya, x, y, dy) |
|
Module for kernel regression and kernel density estimation.
This module provides routines for kernel regression of data as well as kernel density estimation of both probability density functions (PDF) and cumulative density functions (CDF).
So far only a Gaussian kernel is implemented (Nadaraya-Watson) which can be used for one- and multidimensional data.
Furthermore, the estimation of the bandwith needed for kernel methods is provided by either Silverman''s rule of thumb or a Cross-Vaildation approach.
The Cross-Validation method is actually an optimization of the bandwith and might be the most costly part of the kernel smoother. Therefore, the bandwith estimation is not necessarily part of the kernel smoothing but can be determined first and given as an optional argument to the smoother.
- Changelog
- Juliane Mai, Mar 2013
- Stephan Thober, Mar 2013
- Matthias Cuntz, Mar 2013
- Matthias Cuntz, May 2013
- sort -> qsort
- module procedure golden
- Stephan Thober, Jul 2015
- using sort_index in favor of qsort_index
- Matthias Cuntz, Mar 2016
- Romberg integration in cumdensity
- Juliane Mai
- Date
- Mar 2013
- Copyright
- Copyright 2005-2024, the CHS Developers, Sabine Attinger: All rights reserved. FORCES is released under the LGPLv3+ license
The UFZ (CHS) FORCES code is free software. You can redistribute it and/or modify it under the terms of the GNU General Public License as published by the free Software Foundation either version 3 of the License, or (at your option) any later version.
This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.
You received a copy of the GNU Lesser General Public License along with the UFZ CHS FORCES code. It can be found in the files COPYING
and COPYING.LESSER
provided with this software. The complete GNU license text can also be found at http://www.gnu.org/licenses/.
Definition in file mo_kernel.f90.