static struct file_handle *model_file;
static bool run_regression (struct casereader *, struct cmd_regression *,
static struct file_handle *model_file;
static bool run_regression (struct casereader *, struct cmd_regression *,
/* Data pass. */
grouper = casegrouper_create_splits (proc_open (ds), dataset_dict (ds));
while (casegrouper_get_next_group (grouper, &group))
/* Data pass. */
grouper = casegrouper_create_splits (proc_open (ds), dataset_dict (ds));
while (casegrouper_get_next_group (grouper, &group))
/* Identify the explanatory variables in v_variables. Returns
the number of independent variables. */
static int
/* Identify the explanatory variables in v_variables. Returns
the number of independent variables. */
static int
for (i = 0; i < n_variables; i++)
if (!is_depvar (i, depvar))
indep_vars[n_indep_vars++] = v_variables[i];
for (i = 0; i < n_variables; i++)
if (!is_depvar (i, depvar))
indep_vars[n_indep_vars++] = v_variables[i];
+ if ((n_indep_vars < 2) && is_depvar (0, depvar))
+ {
+ /*
+ There is only one independent variable, and it is the same
+ as the dependent variable. Print a warning and continue.
+ */
+ msg (SE,
+ gettext ("The dependent variable is equal to the independent variable."
+ "The least squares line is therefore Y=X."
+ "Standard errors and related statistics may be meaningless."));
+ n_indep_vars = 1;
+ indep_vars[0] = v_variables[0];
+ }
Returns number of valid cases. */
static int
prepare_categories (struct casereader *input,
Returns number of valid cases. */
static int
prepare_categories (struct casereader *input,
- const struct variable **vars, size_t n_vars,
- struct moments_var *mom)
+ const struct variable **vars, size_t n_vars,
+ struct moments_var *mom)
for (i = 0; i < n_vars; i++)
if (var_is_alpha (vars[i]))
cat_stored_values_create (vars[i]);
for (i = 0; i < n_vars; i++)
if (var_is_alpha (vars[i]))
cat_stored_values_create (vars[i]);
- The second condition ensures the program will run even if
- there is only one variable to act as both explanatory and
- response.
+ The second condition ensures the program will run even if
+ there is only one variable to act as both explanatory and
+ response.
- {
- const union value *val = case_data (&c, vars[i]);
- if (var_is_alpha (vars[i]))
- cat_value_update (vars[i], val);
- else
- moments1_add (mom[i].m, val->f, 1.0);
- }
+ {
+ const union value *val = case_data (&c, vars[i]);
+ if (var_is_alpha (vars[i]))
+ cat_value_update (vars[i], val);
+ else
+ moments1_add (mom[i].m, val->f, 1.0);
+ }
dep_var = cmd->v_dependent[k];
n_indep = identify_indep_vars (indep_vars, dep_var);
dep_var = cmd->v_dependent[k];
n_indep = identify_indep_vars (indep_vars, dep_var);
reader = casereader_clone (input);
reader = casereader_create_filter_missing (reader, indep_vars, n_indep,
reader = casereader_clone (input);
reader = casereader_create_filter_missing (reader, indep_vars, n_indep,
reader = casereader_create_filter_missing (reader, &dep_var, 1,
reader = casereader_create_filter_missing (reader, &dep_var, 1,
- MV_ANY, NULL);
- n_data = prepare_categories (casereader_clone (reader),
- indep_vars, n_indep, mom);
+ MV_ANY, NULL);
+ n_data = prepare_categories (casereader_clone (reader),
+ indep_vars, n_indep, mom);
models[k] = pspp_linreg_cache_alloc (X->m->size1, X->m->size2);
models[k]->indep_means = gsl_vector_alloc (X->m->size2);
models[k]->indep_std = gsl_vector_alloc (X->m->size2);
models[k] = pspp_linreg_cache_alloc (X->m->size1, X->m->size2);
models[k]->indep_means = gsl_vector_alloc (X->m->size2);
models[k]->indep_std = gsl_vector_alloc (X->m->size2);
For large data sets, use QR decomposition.
*/
if (n_data > sqrt (n_indep) && n_data > REG_LARGE_DATA)
{
For large data sets, use QR decomposition.
*/
if (n_data > sqrt (n_indep) && n_data > REG_LARGE_DATA)
{
- The second pass fills the design matrix.
- */
- reader = casereader_create_counter (reader, &row, -1);
- for (; casereader_read (reader, &c); case_destroy (&c))
- {
- for (i = 0; i < n_indep; ++i)
- {
- const struct variable *v = indep_vars[i];
- const union value *val = case_data (&c, v);
- if (var_is_alpha (v))
- design_matrix_set_categorical (X, row, v, val);
- else
- design_matrix_set_numeric (X, row, v, val);
- }
- gsl_vector_set (Y, row, case_num (&c, dep_var));
- }
+ The second pass fills the design matrix.
+ */
+ reader = casereader_create_counter (reader, &row, -1);
+ for (; casereader_read (reader, &c); case_destroy (&c))
+ {
+ for (i = 0; i < n_indep; ++i)
+ {
+ const struct variable *v = indep_vars[i];
+ const union value *val = case_data (&c, v);
+ if (var_is_alpha (v))
+ design_matrix_set_categorical (X, row, v, val);
+ else
+ design_matrix_set_numeric (X, row, v, val);
+ }
+ gsl_vector_set (Y, row, case_num (&c, dep_var));
+ }
/*
Now that we know the number of coefficients, allocate space
and store pointers to the variables that correspond to the
/*
Now that we know the number of coefficients, allocate space
and store pointers to the variables that correspond to the
pspp_linreg ((const gsl_vector *) Y, X->m, &lopts, models[k]);
compute_moments (models[k], mom, X, n_variables);
pspp_linreg ((const gsl_vector *) Y, X->m, &lopts, models[k]);
compute_moments (models[k], mom, X, n_variables);
- if (!taint_has_tainted_successor (casereader_get_taint (input)))
- {
- subcommand_statistics (cmd->a_statistics, models[k]);
- subcommand_export (cmd->sbc_export, models[k]);
- }
+ if (!taint_has_tainted_successor (casereader_get_taint (input)))
+ {
+ subcommand_statistics (cmd->a_statistics, models[k]);
+ subcommand_export (cmd->sbc_export, models[k]);
+ }