Parameter estimate matched with appropriate variable during estimation

[pspp] / src / regression.q

diff --git a/src/regression.q b/src/regression.q
index d3a81e401418a47389cd45b466c870efb5d491e2..e69761e3d39a21176728868ec951d93317f811e2 100644 (file)
--- a/src/regression.q
+++ b/src/regression.q
@@ -24,16 +24,19 @@
 #include <gsl/gsl_matrix.h>
 #include "alloc.h"
 #include "case.h"
+#include "casefile.h"
+#include "cat.h"
+#include "command.h"
 #include "dictionary.h"
+#include "error.h"
 #include "file-handle.h"
-#include "command.h"
+#include "gettext.h"
 #include "lexer.h"
+#include <linreg/pspp_linreg.h>
 #include "tab.h"
 #include "var.h"
 #include "vfm.h"
-#include "casefile.h"
-#include <linreg/pspp_linreg.h>
-#include "cat.h"
+
 /* (headers) */
 
 
@@ -69,6 +72,11 @@ static struct cmd_regression cmd;
  */
 size_t *indep_vars;
 
+/*
+  Return value for the procedure.
+ */
+int pspp_reg_rc = CMD_SUCCESS;
+
 static void run_regression (const struct casefile *, void *);
 /* 
    STATISTICS subcommand output functions.
@@ -143,7 +151,8 @@ reg_stats_coeff (pspp_linreg_cache * c)
   struct tab_table *t;
 
   assert (c != NULL);
-  n_rows = 2 + c->param_estimates->size;
+  n_rows = c->n_coeffs + 2;
+
   t = tab_create (n_cols, n_rows, 0);
   tab_headers (t, 2, 0, 1, 0);
   tab_dim (t, tab_natural_dimensions);
@@ -158,7 +167,7 @@ reg_stats_coeff (pspp_linreg_cache * c)
   tab_text (t, 5, 0, TAB_CENTER | TAT_TITLE, _("t"));
   tab_text (t, 6, 0, TAB_CENTER | TAT_TITLE, _("Significance"));
   tab_text (t, 1, 1, TAB_LEFT | TAT_TITLE, _("(Constant)"));
-  coeff = gsl_vector_get (c->param_estimates, 0);
+  coeff = c->coeff[0].estimate;
   tab_float (t, 2, 1, 0, coeff, 10, 2);
   std_err = sqrt (gsl_matrix_get (c->cov, 0, 0));
   tab_float (t, 3, 1, 0, std_err, 10, 2);
@@ -168,40 +177,39 @@ reg_stats_coeff (pspp_linreg_cache * c)
   tab_float (t, 5, 1, 0, t_stat, 10, 2);
   pval = 2 * gsl_cdf_tdist_Q (fabs (t_stat), 1.0);
   tab_float (t, 6, 1, 0, pval, 10, 2);
-  for (j = 0; j < c->n_indeps; j++)
+  for (j = 1; j <= c->n_indeps; j++)
     {
       i = indep_vars[j];
-      struct variable *v = cmd.v_variables[i];
-      label = var_to_string (v);
-      tab_text (t, 1, j + 2, TAB_CENTER, label);
+      label = var_to_string (c->coeff[j].v);
+      tab_text (t, 1, j + 1, TAB_CENTER, label);
       /*
          Regression coefficients.
        */
-      coeff = gsl_vector_get (c->param_estimates, j + 1);
-      tab_float (t, 2, j + 2, 0, coeff, 10, 2);
+      coeff = c->coeff[j].estimate;
+      tab_float (t, 2, j + 1, 0, coeff, 10, 2);
       /*
          Standard error of the coefficients.
        */
-      std_err = sqrt (gsl_matrix_get (c->cov, j + 1, j + 1));
-      tab_float (t, 3, j + 2, 0, std_err, 10, 2);
+      std_err = sqrt (gsl_matrix_get (c->cov, j, j));
+      tab_float (t, 3, j + 1, 0, std_err, 10, 2);
       /*
          'Standardized' coefficient, i.e., regression coefficient
          if all variables had unit variance.
        */
-      beta = gsl_vector_get (c->indep_std, j + 1);
+      beta = gsl_vector_get (c->indep_std, j);
       beta *= coeff / c->depvar_std;
-      tab_float (t, 4, j + 2, 0, beta, 10, 2);
+      tab_float (t, 4, j + 1, 0, beta, 10, 2);
 
       /*
          Test statistic for H0: coefficient is 0.
        */
       t_stat = coeff / std_err;
-      tab_float (t, 5, j + 2, 0, t_stat, 10, 2);
+      tab_float (t, 5, j + 1, 0, t_stat, 10, 2);
       /*
          P values for the test statistic above.
        */
       pval = 2 * gsl_cdf_tdist_Q (fabs (t_stat), 1.0);
-      tab_float (t, 6, j + 2, 0, pval, 10, 2);
+      tab_float (t, 6, j + 1, 0, pval, 10, 2);
     }
   tab_title (t, 0, _("Coefficients"));
   tab_submit (t);
@@ -462,7 +470,7 @@ cmd_regression (void)
     }
   multipass_procedure_with_splits (run_regression, &cmd);
 
-  return CMD_SUCCESS;
+  return pspp_reg_rc;
 }
 
 /*
@@ -492,6 +500,7 @@ run_regression (const struct casefile *cf, void *cmd_ UNUSED)
   size_t n_data = 0;
   size_t row;
   int n_indep;
+  int j = 0;
   const union value *val;
   struct casereader *r;
   struct casereader *r2;
@@ -506,11 +515,11 @@ run_regression (const struct casefile *cf, void *cmd_ UNUSED)
 
   n_data = casefile_get_case_cnt (cf);
   n_indep = cmd.n_variables - cmd.n_dependent;
-  indep_vars = (size_t *) malloc (n_indep * sizeof (*indep_vars));
+  indep_vars = xnmalloc (n_indep, sizeof *indep_vars);
 
   Y = gsl_vector_alloc (n_data);
   lopts.get_depvar_mean_std = 1;
-  lopts.get_indep_mean_std = (int *) malloc (n_indep * sizeof (int));
+  lopts.get_indep_mean_std = xnmalloc (n_indep, sizeof (int));
 
   lcache = pspp_linreg_cache_alloc (n_data, n_indep);
   lcache->indep_means = gsl_vector_alloc (n_indep);
@@ -560,7 +569,13 @@ run_regression (const struct casefile *cf, void *cmd_ UNUSED)
           */
          if (is_depvar (i))
            {
-             assert (v->type == NUMERIC);
+             if (v->type != NUMERIC)
+               {
+                 msg (SE, gettext ("Dependent variable must be numeric."));
+                 pspp_reg_rc = CMD_FAILURE;
+                 return;
+               }
+             lcache->depvar = (const struct var *) v;
              gsl_vector_set (Y, row, val->f);
            }
          else
@@ -581,6 +596,19 @@ run_regression (const struct casefile *cf, void *cmd_ UNUSED)
            }
        }
     }
+  /*
+     Now that we know the number of coefficients, allocate space
+     and store pointers to the variables that correspond to the
+     coefficients.
+   */
+  lcache->coeff = xnmalloc (X->m->size2 + 1, sizeof (*lcache->coeff));
+  for (i = 0; i < X->m->size2; i++)
+    {
+      j = i + 1;               /* The first coeff is the intercept. */
+      lcache->coeff[j].v =
+       (const struct variable *) design_matrix_col_to_var (X, i);
+      assert (lcache->coeff[j].v != NULL);
+    }
   /* 
      Find the least-squares estimates and other statistics.
    */
@@ -592,6 +620,7 @@ run_regression (const struct casefile *cf, void *cmd_ UNUSED)
   free (lopts.get_indep_mean_std);
   free (indep_vars);
   casereader_destroy (r);
+  return;
 }
 
 /*