-/*
- lib/linreg/linreg.c
-
- Copyright (C) 2005 Free Software Foundation, Inc. Written by Jason H. Stover.
-
- This program 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 2 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 should have received a copy of the GNU General Public License along with
- this program; if not, write to the Free Software Foundation, Inc., 51
- Franklin Street, Fifth Floor, Boston, MA 02111-1307, USA.
- */
+/* PSPP - a program for statistical analysis.
+ Copyright (C) 2005 Free Software Foundation, Inc. Written by Jason H. Stover.
+
+ This program 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 should have received a copy of the GNU General Public License
+ along with this program. If not, see <http://www.gnu.org/licenses/>. */
+
+#include <config.h>
#include <gsl/gsl_fit.h>
#include <gsl/gsl_multifit.h>
*/
#include <math/linreg/linreg.h>
-#include <math/linreg/coefficient.h>
+#include <math/coefficient.h>
#include <gsl/gsl_errno.h>
#include <linreg/sweep.h>
/*
return GSL_SUCCESS;
}
+
/*
Set V to contain an array of pointers to the variables
used in the model. V must be at least C->N_COEFFS in length.
The return value is the number of distinct variables found.
*/
int
-pspp_linreg_get_vars (const void *c_, struct variable **v)
+pspp_linreg_get_vars (const void *c_, const struct variable **v)
{
const pspp_linreg_cache *c = c_;
- struct pspp_linreg_coeff *coef = NULL;
+ struct pspp_coeff *coef = NULL;
const struct variable *tmp;
int i;
int result = 0;
/*
- Make sure the caller doesn't try to sneak a variable
- into V that is not in the model.
+ Make sure the caller doesn't try to sneak a variable
+ into V that is not in the model.
*/
for (i = 0; i < c->n_coeffs; i++)
{
v[i] = NULL;
}
/*
- Start at c->coeff + 1 to avoid the intercept.
+ Start at c->coeff[1] to avoid the intercept.
*/
- v[result] = (struct variable *) pspp_linreg_coeff_get_var (c->coeff + 1, 0);
+ v[result] = pspp_coeff_get_var (c->coeff[1], 0);
result = (v[result] == NULL) ? 0 : 1;
- for (coef = c->coeff + 2; coef < c->coeff + c->n_coeffs; coef++)
+ for (coef = c->coeff[2]; coef < c->coeff[c->n_coeffs]; coef++)
{
- tmp = pspp_linreg_coeff_get_var (coef, 0);
+ tmp = pspp_coeff_get_var (coef, 0);
assert (tmp != NULL);
/* Repeated variables are likely to bunch together, at the end
- of the array. */
+ of the array. */
i = result - 1;
- while (i >= 0 && (v[i]->index != tmp->index))
+ while (i >= 0 && v[i] != tmp)
{
i--;
}
if (i < 0 && result < c->n_coeffs)
{
- v[result] = (struct variable *) tmp;
+ v[result] = tmp;
result++;
}
}
c->indep_means = gsl_vector_alloc (p);
c->indep_std = gsl_vector_alloc (p);
c->ssx = gsl_vector_alloc (p); /* Sums of squares for the
- independent variables.
- */
+ independent variables.
+ */
c->ss_indeps = gsl_vector_alloc (p); /* Sums of squares for the
- model parameters.
- */
+ model parameters.
+ */
c->cov = gsl_matrix_alloc (p + 1, p + 1); /* Covariance matrix. */
c->n_obs = n;
c->n_indeps = p;
*/
c->method = PSPP_LINREG_SWEEP;
c->predict = pspp_linreg_predict;
- c->residual = pspp_linreg_residual; /* The procedure to compute my
- residuals. */
- c->get_vars = pspp_linreg_get_vars; /* The procedure that returns
- pointers to model
- variables. */
- c->resid = NULL; /* The variable storing my residuals. */
- c->pred = NULL; /* The variable storing my predicted values. */
+ c->residual = pspp_linreg_residual; /* The procedure to compute my
+ residuals. */
+ c->get_vars = pspp_linreg_get_vars; /* The procedure that returns
+ pointers to model
+ variables. */
+ c->resid = NULL; /* The variable storing my residuals. */
+ c->pred = NULL; /* The variable storing my predicted values. */
return c;
}
bool
-pspp_linreg_cache_free (void * m)
+pspp_linreg_cache_free (void *m)
{
+ int i;
+
pspp_linreg_cache *c = m;
- gsl_vector_free (c->indep_means);
- gsl_vector_free (c->indep_std);
- gsl_vector_free (c->ss_indeps);
- gsl_matrix_free (c->cov);
- pspp_linreg_coeff_free (c->coeff);
- free (c);
+ if (c != NULL)
+ {
+ gsl_vector_free (c->indep_means);
+ gsl_vector_free (c->indep_std);
+ gsl_vector_free (c->ss_indeps);
+ gsl_matrix_free (c->cov);
+ gsl_vector_free (c->ssx);
+ for (i = 0; i < c->n_coeffs; i++)
+ {
+ pspp_coeff_free (c->coeff[i]);
+ }
+ free (c);
+ }
return true;
}
const pspp_linreg_opts * opts, pspp_linreg_cache * cache)
{
int rc;
- gsl_matrix *design;
+ gsl_matrix *design = NULL;
gsl_matrix_view xtx;
gsl_matrix_view xm;
gsl_matrix_view xmxtx;
cache->dfm = cache->n_indeps;
cache->dfe = cache->dft - cache->dfm;
cache->n_coeffs = X->size2 + 1; /* Adjust this later to allow for
- regression through the origin.
- */
+ regression through the origin.
+ */
if (cache->method == PSPP_LINREG_SWEEP)
{
gsl_matrix *sw;
for (i = 0; i < cache->n_indeps; i++)
{
tmp = gsl_matrix_get (sw, i, cache->n_indeps);
- cache->coeff[i + 1].estimate = tmp;
+ cache->coeff[i + 1]->estimate = tmp;
m -= tmp * gsl_vector_get (cache->indep_means, i);
}
/*
}
gsl_matrix_set (cache->cov, 0, 0, tmp);
- cache->coeff[0].estimate = m;
+ cache->coeff[0]->estimate = m;
}
else
{
}
gsl_matrix_free (sw);
}
+ else if (cache->method == PSPP_LINREG_CONDITIONAL_INVERSE)
+ {
+ /*
+ Use the SVD of X^T X to find a conditional inverse of X^TX. If
+ the SVD is X^T X = U D V^T, then set the conditional inverse
+ to (X^T X)^c = V D^- U^T. D^- is defined as follows: If entry
+ (i, i) has value sigma_i, then entry (i, i) of D^- is 1 /
+ sigma_i if sigma_i > 0, and 0 otherwise. Then solve the normal
+ equations by setting the estimated parameter vector to
+ (X^TX)^c X^T Y.
+ */
+ }
else
{
gsl_multifit_linear_workspace *wk;
cache->cov, &(cache->sse), wk);
for (i = 0; i < cache->n_coeffs; i++)
{
- cache->coeff[i].estimate = gsl_vector_get (param_estimates, i);
+ cache->coeff[i]->estimate = gsl_vector_get (param_estimates, i);
}
if (rc == GSL_SUCCESS)
{