Fixed degrees of freed in t-stat for intercept

[pspp-builds.git] / src / language / stats / regression.q

diff --git a/src/language/stats/regression.q b/src/language/stats/regression.q
index c27d8a40a7e1eb0314d5d8c088d86ec5988d88c1..53ac594b455ff4955959b3b8dcf2049ec98915b9 100644 (file)
--- a/src/language/stats/regression.q
+++ b/src/language/stats/regression.q
@@ -24,7 +24,6 @@
 #include <data/case.h>
 #include <data/casegrouper.h>
 #include <data/casereader.h>
-#include <data/category.h>
 #include <data/dictionary.h>
 #include <data/missing-values.h>
 #include <data/procedure.h>
@@ -41,7 +40,7 @@
 #include <math/covariance.h>
 #include <math/linreg.h>
 #include <math/moments.h>
-#include <output/table.h>
+#include <output/tab.h>
 
 #include "xalloc.h"
 
@@ -147,8 +146,7 @@ reg_stats_r (linreg *c, void *aux UNUSED)
   rsq = linreg_ssreg (c) / linreg_sst (c);
   adjrsq = 1.0 - (1.0 - rsq) * (linreg_n_obs (c) - 1.0) / (linreg_n_obs (c) - linreg_n_coeffs (c));
   std_error = sqrt (linreg_mse (c));
-  t = tab_create (n_cols, n_rows, 0);
-  tab_dim (t, tab_natural_dimensions, NULL);
+  t = tab_create (n_cols, n_rows);
   tab_box (t, TAL_2, TAL_2, -1, TAL_1, 0, 0, n_cols - 1, n_rows - 1);
   tab_hline (t, TAL_2, 0, n_cols - 1, 1);
   tab_vline (t, TAL_2, 2, 0, n_rows - 1);
@@ -184,14 +182,13 @@ reg_stats_coeff (linreg * c, void *aux_)
 
   const struct variable *v;
   struct tab_table *t;
+  gsl_matrix *cov = aux_;
 
   assert (c != NULL);
-  gsl_matrix *cov = (gsl_matrix *) aux_;
   n_rows = linreg_n_coeffs (c) + 3;
 
-  t = tab_create (n_cols, n_rows, 0);
+  t = tab_create (n_cols, n_rows);
   tab_headers (t, 2, 0, 1, 0);
-  tab_dim (t, tab_natural_dimensions, NULL);
   tab_box (t, TAL_2, TAL_2, -1, TAL_1, 0, 0, n_cols - 1, n_rows - 1);
   tab_hline (t, TAL_2, 0, n_cols - 1, 1);
   tab_vline (t, TAL_2, 2, 0, n_rows - 1);
@@ -209,7 +206,7 @@ reg_stats_coeff (linreg * c, void *aux_)
   tab_double (t, 4, 1, 0, 0.0, NULL);
   t_stat = linreg_intercept (c) / std_err;
   tab_double (t, 5, 1, 0, t_stat, NULL);
-  pval = 2 * gsl_cdf_tdist_Q (fabs (t_stat), 1.0);
+  pval = 2 * gsl_cdf_tdist_Q (fabs (t_stat), (double) (linreg_n_obs (c) - linreg_n_coeffs (c)));
   tab_double (t, 6, 1, 0, pval, NULL);
   for (j = 0; j < linreg_n_coeffs (c); j++)
     {
@@ -274,9 +271,8 @@ reg_stats_anova (linreg * c, void *aux UNUSED)
   struct tab_table *t;
 
   assert (c != NULL);
-  t = tab_create (n_cols, n_rows, 0);
+  t = tab_create (n_cols, n_rows);
   tab_headers (t, 2, 0, 1, 0);
-  tab_dim (t, tab_natural_dimensions, NULL);
 
   tab_box (t, TAL_2, TAL_2, -1, TAL_1, 0, 0, n_cols - 1, n_rows - 1);
 
@@ -365,9 +361,8 @@ reg_stats_bcov (linreg * c, void *aux UNUSED)
   assert (c != NULL);
   n_cols = c->n_indeps + 1 + 2;
   n_rows = 2 * (c->n_indeps + 1);
-  t = tab_create (n_cols, n_rows, 0);
+  t = tab_create (n_cols, n_rows);
   tab_headers (t, 2, 0, 1, 0);
-  tab_dim (t, tab_natural_dimensions, NULL);
   tab_box (t, TAL_2, TAL_2, -1, TAL_1, 0, 0, n_cols - 1, n_rows - 1);
   tab_hline (t, TAL_2, 0, n_cols - 1, 1);
   tab_vline (t, TAL_2, 2, 0, n_rows - 1);
@@ -867,9 +862,57 @@ fill_covariance (gsl_matrix *cov, struct covariance *all_cov,
   gsl_matrix_set (cov, cov->size1 - 1, cov->size1 - 1, 
                  gsl_matrix_get (cm, dep_subscript, dep_subscript));
   free (rows);
+  gsl_matrix_free (cm);
   return result;
 }
+static size_t
+get_n_all_vars (struct cmd_regression *cmd)
+{
+  size_t result = n_variables;
+  size_t i;
+  size_t j;
 
+  result += cmd->n_dependent;
+  for (i = 0; i < cmd->n_dependent; i++)
+    {
+      for (j = 0; j < n_variables; j++)
+       {
+         if (v_variables[j] == cmd->v_dependent[i])
+           {
+             result--;
+           }
+       }
+    }
+  return result;
+}
+static void
+fill_all_vars (const struct variable **vars, struct cmd_regression *cmd)
+{
+  size_t i;
+  size_t j;
+  bool absent;
+  
+  for (i = 0; i < n_variables; i++)
+    {
+      vars[i] = v_variables[i];
+    }
+  for (i = 0; i < cmd->n_dependent; i++)
+    {
+      absent = true;
+      for (j = 0; j < n_variables; j++)
+       {
+         if (cmd->v_dependent[i] == v_variables[j])
+           {
+             absent = false;
+             break;
+           }
+       }
+      if (absent)
+       {
+         vars[i + n_variables] = cmd->v_dependent[i];
+       }
+    }
+}
 static bool
 run_regression (struct casereader *input, struct cmd_regression *cmd,
                struct dataset *ds, linreg **models)
@@ -882,10 +925,11 @@ run_regression (struct casereader *input, struct cmd_regression *cmd,
   struct ccase *c;
   struct covariance *cov;
   const struct variable **vars;
+  const struct variable **all_vars;
   const struct variable *dep_var;
   struct casereader *reader;
   const struct dictionary *dict;
-  gsl_matrix *this_cm;
+  size_t n_all_vars;
 
   assert (models != NULL);
 
@@ -912,9 +956,12 @@ run_regression (struct casereader *input, struct cmd_regression *cmd,
     {
       dict_get_vars (dict, &v_variables, &n_variables, 0);
     }
+  n_all_vars = get_n_all_vars (cmd);
+  all_vars = xnmalloc (n_all_vars, sizeof (*all_vars));
+  fill_all_vars (all_vars, cmd);
   vars = xnmalloc (n_variables, sizeof (*vars));
-  means  = xnmalloc (n_variables, sizeof (*means));
-  cov = covariance_1pass_create (n_variables, v_variables,
+  means  = xnmalloc (n_all_vars, sizeof (*means));
+  cov = covariance_1pass_create (n_all_vars, all_vars,
                                 dict_get_weight (dict), MV_ANY);
 
   reader = casereader_clone (input);
@@ -927,12 +974,13 @@ run_regression (struct casereader *input, struct cmd_regression *cmd,
   
   for (k = 0; k < cmd->n_dependent; k++)
     {
+      gsl_matrix *this_cm;
       dep_var = cmd->v_dependent[k];
       n_indep = identify_indep_vars (vars, dep_var);
       
       this_cm = gsl_matrix_alloc (n_indep + 1, n_indep + 1);
       n_data = fill_covariance (this_cm, cov, vars, n_indep, 
-                               dep_var, v_variables, n_variables, means);
+                               dep_var, all_vars, n_all_vars, means);
       models[k] = linreg_alloc (dep_var, (const struct variable **) vars,
                                n_data, n_indep);
       models[k]->depvar = dep_var;
@@ -968,10 +1016,12 @@ run_regression (struct casereader *input, struct cmd_regression *cmd,
          linreg_free (models[k]);
          models[k] = NULL;
        }
+      gsl_matrix_free (this_cm);
     }
   
   casereader_destroy (reader);
   free (vars);
+  free (all_vars);
   free (means);
   casereader_destroy (input);
   covariance_destroy (cov);