X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Fstats%2Fregression.q;h=0718b8d4d0bccce1da5ff3269ae0fd1b5ecc9157;hb=e385eeb8a2ea75fb2d9c1c628619baa03c914dae;hp=abb3bd353aebea6814d55c7b7c00ab0be926f95a;hpb=74469ec6a0f6b5b33c4afaace173710adac46634;p=pspp-builds.git

diff --git a/src/language/stats/regression.q b/src/language/stats/regression.q
index abb3bd35..0718b8d4 100644
--- a/src/language/stats/regression.q
+++ b/src/language/stats/regression.q
@@ -144,8 +144,8 @@ reg_stats_r (linreg * c)
   double std_error;
 
   assert (c != NULL);
-  rsq = c->ssm / c->sst;
-  adjrsq = 1.0 - (1.0 - rsq) * (c->n_obs - 1.0) / (c->n_obs - c->n_indeps);
+  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);
@@ -186,7 +186,7 @@ reg_stats_coeff (linreg * c)
   struct tab_table *t;
 
   assert (c != NULL);
-  n_rows = c->n_coeffs + 3;
+  n_rows = linreg_n_coeffs (c) + 3;
 
   t = tab_create (n_cols, n_rows, 0);
   tab_headers (t, 2, 0, 1, 0);
@@ -293,9 +293,9 @@ reg_stats_anova (linreg * c)
   tab_text (t, 1, 3, TAB_LEFT | TAT_TITLE, _("Total"));
 
   /* Sums of Squares */
-  tab_double (t, 2, 1, 0, c->ssm, NULL);
-  tab_double (t, 2, 3, 0, c->sst, NULL);
-  tab_double (t, 2, 2, 0, c->sse, NULL);
+  tab_double (t, 2, 1, 0, linreg_ssreg (c), NULL);
+  tab_double (t, 2, 3, 0, linreg_sst (c), NULL);
+  tab_double (t, 2, 2, 0, linreg_sse (c), NULL);
 
 
   /* Degrees of freedom */
@@ -805,15 +805,16 @@ static double
 fill_covariance (gsl_matrix *cov, struct covariance *all_cov, 
 		 const struct variable **vars,
 		 size_t n_vars, const struct variable *dep_var, 
-		 const struct variable **all_vars, size_t n_all_vars)
+		 const struct variable **all_vars, size_t n_all_vars,
+		 double *means)
 {
   size_t i;
   size_t j;
-  size_t k = 0;
   size_t dep_subscript;
   size_t *rows;
   const gsl_matrix *ssizes;
   const gsl_matrix *cm;
+  const gsl_matrix *mean_matrix;
   double result = 0.0;
   
   cm = covariance_calculate (all_cov);
@@ -821,31 +822,29 @@ fill_covariance (gsl_matrix *cov, struct covariance *all_cov,
   
   for (i = 0; i < n_all_vars; i++)
     {
-      for (j = k; j < n_vars; j++)
+      for (j = 0; j < n_vars; j++)
 	{
 	  if (vars[j] == all_vars[i])
 	    {
-	      if (vars[j] != dep_var)
-		{
-		  rows[j] = i;
-		}
-	      else
-		{
-		  dep_subscript = i;
-		}
-	      k++;
-	      break;
+	      rows[j] = i;
 	    }
 	}
+      if (all_vars[i] == dep_var)
+	{
+	  dep_subscript = i;
+	}
     }
+  mean_matrix = covariance_moments (all_cov, MOMENT_MEAN);
   for (i = 0; i < cov->size1 - 1; i++)
     {
+      means[i] = gsl_matrix_get (mean_matrix, rows[i], 0);
       for (j = 0; j < cov->size2 - 1; j++)
 	{
 	  gsl_matrix_set (cov, i, j, gsl_matrix_get (cm, rows[i], rows[j]));
 	  gsl_matrix_set (cov, j, i, gsl_matrix_get (cm, rows[j], rows[i]));
 	}
     }
+  means[cov->size1 - 1] = gsl_matrix_get (mean_matrix, dep_subscript, 0);
   ssizes = covariance_moments (all_cov, MOMENT_NONE);
   result = gsl_matrix_get (ssizes, dep_subscript, rows[0]);
   for (i = 0; i < cov->size1 - 1; i++)
@@ -859,6 +858,8 @@ fill_covariance (gsl_matrix *cov, struct covariance *all_cov,
 	  result = gsl_matrix_get (ssizes, rows[i], dep_subscript);
 	}
     }
+  gsl_matrix_set (cov, cov->size1 - 1, cov->size1 - 1, 
+		  gsl_matrix_get (cm, dep_subscript, dep_subscript));
   free (rows);
   return result;
 }
@@ -871,6 +872,7 @@ run_regression (struct casereader *input, struct cmd_regression *cmd,
   int n_indep = 0;
   int k;
   double n_data;
+  double *means;
   struct ccase *c;
   struct covariance *cov;
   const struct variable **vars;
@@ -905,6 +907,7 @@ run_regression (struct casereader *input, struct cmd_regression *cmd,
       dict_get_vars (dict, &v_variables, &n_variables, 0);
     }
   vars = xnmalloc (n_variables, sizeof (*vars));
+  means  = xnmalloc (n_variables, sizeof (*means));
   cov = covariance_1pass_create (n_variables, v_variables,
 				 dict_get_weight (dict), MV_ANY);
 
@@ -923,11 +926,14 @@ run_regression (struct casereader *input, struct cmd_regression *cmd,
       
       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);
+				dep_var, v_variables, n_variables, means);
       models[k] = linreg_alloc (dep_var, (const struct variable **) vars,
 				n_data, n_indep);
       models[k]->depvar = dep_var;
-      
+      for (i = 0; i < n_indep; i++)
+	{
+	  linreg_set_indep_variable_mean (models[k], i, means[i]);
+	}
       /*
 	For large data sets, use QR decomposition.
       */
@@ -956,9 +962,10 @@ run_regression (struct casereader *input, struct cmd_regression *cmd,
 	  models[k] = NULL;
 	}
     }
-
+  
   casereader_destroy (reader);
   free (vars);
+  free (means);
   casereader_destroy (input);
   covariance_destroy (cov);