def setup_class(cls):
df = data_bin
res = GLM(df['constrict'], df[['const', 'log_rate', 'log_volumne']],
family=families.Binomial()).fit(attach_wls=True, atol=1e-10)
cls.infl1 = res.get_influence()
cls.infl0 = MLEInfluence(res)
def setup_class(cls):
df = data_bin
res = GLM(df['constrict'], df[['const', 'log_rate', 'log_volumne']],
family=families.Binomial()).fit(attach_wls=True, atol=1e-10)
cls.infl1 = res.get_influence()
cls.infl0 = MLEInfluence(res)
def setup_class(cls):
yi = np.array([0, 2, 14, 19, 30])
ni = 40 * np.ones(len(yi))
xi = np.arange(1, len(yi) + 1)
exog = np.column_stack((np.ones(len(yi)), xi))
endog = np.column_stack((yi, ni - yi))
res = GLM(endog, exog, family=families.Binomial()).fit()
cls.infl1 = res.get_influence()
cls.infl0 = MLEInfluence(res)
cls.cd_rtol = 5e-5
def setup_class(cls):
yi = np.array([0, 2, 14, 19, 30])
ni = 40 * np.ones(len(yi))
xi = np.arange(1, len(yi) + 1)
exog = np.column_stack((np.ones(len(yi)), xi))
endog = np.column_stack((yi, ni - yi))
res = GLM(endog, exog, family=families.Binomial()).fit()
cls.infl1 = res.get_influence()
cls.infl0 = MLEInfluence(res)
cls.cd_rtol = 5e-5
def test_influence_glm_bernoulli():
# example uses Finney's data and is used in Pregibon 1981
df = data_bin
results_sas = np.asarray(results_sas_df)
res = GLM(df['constrict'], df[['const', 'log_rate', 'log_volumne']],
family=families.Binomial()).fit(attach_wls=True, atol=1e-10)
infl = res.get_influence(observed=False)
k_vars = 3
assert_allclose(infl.dfbetas, results_sas[:, 5:8], atol=1e-4)
assert_allclose(infl.d_params, results_sas[:, 5:8] * res.bse.values, atol=1e-4)
assert_allclose(infl.cooks_distance[0] * k_vars, results_sas[:, 8], atol=6e-5)
assert_allclose(infl.hat_matrix_diag, results_sas[:, 4], atol=6e-5)
c_bar = infl.cooks_distance[0] * 3 * (1 - infl.hat_matrix_diag)
assert_allclose(c_bar, results_sas[:, 9], atol=6e-5)
def test_influence_glm_bernoulli():
# example uses Finney's data and is used in Pregibon 1981
df = data_bin
results_sas = np.asarray(results_sas_df)
res = GLM(df['constrict'], df[['const', 'log_rate', 'log_volumne']],
family=families.Binomial()).fit(attach_wls=True, atol=1e-10)
infl = res.get_influence(observed=False)
k_vars = 3
assert_allclose(infl.dfbetas, results_sas[:, 5:8], atol=1e-4)
assert_allclose(infl.d_params, results_sas[:, 5:8] * res.bse.values, atol=1e-4)
assert_allclose(infl.cooks_distance[0] * k_vars, results_sas[:, 8], atol=6e-5)
assert_allclose(infl.hat_matrix_diag, results_sas[:, 4], atol=6e-5)
c_bar = infl.cooks_distance[0] * 3 * (1 - infl.hat_matrix_diag)
assert_allclose(c_bar, results_sas[:, 9], atol=6e-5)
#
# This measures are based on a one-step approximation to the the results
# for deleting one observation. One-step approximations are usually accurate
# for small changes but underestimate the magnitude of large changes. Event
# though large changes are underestimated, they still show clearly the
# effect of influential observations
#
# In this example observation 4 and 18 have a large standardized residual
# and large Cook's distance, but not a large leverage. Observation 13 has
# the largest leverage but only small Cook's distance and not a large
# studentized residual.
#
# Only the two observations 4 and 18 have a large impact on the parameter
# estimates.
infl = res.get_influence(observed=False)
summ_df = infl.summary_frame()
summ_df.sort_values("cooks_d", ascending=False)[:10]
fig = infl.plot_influence()
fig.tight_layout(pad=1.0)
fig = infl.plot_index(y_var="cooks",
threshold=2 * infl.cooks_distance[0].mean())
fig.tight_layout(pad=1.0)
fig = infl.plot_index(y_var="resid", threshold=1)
fig.tight_layout(pad=1.0)
fig = infl.plot_index(y_var="dfbeta", idx=1, threshold=0.5)
#
# This measures are based on a one-step approximation to the the results
# for deleting one observation. One-step approximations are usually accurate
# for small changes but underestimate the magnitude of large changes. Event
# though large changes are underestimated, they still show clearly the
# effect of influential observations
#
# In this example observation 4 and 18 have a large standardized residual
# and large Cook's distance, but not a large leverage. Observation 13 has
# the largest leverage but only small Cook's distance and not a large
# studentized residual.
#
# Only the two observations 4 and 18 have a large impact on the parameter
# estimates.
infl = res.get_influence(observed=False)
summ_df = infl.summary_frame()
summ_df.sort_values('cooks_d', ascending=False)[:10]
infl.plot_influence()
infl.plot_index(y_var='cooks', threshold=2 * infl.cooks_distance[0].mean())
infl.plot_index(y_var='resid', threshold=1)
infl.plot_index(y_var='dfbeta', idx=1, threshold=0.5)
infl.plot_index(y_var='dfbeta', idx=2, threshold=0.5)
infl.plot_index(y_var='dfbeta', idx=0, threshold=0.5)
