/* PSPP - a program for statistical analysis.
- Copyright (C) 2005, 2009, 2010, 2011, 2012, 2013 Free Software Foundation, Inc.
+ Copyright (C) 2005, 2009, 2010, 2011, 2012, 2013, 2014,
+ 2016, 2017, 2019 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
#include <config.h>
+#include <float.h>
#include <stdbool.h>
+#include <gsl/gsl_math.h>
#include <gsl/gsl_cdf.h>
#include <gsl/gsl_matrix.h>
#include "libpspp/message.h"
#include "libpspp/taint.h"
-#include "output/tab.h"
+#include "output/pivot-table.h"
+
+#include "gl/intprops.h"
+#include "gl/minmax.h"
#include "gettext.h"
#define _(msgid) gettext (msgid)
#define N_(msgid) msgid
-#include <gl/intprops.h>
+#define STATS_R 1
+#define STATS_COEFF 2
+#define STATS_ANOVA 4
+#define STATS_OUTS 8
+#define STATS_CI 16
+#define STATS_BCOV 32
+#define STATS_TOL 64
+
+#define STATS_DEFAULT (STATS_R | STATS_COEFF | STATS_ANOVA | STATS_OUTS)
+
-#define REG_LARGE_DATA 1000
struct regression
{
const struct variable **dep_vars;
size_t n_dep_vars;
- bool r;
- bool coeff;
- bool anova;
- bool bcov;
-
+ unsigned int stats;
+ double ci;
bool resid;
bool pred;
-};
-struct per_split_ws
-{
- linreg **models;
+ bool origin;
};
struct regression_workspace
{
- struct per_split_ws *psw;
+ /* The new variables which will be introduced by /SAVE */
+ const struct variable **predvars;
+ const struct variable **residvars;
+ /* A reader/writer pair to temporarily hold the
+ values of the new variables */
struct casewriter *writer;
struct casereader *reader;
+ /* Indeces of the new values in the reader/writer (-1 if not applicable) */
int res_idx;
int pred_idx;
- int extras;
- const struct variable **predvars;
- const struct variable **residvars;
+ /* 0, 1 or 2 depending on what new variables are to be created */
+ int extras;
};
static void run_regression (const struct regression *cmd,
- struct per_split_ws *psw,
struct regression_workspace *ws,
struct casereader *input);
-
+/* Return a string based on PREFIX which may be used as the name
+ of a new variable in DICT */
static char *
reg_get_name (const struct dictionary *dict, const char *prefix)
{
return var;
}
-struct thing
+/* Auxiliary data for transformation when /SAVE is entered */
+struct save_trans_data
{
int n_dep_vars;
struct regression_workspace *ws;
};
-static int
-transX (void *aux, struct ccase **c, casenumber x UNUSED)
+static bool
+save_trans_free (void *aux)
+{
+ struct save_trans_data *save_trans_data = aux;
+ free (save_trans_data->ws->predvars);
+ free (save_trans_data->ws->residvars);
+
+ casereader_destroy (save_trans_data->ws->reader);
+ free (save_trans_data->ws);
+ free (save_trans_data);
+ return true;
+}
+
+static enum trns_result
+save_trans_func (void *aux, struct ccase **c, casenumber x UNUSED)
{
- struct thing *thing = aux;
- struct regression_workspace *ws = thing->ws;
- const struct ccase *in = casereader_read (ws->reader);
+ struct save_trans_data *save_trans_data = aux;
+ struct regression_workspace *ws = save_trans_data->ws;
+ struct ccase *in = casereader_read (ws->reader);
if (in)
{
int k;
*c = case_unshare (*c);
- for (k = 0; k < thing->n_dep_vars; ++k)
+ for (k = 0; k < save_trans_data->n_dep_vars; ++k)
{
if (ws->pred_idx != -1)
{
- double pred = case_data_idx (in, ws->extras * k + ws->pred_idx)->f;
- case_data_rw (*c, ws->predvars[k])->f = pred;
+ double pred = case_num_idx (in, ws->extras * k + ws->pred_idx);
+ *case_num_rw (*c, ws->predvars[k]) = pred;
}
-
+
if (ws->res_idx != -1)
{
- double resid = case_data_idx (in, ws->extras * k + ws->res_idx)->f;
- case_data_rw (*c, ws->residvars[k])->f = resid;
+ double resid = case_num_idx (in, ws->extras * k + ws->res_idx);
+ *case_num_rw (*c, ws->residvars[k]) = resid;
}
}
+ case_unref (in);
}
return TRNS_CONTINUE;
}
-
int
cmd_regression (struct lexer *lexer, struct dataset *ds)
{
- int n_splits = 0;
struct regression_workspace workspace;
struct regression regression;
const struct dictionary *dict = dataset_dict (ds);
bool save;
- workspace.psw = NULL;
memset (®ression, 0, sizeof (struct regression));
- regression.anova = true;
- regression.coeff = true;
- regression.r = true;
-
+ regression.ci = 0.95;
+ regression.stats = STATS_DEFAULT;
regression.pred = false;
regression.resid = false;
regression.ds = ds;
+ regression.origin = false;
- /* Accept an optional, completely pointless "/VARIABLES=" */
- lex_match (lexer, T_SLASH);
- if (lex_match_id (lexer, "VARIABLES"))
- {
- if (!lex_force_match (lexer, T_EQUALS))
- goto error;
- }
-
- if (!parse_variables_const (lexer, dict,
- ®ression.vars, ®ression.n_vars,
- PV_NO_DUPLICATE | PV_NUMERIC))
- goto error;
-
-
+ bool variables_seen = false;
+ bool method_seen = false;
+ bool dependent_seen = false;
while (lex_token (lexer) != T_ENDCMD)
{
lex_match (lexer, T_SLASH);
- if (lex_match_id (lexer, "DEPENDENT"))
+ if (lex_match_id (lexer, "VARIABLES"))
{
- if (!lex_force_match (lexer, T_EQUALS))
- goto error;
+ if (method_seen)
+ {
+ msg (SE, _("VARIABLES may not appear after %s"), "METHOD");
+ goto error;
+ }
+ if (dependent_seen)
+ {
+ msg (SE, _("VARIABLES may not appear after %s"), "DEPENDENT");
+ goto error;
+ }
+ variables_seen = true;
+ lex_match (lexer, T_EQUALS);
+
+ if (!parse_variables_const (lexer, dict,
+ ®ression.vars, ®ression.n_vars,
+ PV_NO_DUPLICATE | PV_NUMERIC))
+ goto error;
+ }
+ else if (lex_match_id (lexer, "DEPENDENT"))
+ {
+ dependent_seen = true;
+ lex_match (lexer, T_EQUALS);
+
+ free (regression.dep_vars);
+ regression.n_dep_vars = 0;
if (!parse_variables_const (lexer, dict,
®ression.dep_vars,
PV_NO_DUPLICATE | PV_NUMERIC))
goto error;
}
+ else if (lex_match_id (lexer, "ORIGIN"))
+ {
+ regression.origin = true;
+ }
+ else if (lex_match_id (lexer, "NOORIGIN"))
+ {
+ regression.origin = false;
+ }
else if (lex_match_id (lexer, "METHOD"))
{
+ method_seen = true;
lex_match (lexer, T_EQUALS);
if (!lex_force_match_id (lexer, "ENTER"))
{
goto error;
}
+
+ if (! variables_seen)
+ {
+ if (!parse_variables_const (lexer, dict,
+ ®ression.vars, ®ression.n_vars,
+ PV_NO_DUPLICATE | PV_NUMERIC))
+ goto error;
+ }
}
else if (lex_match_id (lexer, "STATISTICS"))
{
+ unsigned long statistics = 0;
lex_match (lexer, T_EQUALS);
while (lex_token (lexer) != T_ENDCMD
{
if (lex_match (lexer, T_ALL))
{
+ statistics = ~0;
}
else if (lex_match_id (lexer, "DEFAULTS"))
{
+ statistics |= STATS_DEFAULT;
}
else if (lex_match_id (lexer, "R"))
{
+ statistics |= STATS_R;
}
else if (lex_match_id (lexer, "COEFF"))
{
+ statistics |= STATS_COEFF;
}
else if (lex_match_id (lexer, "ANOVA"))
{
+ statistics |= STATS_ANOVA;
}
else if (lex_match_id (lexer, "BCOV"))
{
+ statistics |= STATS_BCOV;
+ }
+ else if (lex_match_id (lexer, "TOL"))
+ {
+ statistics |= STATS_TOL;
+ }
+ else if (lex_match_id (lexer, "CI"))
+ {
+ statistics |= STATS_CI;
+
+ if (lex_match (lexer, T_LPAREN) &&
+ lex_force_num (lexer))
+ {
+ regression.ci = lex_number (lexer) / 100.0;
+ lex_get (lexer);
+ if (! lex_force_match (lexer, T_RPAREN))
+ goto error;
+ }
}
else
{
goto error;
}
}
+
+ if (statistics)
+ regression.stats = statistics;
+
}
else if (lex_match_id (lexer, "SAVE"))
{
workspace.extras = 0;
workspace.res_idx = -1;
workspace.pred_idx = -1;
- workspace.writer = NULL;
+ workspace.writer = NULL;
workspace.reader = NULL;
+ workspace.residvars = NULL;
+ workspace.predvars = NULL;
if (save)
{
int i;
if (regression.resid)
{
- workspace.extras ++;
- workspace.res_idx = 0;
+ workspace.res_idx = workspace.extras ++;
workspace.residvars = xcalloc (regression.n_dep_vars, sizeof (*workspace.residvars));
for (i = 0; i < regression.n_dep_vars; ++i)
if (regression.pred)
{
- workspace.extras ++;
- workspace.pred_idx = 1;
+ workspace.pred_idx = workspace.extras ++;
workspace.predvars = xcalloc (regression.n_dep_vars, sizeof (*workspace.predvars));
for (i = 0; i < regression.n_dep_vars; ++i)
msg (SW, _("REGRESSION with SAVE ignores TEMPORARY. "
"Temporary transformations will be made permanent."));
+ if (dict_get_filter (dict))
+ msg (SW, _("REGRESSION with SAVE ignores FILTER. "
+ "All cases will be processed."));
+
workspace.writer = autopaging_writer_create (proto);
+ caseproto_unref (proto);
}
- n_splits = 0;
{
struct casegrouper *grouper;
struct casereader *group;
while (casegrouper_get_next_group (grouper, &group))
{
- workspace.psw = xrealloc (workspace.psw, ++n_splits * sizeof (*workspace.psw));
-
- run_regression (®ression, &workspace.psw[n_splits - 1],
+ run_regression (®ression,
&workspace,
group);
ok = proc_commit (ds) && ok;
}
+ if (workspace.writer)
{
- if (workspace.writer)
- {
- struct thing *thing = xmalloc (sizeof *thing);
- struct casereader *r = casewriter_make_reader (workspace.writer);
- workspace.writer = NULL;
- workspace.reader = r;
- thing->ws = xmalloc (sizeof (workspace));
- memcpy (thing->ws, &workspace, sizeof (workspace));
- thing->n_dep_vars = regression.n_dep_vars;
-
- add_transformation (ds, transX, NULL, thing);
- }
+ struct save_trans_data *save_trans_data = xmalloc (sizeof *save_trans_data);
+ struct casereader *r = casewriter_make_reader (workspace.writer);
+ workspace.writer = NULL;
+ workspace.reader = r;
+ save_trans_data->ws = xmalloc (sizeof (workspace));
+ memcpy (save_trans_data->ws, &workspace, sizeof (workspace));
+ save_trans_data->n_dep_vars = regression.n_dep_vars;
+
+ static const struct trns_class trns_class = {
+ .name = "REGRESSION",
+ .execute = save_trans_func,
+ .destroy = save_trans_free,
+ };
+ add_transformation (ds, &trns_class, save_trans_data);
}
return CMD_FAILURE;
}
-
+/* Return the size of the union of dependent and independent variables */
static size_t
get_n_all_vars (const struct regression *cmd)
{
return result;
}
+/* Fill VARS with the union of dependent and independent variables */
static void
fill_all_vars (const struct variable **vars, const struct regression *cmd)
{
+ size_t x = 0;
size_t i;
- size_t j;
- bool absent;
-
for (i = 0; i < cmd->n_vars; i++)
{
vars[i] = cmd->vars[i];
}
+
for (i = 0; i < cmd->n_dep_vars; i++)
{
- absent = true;
+ size_t j;
+ bool absent = true;
for (j = 0; j < cmd->n_vars; j++)
{
if (cmd->dep_vars[i] == cmd->vars[j])
}
if (absent)
{
- vars[i + cmd->n_vars] = cmd->dep_vars[i];
+ vars[cmd->n_vars + x++] = cmd->dep_vars[i];
}
}
}
+
+/* Fill the array VARS, with all the predictor variables from CMD, except
+ variable X */
+static void
+fill_predictor_x (const struct variable **vars, const struct variable *x, const struct regression *cmd)
+{
+ size_t i;
+ size_t n = 0;
+
+ for (i = 0; i < cmd->n_vars; i++)
+ {
+ if (cmd->vars[i] == x)
+ continue;
+
+ vars[n++] = cmd->vars[i];
+ }
+}
+
/*
Is variable k the dependent variable?
*/
*/
msg (SW,
gettext
- ("The dependent variable is equal to the independent variable."
- "The least squares line is therefore Y=X."
+ ("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] = cmd->vars[0];
return n_indep_vars;
}
-
static double
fill_covariance (gsl_matrix * cov, struct covariance *all_cov,
const struct variable **vars,
{
size_t i;
size_t j;
- size_t dep_subscript;
+ size_t dep_subscript = SIZE_MAX;
size_t *rows;
const gsl_matrix *ssizes;
const gsl_matrix *mean_matrix;
const gsl_matrix *ssize_matrix;
double result = 0.0;
- gsl_matrix *cm = covariance_calculate_unnormalized (all_cov);
+ const gsl_matrix *cm = covariance_calculate_unnormalized (all_cov);
if (cm == NULL)
return 0;
dep_subscript = i;
}
}
+ assert (dep_subscript != SIZE_MAX);
+
mean_matrix = covariance_moments (all_cov, MOMENT_MEAN);
ssize_matrix = covariance_moments (all_cov, MOMENT_NONE);
for (i = 0; i < cov->size1 - 1; i++)
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;
}
+\f
+
+struct model_container
+{
+ struct linreg **models;
+};
/*
STATISTICS subcommand output functions.
*/
-static void reg_stats_r (linreg *, void *, const struct variable *);
-static void reg_stats_coeff (linreg *, void *, const struct variable *);
-static void reg_stats_anova (linreg *, void *, const struct variable *);
-static void reg_stats_bcov (linreg *, void *, const struct variable *);
-
-static void
-statistics_keyword_output (void (*)
- (linreg *, void *, const struct variable *), bool,
- linreg *, void *, const struct variable *);
-
-
-
-static void
-subcommand_statistics (const struct regression *cmd, linreg * c, void *aux,
- const struct variable *var)
-{
- statistics_keyword_output (reg_stats_r, cmd->r, c, aux, var);
- statistics_keyword_output (reg_stats_anova, cmd->anova, c, aux, var);
- statistics_keyword_output (reg_stats_coeff, cmd->coeff, c, aux, var);
- statistics_keyword_output (reg_stats_bcov, cmd->bcov, c, aux, var);
-}
-
-
-static void
-run_regression (const struct regression *cmd,
- struct per_split_ws *psw,
- struct regression_workspace *ws,
- struct casereader *input)
+static void reg_stats_r (const struct linreg *, const struct variable *);
+static void reg_stats_coeff (const struct regression *, const struct linreg *,
+ const struct model_container *, const gsl_matrix *,
+ const struct variable *);
+static void reg_stats_anova (const struct linreg *, const struct variable *);
+static void reg_stats_bcov (const struct linreg *, const struct variable *);
+
+
+static struct linreg **
+run_regression_get_models (const struct regression *cmd,
+ struct casereader *input,
+ bool output)
{
size_t i;
+ struct model_container *model_container = XCALLOC (cmd->n_vars, struct model_container);
- int k;
struct ccase *c;
struct covariance *cov;
struct casereader *reader;
+
+ if (cmd->stats & STATS_TOL)
+ {
+ for (i = 0; i < cmd->n_vars; i++)
+ {
+ struct regression subreg;
+ subreg.origin = cmd->origin;
+ subreg.ds = cmd->ds;
+ subreg.n_vars = cmd->n_vars - 1;
+ subreg.n_dep_vars = 1;
+ subreg.vars = xmalloc (sizeof (*subreg.vars) * cmd->n_vars - 1);
+ subreg.dep_vars = xmalloc (sizeof (*subreg.dep_vars));
+ fill_predictor_x (subreg.vars, cmd->vars[i], cmd);
+ subreg.dep_vars[0] = cmd->vars[i];
+ subreg.stats = STATS_R;
+ subreg.ci = 0;
+ subreg.resid = false;
+ subreg.pred = false;
+
+ model_container[i].models =
+ run_regression_get_models (&subreg, input, false);
+ free (subreg.vars);
+ free (subreg.dep_vars);
+ }
+ }
+
size_t n_all_vars = get_n_all_vars (cmd);
const struct variable **all_vars = xnmalloc (n_all_vars, sizeof (*all_vars));
- double *means = xnmalloc (n_all_vars, sizeof (*means));
-
+ /* In the (rather pointless) case where the dependent variable is
+ the independent variable, n_all_vars == 1.
+ However this would result in a buffer overflow so we must
+ over-allocate the space required in this malloc call.
+ See bug #58599 */
+ double *means = xnmalloc (n_all_vars <= 1 ? 2 : n_all_vars,
+ sizeof (*means));
fill_all_vars (all_vars, cmd);
cov = covariance_1pass_create (n_all_vars, all_vars,
dict_get_weight (dataset_dict (cmd->ds)),
- MV_ANY);
+ MV_ANY, cmd->origin == false);
reader = casereader_clone (input);
reader = casereader_create_filter_missing (reader, all_vars, n_all_vars,
MV_ANY, NULL, NULL);
-
-
- {
+{
struct casereader *r = casereader_clone (reader);
for (; (c = casereader_read (r)) != NULL; case_unref (c))
casereader_destroy (r);
}
- psw->models = xcalloc (cmd->n_dep_vars, sizeof (*psw->models));
- for (k = 0; k < cmd->n_dep_vars; k++)
- {
+ struct linreg **models = XCALLOC (cmd->n_dep_vars, struct linreg*);
+ for (int k = 0; k < cmd->n_dep_vars; k++)
+ {
const struct variable **vars = xnmalloc (cmd->n_vars, sizeof (*vars));
const struct variable *dep_var = cmd->dep_vars[k];
int n_indep = identify_indep_vars (cmd, vars, dep_var);
- gsl_matrix *this_cm = gsl_matrix_alloc (n_indep + 1, n_indep + 1);
- double n_data = fill_covariance (this_cm, cov, vars, n_indep,
+ gsl_matrix *cov_matrix = gsl_matrix_alloc (n_indep + 1, n_indep + 1);
+ double n_data = fill_covariance (cov_matrix, cov, vars, n_indep,
dep_var, all_vars, n_all_vars, means);
- psw->models[k] = linreg_alloc (dep_var, vars, n_data, n_indep);
- psw->models[k]->depvar = dep_var;
+ models[k] = linreg_alloc (dep_var, vars, n_data, n_indep, cmd->origin);
for (i = 0; i < n_indep; i++)
{
- linreg_set_indep_variable_mean (psw->models[k], i, means[i]);
+ linreg_set_indep_variable_mean (models[k], i, means[i]);
}
- linreg_set_depvar_mean (psw->models[k], means[i]);
- /*
- For large data sets, use QR decomposition.
- */
- if (n_data > sqrt (n_indep) && n_data > REG_LARGE_DATA)
- {
- psw->models[k]->method = LINREG_QR;
- }
-
+ linreg_set_depvar_mean (models[k], means[i]);
if (n_data > 0)
{
- /*
- Find the least-squares estimates and other statistics.
- */
- linreg_fit (this_cm, psw->models[k]);
+ linreg_fit (cov_matrix, models[k]);
- if (!taint_has_tainted_successor (casereader_get_taint (input)))
+ if (output && !taint_has_tainted_successor (casereader_get_taint (input)))
{
- subcommand_statistics (cmd, psw->models[k], this_cm, dep_var);
- }
+ /*
+ Find the least-squares estimates and other statistics.
+ */
+ if (cmd->stats & STATS_R)
+ reg_stats_r (models[k], dep_var);
+
+ if (cmd->stats & STATS_ANOVA)
+ reg_stats_anova (models[k], dep_var);
+
+ if (cmd->stats & STATS_COEFF)
+ reg_stats_coeff (cmd, models[k],
+ model_container,
+ cov_matrix, dep_var);
+
+ if (cmd->stats & STATS_BCOV)
+ reg_stats_bcov (models[k], dep_var);
+ }
}
else
{
msg (SE, _("No valid data found. This command was skipped."));
}
- gsl_matrix_free (this_cm);
free (vars);
+ gsl_matrix_free (cov_matrix);
}
+ casereader_destroy (reader);
+
+ for (int i = 0; i < cmd->n_vars; i++)
+ {
+ if (model_container[i].models)
+ {
+ linreg_unref (model_container[i].models[0]);
+ }
+ free (model_container[i].models);
+ }
+ free (model_container);
+
+ free (all_vars);
+ free (means);
+ covariance_destroy (cov);
+ return models;
+}
+
+static void
+run_regression (const struct regression *cmd,
+ struct regression_workspace *ws,
+ struct casereader *input)
+{
+ struct linreg **models = run_regression_get_models (cmd, input, true);
if (ws->extras > 0)
{
- struct casereader *r = casereader_clone (reader);
-
+ struct ccase *c;
+ struct casereader *r = casereader_clone (input);
+
for (; (c = casereader_read (r)) != NULL; case_unref (c))
{
- struct ccase *outc = case_clone (c);
- for (k = 0; k < cmd->n_dep_vars; k++)
+ struct ccase *outc = case_create (casewriter_get_proto (ws->writer));
+ for (int k = 0; k < cmd->n_dep_vars; k++)
{
const struct variable **vars = xnmalloc (cmd->n_vars, sizeof (*vars));
const struct variable *dep_var = cmd->dep_vars[k];
int n_indep = identify_indep_vars (cmd, vars, dep_var);
double *vals = xnmalloc (n_indep, sizeof (*vals));
- for (i = 0; i < n_indep; i++)
+ for (int i = 0; i < n_indep; i++)
{
const union value *tmp = case_data (c, vars[i]);
vals[i] = tmp->f;
if (cmd->pred)
{
- double pred = linreg_predict (psw->models[k], vals, n_indep);
- case_data_rw_idx (outc, k * ws->extras + ws->pred_idx)->f = pred;
+ double pred = linreg_predict (models[k], vals, n_indep);
+ *case_num_rw_idx (outc, k * ws->extras + ws->pred_idx) = pred;
}
if (cmd->resid)
{
- double obs = case_data (c, psw->models[k]->depvar)->f;
- double res = linreg_residual (psw->models[k], obs, vals, n_indep);
- case_data_rw_idx (outc, k * ws->extras + ws->res_idx)->f = res;
+ double obs = case_num (c, linreg_dep_var (models[k]));
+ double res = linreg_residual (models[k], obs, vals, n_indep);
+ *case_num_rw_idx (outc, k * ws->extras + ws->res_idx) = res;
}
- }
+ free (vals);
+ free (vars);
+ }
casewriter_write (ws->writer, outc);
}
casereader_destroy (r);
}
- casereader_destroy (reader);
-
+ for (int k = 0; k < cmd->n_dep_vars; k++)
+ {
+ linreg_unref (models[k]);
+ }
- free (all_vars);
- free (means);
+ free (models);
casereader_destroy (input);
- covariance_destroy (cov);
}
-\f
-
+\f
static void
-reg_stats_r (linreg * c, void *aux UNUSED, const struct variable *var)
+reg_stats_r (const struct linreg * c, const struct variable *var)
{
- struct tab_table *t;
- int n_rows = 2;
- int n_cols = 5;
- double rsq;
- double adjrsq;
- double std_error;
-
- assert (c != NULL);
- rsq = linreg_ssreg (c) / linreg_sst (c);
- adjrsq = rsq -
- (1.0 - rsq) * linreg_n_coeffs (c) / (linreg_n_obs (c) -
- linreg_n_coeffs (c) - 1);
- std_error = sqrt (linreg_mse (c));
- 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);
- tab_vline (t, TAL_0, 1, 0, 0);
-
- tab_text (t, 1, 0, TAB_CENTER | TAT_TITLE, _("R"));
- tab_text (t, 2, 0, TAB_CENTER | TAT_TITLE, _("R Square"));
- tab_text (t, 3, 0, TAB_CENTER | TAT_TITLE, _("Adjusted R Square"));
- tab_text (t, 4, 0, TAB_CENTER | TAT_TITLE, _("Std. Error of the Estimate"));
- tab_double (t, 1, 1, TAB_RIGHT, sqrt (rsq), NULL);
- tab_double (t, 2, 1, TAB_RIGHT, rsq, NULL);
- tab_double (t, 3, 1, TAB_RIGHT, adjrsq, NULL);
- tab_double (t, 4, 1, TAB_RIGHT, std_error, NULL);
- tab_title (t, _("Model Summary (%s)"), var_to_string (var));
- tab_submit (t);
+ struct pivot_table *table = pivot_table_create__ (
+ pivot_value_new_text_format (N_("Model Summary (%s)"),
+ var_to_string (var)),
+ "Model Summary");
+
+ pivot_dimension_create (table, PIVOT_AXIS_COLUMN, N_("Statistics"),
+ N_("R"), N_("R Square"), N_("Adjusted R Square"),
+ N_("Std. Error of the Estimate"));
+
+ double rsq = linreg_ssreg (c) / linreg_sst (c);
+ double adjrsq = (rsq -
+ (1.0 - rsq) * linreg_n_coeffs (c)
+ / (linreg_n_obs (c) - linreg_n_coeffs (c) - 1));
+ double std_error = sqrt (linreg_mse (c));
+
+ double entries[] = {
+ sqrt (rsq), rsq, adjrsq, std_error
+ };
+ for (size_t i = 0; i < sizeof entries / sizeof *entries; i++)
+ pivot_table_put1 (table, i, pivot_value_new_number (entries[i]));
+
+ pivot_table_submit (table);
}
/*
Table showing estimated regression coefficients.
*/
static void
-reg_stats_coeff (linreg * c, void *aux_, const struct variable *var)
+reg_stats_coeff (const struct regression *cmd, const struct linreg *c,
+ const struct model_container *mc, const gsl_matrix *cov,
+ const struct variable *var)
{
- size_t j;
- int n_cols = 7;
- int n_rows;
- int this_row;
- double t_stat;
- double pval;
- double std_err;
- double beta;
- const char *label;
-
- const struct variable *v;
- struct tab_table *t;
- gsl_matrix *cov = aux_;
-
- assert (c != NULL);
- n_rows = linreg_n_coeffs (c) + 3;
-
- t = tab_create (n_cols, n_rows);
- tab_headers (t, 2, 0, 1, 0);
- 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);
- tab_vline (t, TAL_0, 1, 0, 0);
-
- tab_text (t, 2, 0, TAB_CENTER | TAT_TITLE, _("B"));
- tab_text (t, 3, 0, TAB_CENTER | TAT_TITLE, _("Std. Error"));
- tab_text (t, 4, 0, TAB_CENTER | TAT_TITLE, _("Beta"));
- 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)"));
- tab_double (t, 2, 1, 0, linreg_intercept (c), NULL);
- std_err = sqrt (gsl_matrix_get (linreg_cov (c), 0, 0));
- tab_double (t, 3, 1, 0, std_err, NULL);
- 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),
- (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++)
+ struct pivot_table *table = pivot_table_create__ (
+ pivot_value_new_text_format (N_("Coefficients (%s)"), var_to_string (var)),
+ "Coefficients");
+
+ struct pivot_dimension *statistics = pivot_dimension_create (
+ table, PIVOT_AXIS_COLUMN, N_("Statistics"));
+ pivot_category_create_group (statistics->root,
+ N_("Unstandardized Coefficients"),
+ N_("B"), N_("Std. Error"));
+ pivot_category_create_group (statistics->root,
+ N_("Standardized Coefficients"), N_("Beta"));
+ pivot_category_create_leaves (statistics->root, N_("t"),
+ N_("Sig."), PIVOT_RC_SIGNIFICANCE);
+ if (cmd->stats & STATS_CI)
{
- struct string tstr;
- ds_init_empty (&tstr);
- this_row = j + 2;
-
- v = linreg_indep_var (c, j);
- label = var_to_string (v);
- /* Do not overwrite the variable's name. */
- ds_put_cstr (&tstr, label);
- tab_text (t, 1, this_row, TAB_CENTER, ds_cstr (&tstr));
- /*
- Regression coefficients.
- */
- tab_double (t, 2, this_row, 0, linreg_coeff (c, j), NULL);
- /*
- Standard error of the coefficients.
- */
- std_err = sqrt (gsl_matrix_get (linreg_cov (c), j + 1, j + 1));
- tab_double (t, 3, this_row, 0, std_err, NULL);
- /*
- Standardized coefficient, i.e., regression coefficient
- if all variables had unit variance.
- */
- beta = sqrt (gsl_matrix_get (cov, j, j));
- beta *= linreg_coeff (c, j) /
- sqrt (gsl_matrix_get (cov, cov->size1 - 1, cov->size2 - 1));
- tab_double (t, 4, this_row, 0, beta, NULL);
-
- /*
- Test statistic for H0: coefficient is 0.
- */
- t_stat = linreg_coeff (c, j) / std_err;
- tab_double (t, 5, this_row, 0, t_stat, NULL);
- /*
- P values for the test statistic above.
- */
- pval =
- 2 * gsl_cdf_tdist_Q (fabs (t_stat),
- (double) (linreg_n_obs (c) -
- linreg_n_coeffs (c) - 1));
- tab_double (t, 6, this_row, 0, pval, NULL);
- ds_destroy (&tstr);
+ struct pivot_category *interval = pivot_category_create_group__ (
+ statistics->root, pivot_value_new_text_format (
+ N_("%g%% Confidence Interval for B"),
+ cmd->ci * 100.0));
+ pivot_category_create_leaves (interval, N_("Lower Bound"),
+ N_("Upper Bound"));
}
- tab_title (t, _("Coefficients (%s)"), var_to_string (var));
- tab_submit (t);
-}
-/*
- Display the ANOVA table.
-*/
-static void
-reg_stats_anova (linreg * c, void *aux UNUSED, const struct variable *var)
-{
- int n_cols = 7;
- int n_rows = 4;
- const double msm = linreg_ssreg (c) / linreg_dfmodel (c);
- const double mse = linreg_mse (c);
- const double F = msm / mse;
- const double pval = gsl_cdf_fdist_Q (F, c->dfm, c->dfe);
-
- struct tab_table *t;
+ if (cmd->stats & STATS_TOL)
+ pivot_category_create_group (statistics->root,
+ N_("Collinearity Statistics"),
+ N_("Tolerance"), N_("VIF"));
- assert (c != NULL);
- t = tab_create (n_cols, n_rows);
- tab_headers (t, 2, 0, 1, 0);
- tab_box (t, TAL_2, TAL_2, -1, TAL_1, 0, 0, n_cols - 1, n_rows - 1);
+ struct pivot_dimension *variables = pivot_dimension_create (
+ table, PIVOT_AXIS_ROW, N_("Variables"));
- tab_hline (t, TAL_2, 0, n_cols - 1, 1);
- tab_vline (t, TAL_2, 2, 0, n_rows - 1);
- tab_vline (t, TAL_0, 1, 0, 0);
+ double df = linreg_n_obs (c) - linreg_n_coeffs (c) - 1;
+ double q = (1 - cmd->ci) / 2.0; /* 2-tailed test */
+ double tval = gsl_cdf_tdist_Qinv (q, df);
- tab_text (t, 2, 0, TAB_CENTER | TAT_TITLE, _("Sum of Squares"));
- tab_text (t, 3, 0, TAB_CENTER | TAT_TITLE, _("df"));
- tab_text (t, 4, 0, TAB_CENTER | TAT_TITLE, _("Mean Square"));
- tab_text (t, 5, 0, TAB_CENTER | TAT_TITLE, _("F"));
- tab_text (t, 6, 0, TAB_CENTER | TAT_TITLE, _("Significance"));
+ if (!cmd->origin)
+ {
+ int var_idx = pivot_category_create_leaf (
+ variables->root, pivot_value_new_text (N_("(Constant)")));
+
+ double std_err = sqrt (gsl_matrix_get (linreg_cov (c), 0, 0));
+ double t_stat = linreg_intercept (c) / std_err;
+ double base_entries[] = {
+ linreg_intercept (c),
+ std_err,
+ 0.0,
+ t_stat,
+ 2.0 * gsl_cdf_tdist_Q (fabs (t_stat),
+ linreg_n_obs (c) - linreg_n_coeffs (c)),
+ };
+
+ size_t col = 0;
+ for (size_t i = 0; i < sizeof base_entries / sizeof *base_entries; i++)
+ pivot_table_put2 (table, col++, var_idx,
+ pivot_value_new_number (base_entries[i]));
+
+ if (cmd->stats & STATS_CI)
+ {
+ double interval_entries[] = {
+ linreg_intercept (c) - tval * std_err,
+ linreg_intercept (c) + tval * std_err,
+ };
+
+ for (size_t i = 0; i < sizeof interval_entries / sizeof *interval_entries; i++)
+ pivot_table_put2 (table, col++, var_idx,
+ pivot_value_new_number (interval_entries[i]));
+ }
+ }
- tab_text (t, 1, 1, TAB_LEFT | TAT_TITLE, _("Regression"));
- tab_text (t, 1, 2, TAB_LEFT | TAT_TITLE, _("Residual"));
- tab_text (t, 1, 3, TAB_LEFT | TAT_TITLE, _("Total"));
+ for (size_t j = 0; j < linreg_n_coeffs (c); j++)
+ {
+ const struct variable *v = linreg_indep_var (c, j);
+ int var_idx = pivot_category_create_leaf (
+ variables->root, pivot_value_new_variable (v));
+
+ double std_err = sqrt (gsl_matrix_get (linreg_cov (c), j + 1, j + 1));
+ double t_stat = linreg_coeff (c, j) / std_err;
+ double base_entries[] = {
+ linreg_coeff (c, j),
+ sqrt (gsl_matrix_get (linreg_cov (c), j + 1, j + 1)),
+ (sqrt (gsl_matrix_get (cov, j, j)) * linreg_coeff (c, j) /
+ sqrt (gsl_matrix_get (cov, cov->size1 - 1, cov->size2 - 1))),
+ t_stat,
+ 2 * gsl_cdf_tdist_Q (fabs (t_stat), df)
+ };
+
+ size_t col = 0;
+ for (size_t i = 0; i < sizeof base_entries / sizeof *base_entries; i++)
+ pivot_table_put2 (table, col++, var_idx,
+ pivot_value_new_number (base_entries[i]));
+
+ if (cmd->stats & STATS_CI)
+ {
+ double interval_entries[] = {
+ linreg_coeff (c, j) - tval * std_err,
+ linreg_coeff (c, j) + tval * std_err,
+ };
+
+
+ for (size_t i = 0; i < sizeof interval_entries / sizeof *interval_entries; i++)
+ pivot_table_put2 (table, col++, var_idx,
+ pivot_value_new_number (interval_entries[i]));
+ }
+
+ if (cmd->stats & STATS_TOL)
+ {
+ {
+ struct linreg *m = mc[j].models[0];
+ double rsq = linreg_ssreg (m) / linreg_sst (m);
+ pivot_table_put2 (table, col++, var_idx, pivot_value_new_number (1.0 - rsq));
+ pivot_table_put2 (table, col++, var_idx, pivot_value_new_number (1.0 / (1.0 - rsq)));
+ }
+ }
+ }
- /* Sums of Squares */
- 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);
+ pivot_table_submit (table);
+}
+/*
+ Display the ANOVA table.
+*/
+static void
+reg_stats_anova (const struct linreg * c, const struct variable *var)
+{
+ struct pivot_table *table = pivot_table_create__ (
+ pivot_value_new_text_format (N_("ANOVA (%s)"), var_to_string (var)),
+ "ANOVA");
- /* Degrees of freedom */
- tab_text_format (t, 3, 1, TAB_RIGHT, "%g", c->dfm);
- tab_text_format (t, 3, 2, TAB_RIGHT, "%g", c->dfe);
- tab_text_format (t, 3, 3, TAB_RIGHT, "%g", c->dft);
+ pivot_dimension_create (table, PIVOT_AXIS_COLUMN, N_("Statistics"),
+ N_("Sum of Squares"), PIVOT_RC_OTHER,
+ N_("df"), PIVOT_RC_INTEGER,
+ N_("Mean Square"), PIVOT_RC_OTHER,
+ N_("F"), PIVOT_RC_OTHER,
+ N_("Sig."), PIVOT_RC_SIGNIFICANCE);
- /* Mean Squares */
- tab_double (t, 4, 1, TAB_RIGHT, msm, NULL);
- tab_double (t, 4, 2, TAB_RIGHT, mse, NULL);
+ pivot_dimension_create (table, PIVOT_AXIS_ROW, N_("Source"),
+ N_("Regression"), N_("Residual"), N_("Total"));
- tab_double (t, 5, 1, 0, F, NULL);
+ double msm = linreg_ssreg (c) / linreg_dfmodel (c);
+ double mse = linreg_mse (c);
+ double F = msm / mse;
- tab_double (t, 6, 1, 0, pval, NULL);
+ struct entry
+ {
+ int stat_idx;
+ int source_idx;
+ double x;
+ }
+ entries[] = {
+ /* Sums of Squares. */
+ { 0, 0, linreg_ssreg (c) },
+ { 0, 1, linreg_sse (c) },
+ { 0, 2, linreg_sst (c) },
+ /* Degrees of freedom. */
+ { 1, 0, linreg_dfmodel (c) },
+ { 1, 1, linreg_dferror (c) },
+ { 1, 2, linreg_dftotal (c) },
+ /* Mean Squares. */
+ { 2, 0, msm },
+ { 2, 1, mse },
+ /* F */
+ { 3, 0, F },
+ /* Significance. */
+ { 4, 0, gsl_cdf_fdist_Q (F, linreg_dfmodel (c), linreg_dferror (c)) },
+ };
+ for (size_t i = 0; i < sizeof entries / sizeof *entries; i++)
+ {
+ const struct entry *e = &entries[i];
+ pivot_table_put2 (table, e->stat_idx, e->source_idx,
+ pivot_value_new_number (e->x));
+ }
- tab_title (t, _("ANOVA (%s)"), var_to_string (var));
- tab_submit (t);
+ pivot_table_submit (table);
}
static void
-reg_stats_bcov (linreg * c, void *aux UNUSED, const struct variable *var)
+reg_stats_bcov (const struct linreg * c, const struct variable *var)
{
- int n_cols;
- int n_rows;
- int i;
- int k;
- int row;
- int col;
- const char *label;
- struct tab_table *t;
-
- assert (c != NULL);
- n_cols = c->n_indeps + 1 + 2;
- n_rows = 2 * (c->n_indeps + 1);
- t = tab_create (n_cols, n_rows);
- tab_headers (t, 2, 0, 1, 0);
- 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);
- tab_vline (t, TAL_0, 1, 0, 0);
- tab_text (t, 0, 0, TAB_CENTER | TAT_TITLE, _("Model"));
- tab_text (t, 1, 1, TAB_CENTER | TAT_TITLE, _("Covariances"));
- for (i = 0; i < linreg_n_coeffs (c); i++)
- {
- const struct variable *v = linreg_indep_var (c, i);
- label = var_to_string (v);
- tab_text (t, 2, i, TAB_CENTER, label);
- tab_text (t, i + 2, 0, TAB_CENTER, label);
- for (k = 1; k < linreg_n_coeffs (c); k++)
- {
- col = (i <= k) ? k : i;
- row = (i <= k) ? i : k;
- tab_double (t, k + 2, i, TAB_CENTER,
- gsl_matrix_get (c->cov, row, col), NULL);
- }
- }
- tab_title (t, _("Coefficient Correlations (%s)"), var_to_string (var));
- tab_submit (t);
-}
+ struct pivot_table *table = pivot_table_create__ (
+ pivot_value_new_text_format (N_("Coefficient Correlations (%s)"),
+ var_to_string (var)),
+ "Coefficient Correlations");
-static void
-statistics_keyword_output (void (*function)
- (linreg *, void *, const struct variable * var),
- bool keyword, linreg * c, void *aux,
- const struct variable *var)
-{
- if (keyword)
+ for (size_t i = 0; i < 2; i++)
{
- (*function) (c, aux, var);
+ struct pivot_dimension *models = pivot_dimension_create (
+ table, i ? PIVOT_AXIS_ROW : PIVOT_AXIS_COLUMN, N_("Models"));
+ for (size_t j = 0; j < linreg_n_coeffs (c); j++)
+ pivot_category_create_leaf (
+ models->root, pivot_value_new_variable (
+ linreg_indep_var (c, j)));
}
+
+ pivot_dimension_create (table, PIVOT_AXIS_ROW, N_("Statistics"),
+ N_("Covariances"));
+
+ for (size_t i = 0; i < linreg_n_coeffs (c); i++)
+ for (size_t k = 0; k < linreg_n_coeffs (c); k++)
+ {
+ double cov = gsl_matrix_get (linreg_cov (c), MIN (i, k), MAX (i, k));
+ pivot_table_put3 (table, k, i, 0, pivot_value_new_number (cov));
+ }
+
+ pivot_table_submit (table);
}