def anova_single(model, **kwargs):
"""
ANOVA table for one fitted linear model.
Parameters
----------
model : fitted linear model results instance
A fitted linear model
typ : int or str {1,2,3} or {"I","II","III"}
Type of sum of squares to use.
**kwargs**
scale : float
Estimate of variance, If None, will be estimated from the largest
model. Default is None.
test : str {"F", "Chisq", "Cp"} or None
Test statistics to provide. Default is "F".
Notes
-----
Use of this function is discouraged. Use anova_lm instead.
"""
test = kwargs.get("test", "F")
scale = kwargs.get("scale", None)
typ = kwargs.get("typ", 1)
robust = kwargs.get("robust", None)
if robust:
robust = robust.lower()
endog = model.model.endog
exog = model.model.exog
nobs = exog.shape[0]
response_name = model.model.endog_names
design_info = model.model._data._orig_exog.design_info
exog_names = model.model.exog_names
# +1 for resids
n_rows = (len(design_info.terms) - _has_intercept(design_info) + 1)
pr_test = "PR(>%s)" % test
names = ['df', 'sum_sq', 'mean_sq', test, pr_test]
table = DataFrame(np.zeros((n_rows, 5)), columns = names)
if typ in [1,"I"]:
return anova1_lm_single(model, endog, exog, nobs, design_info, table,
n_rows, test, pr_test, robust)
elif typ in [2, "II"]:
return anova2_lm_single(model, design_info, n_rows, test, pr_test,
robust)
elif typ in [3, "III"]:
return anova3_lm_single(model, design_info, n_rows, test, pr_test,
robust)
elif typ in [4, "IV"]:
raise NotImplemented("Type IV not yet implemented")
else: # pragma: no cover
raise ValueError("Type %s not understood" % str(typ))
def anova_single(model, **kwargs):
"""
Anova table for one fitted linear model.
Parameters
----------
model : fitted linear model results instance
A fitted linear model
typ : int or str {1,2,3} or {"I","II","III"}
Type of sum of squares to use.
**kwargs**
scale : float
Estimate of variance, If None, will be estimated from the largest
model. Default is None.
test : str {"F", "Chisq", "Cp"} or None
Test statistics to provide. Default is "F".
Notes
-----
Use of this function is discouraged. Use anova_lm instead.
"""
test = kwargs.get("test", "F")
scale = kwargs.get("scale", None)
typ = kwargs.get("typ", 1)
robust = kwargs.get("robust", None)
if robust:
robust = robust.lower()
endog = model.model.endog
exog = model.model.exog
nobs = exog.shape[0]
response_name = model.model.endog_names
design_info = model.model.data.design_info
exog_names = model.model.exog_names
# +1 for resids
n_rows = (len(design_info.terms) - _has_intercept(design_info) + 1)
pr_test = "PR(>%s)" % test
names = ['df', 'sum_sq', 'mean_sq', test, pr_test]
table = DataFrame(np.zeros((n_rows, 5)), columns=names)
if typ in [1, "I"]:
return anova1_lm_single(model, endog, exog, nobs, design_info, table,
n_rows, test, pr_test, robust)
elif typ in [2, "II"]:
return anova2_lm_single(model, design_info, n_rows, test, pr_test,
robust)
elif typ in [3, "III"]:
return anova3_lm_single(model, design_info, n_rows, test, pr_test,
robust)
elif typ in [4, "IV"]:
raise NotImplementedError("Type IV not yet implemented")
else: # pragma: no cover
raise ValueError("Type %s not understood" % str(typ))
def anova3_lm_single(model, design_info, n_rows, test, pr_test, robust):
n_rows += _has_intercept(design_info)
terms_info = design_info.terms
names = ['sum_sq', 'df', test, pr_test]
table = DataFrame(np.zeros((n_rows, 4)), columns = names)
cov = _get_covariance(model, robust)
col_order = []
index = []
for i, term in enumerate(terms_info):
# grab term, hypothesis is that term == 0
cols = design_info.slice(term)
L1 = np.eye(model.model.exog.shape[1])[cols]
L12 = L1
r = L1.shape[0]
if test == 'F':
f = model.f_test(L12, cov_p=cov)
table.ix[i][test] = test_value = f.fvalue
table.ix[i][pr_test] = f.pvalue
# need to back out SSR from f_test
table.ix[i]['df'] = r
#col_order.append(cols.start)
index.append(term.name())
table.index = Index(index + ['Residual'])
#NOTE: Don't need to sort because terms are an ordered dict now
#table = table.ix[np.argsort(col_order + [model.model.exog.shape[1]+1])]
# back out sum of squares from f_test
ssr = table[test] * table['df'] * model.ssr/model.df_resid
table['sum_sq'] = ssr
# fill in residual
table.ix['Residual'][['sum_sq','df', test, pr_test]] = (model.ssr,
model.df_resid,
np.nan, np.nan)
return table
def anova3_lm_single(model, design_info, n_rows, test, pr_test, robust):
n_rows += _has_intercept(design_info)
terms_info = design_info.terms
names = ['sum_sq', 'df', test, pr_test]
table = DataFrame(np.zeros((n_rows, 4)), columns = names)
cov = _get_covariance(model, robust)
col_order = []
index = []
for i, term in enumerate(terms_info):
# grab term, hypothesis is that term == 0
cols = design_info.slice(term)
L1 = np.eye(model.model.exog.shape[1])[cols]
L12 = L1
r = L1.shape[0]
if test == 'F':
f = model.f_test(L12, cov_p=cov)
table.loc[table.index[i], test] = test_value = f.fvalue
table.loc[table.index[i], pr_test] = f.pvalue
# need to back out SSR from f_test
table.loc[table.index[i], 'df'] = r
#col_order.append(cols.start)
index.append(term.name())
table.index = Index(index + ['Residual'])
#NOTE: Do not need to sort because terms are an ordered dict now
#table = table.iloc[np.argsort(col_order + [model.model.exog.shape[1]+1])]
# back out sum of squares from f_test
ssr = table[test] * table['df'] * model.ssr/model.df_resid
table['sum_sq'] = ssr
# fill in residual
table.loc['Residual', ['sum_sq','df', test, pr_test]] = (model.ssr,
model.df_resid,
np.nan, np.nan)
return table
