X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Fstats%2Fregression.q;h=e5b86ea2bc84a024a9f2503796b16a3654c8a2d1;hb=036ae30df61b1c998e1aa027863ac2349a67066b;hp=c7e8179a579086620064f53e0bd6bb5eace213ce;hpb=f550aee00a62fe1d8baf62d83cd7efef6cc2ee92;p=pspp

diff --git a/src/language/stats/regression.q b/src/language/stats/regression.q
index c7e8179a57..e5b86ea2bc 100644
--- a/src/language/stats/regression.q
+++ b/src/language/stats/regression.q
@@ -1,5 +1,5 @@
 /* PSPP - a program for statistical analysis.
-   Copyright (C) 2005, 2009 Free Software Foundation, Inc.
+   Copyright (C) 2005, 2009, 2010 Free Software Foundation, Inc.
 
    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
@@ -206,7 +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++)
     {
@@ -752,10 +752,10 @@ regression_custom_variables (struct lexer *lexer, struct dataset *ds,
 {
   const struct dictionary *dict = dataset_dict (ds);
 
-  lex_match (lexer, '=');
+  lex_match (lexer, T_EQUALS);
 
   if ((lex_token (lexer) != T_ID
-       || dict_lookup_var (dict, lex_tokid (lexer)) == NULL)
+       || dict_lookup_var (dict, lex_tokcstr (lexer)) == NULL)
       && lex_token (lexer) != T_ALL)
     return 2;
 
@@ -862,9 +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)
@@ -877,10 +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);
 
@@ -907,9 +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);
@@ -922,12 +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;
@@ -963,10 +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);