def test_glm(self):
# prelimnimary, getting started with basic test for GLM.get_prediction
from statsmodels.genmod.generalized_linear_model import GLM
res_wls = self.res_wls
mod_wls = res_wls.model
y, X, wi = mod_wls.endog, mod_wls.exog, mod_wls.weights
w_sqrt = np.sqrt(wi) # notation wi is weights, `w` is var
mod_glm = GLM(y * w_sqrt, X * w_sqrt[:,None])
# compare using t distribution
res_glm = mod_glm.fit(use_t=True)
pred_glm = res_glm.get_prediction()
sf_glm = pred_glm.summary_frame()
pred_res_wls = res_wls.get_prediction()
sf_wls = pred_res_wls.summary_frame()
n_compare = 30 # in glm with predict wendog
assert_allclose(sf_glm.values[:n_compare],
sf_wls.values[:n_compare, :4])
# compare using normal distribution
res_glm = mod_glm.fit() # default use_t=False
pred_glm = res_glm.get_prediction()
sf_glm = pred_glm.summary_frame()
res_wls = mod_wls.fit(use_t=False)
pred_res_wls = res_wls.get_prediction()
sf_wls = pred_res_wls.summary_frame()
assert_allclose(sf_glm.values[:n_compare],
sf_wls.values[:n_compare, :4])
# function for parameter transformation
# should be separate test method
from statsmodels.genmod._prediction import params_transform_univariate
rates = params_transform_univariate(res_glm.params, res_glm.cov_params())
rates2 = np.column_stack((np.exp(res_glm.params),
res_glm.bse * np.exp(res_glm.params),
np.exp(res_glm.conf_int())))
assert_allclose(rates.summary_frame().values, rates2, rtol=1e-13)
from statsmodels.genmod.families import links
# with identity transform
pt = params_transform_univariate(res_glm.params, res_glm.cov_params(), link=links.identity())
assert_allclose(pt.tvalues, res_glm.tvalues, rtol=1e-13)
assert_allclose(pt.se_mean, res_glm.bse, rtol=1e-13)
ptt = pt.t_test()
assert_allclose(ptt[0], res_glm.tvalues, rtol=1e-13)
assert_allclose(ptt[1], res_glm.pvalues, rtol=1e-13)
# prediction with exog and no weights does not error
res_glm = mod_glm.fit()
pred_glm = res_glm.get_prediction(X)
def params_transform_univariate(params, cov_params, link=None, transform=None,
row_labels=None):
"""
results for univariate, nonlinear, monotonicaly transformed parameters
This provides transformed values, standard errors and confidence interval
for transformations of parameters, for example in calculating rates with
`exp(params)` in the case of Poisson or other models with exponential
mean function.
"""
from statsmodels.genmod.families import links
if link is None and transform is None:
link = links.Log()
if row_labels is None and hasattr(params, 'index'):
row_labels = params.index
params = np.asarray(params)
predicted_mean = link.inverse(params)
link_deriv = link.inverse_deriv(params)
var_pred_mean = link_deriv**2 * np.diag(cov_params)
# TODO: do we want covariance also, or just var/se
dist = stats.norm
# TODO: need ci for linear prediction, method of `lin_pred
linpred = PredictionResults(params, np.diag(cov_params), dist=dist,
row_labels=row_labels, link=links.identity())
res = PredictionResults(predicted_mean, var_pred_mean, dist=dist,
row_labels=row_labels, linpred=linpred, link=link)
return res
def test_glm(self):
# prelimnimary, getting started with basic test for GLM.get_prediction
from statsmodels.genmod.generalized_linear_model import GLM
res_wls = self.res_wls
mod_wls = res_wls.model
y, X, wi = mod_wls.endog, mod_wls.exog, mod_wls.weights
w_sqrt = np.sqrt(wi) # notation wi is weights, `w` is var
mod_glm = GLM(y * w_sqrt, X * w_sqrt[:,None])
# compare using t distribution
res_glm = mod_glm.fit(use_t=True)
pred_glm = res_glm.get_prediction()
sf_glm = pred_glm.summary_frame()
pred_res_wls = res_wls.get_prediction()
sf_wls = pred_res_wls.summary_frame()
n_compare = 30 # in glm with predict wendog
assert_allclose(sf_glm.values[:n_compare],
sf_wls.values[:n_compare, :4])
# compare using normal distribution
res_glm = mod_glm.fit() # default use_t=False
pred_glm = res_glm.get_prediction()
sf_glm = pred_glm.summary_frame()
res_wls = mod_wls.fit(use_t=False)
pred_res_wls = res_wls.get_prediction()
sf_wls = pred_res_wls.summary_frame()
assert_allclose(sf_glm.values[:n_compare],
sf_wls.values[:n_compare, :4])
# function for parameter transformation
# should be separate test method
from statsmodels.genmod._prediction import params_transform_univariate
rates = params_transform_univariate(res_glm.params, res_glm.cov_params())
rates2 = np.column_stack((np.exp(res_glm.params),
res_glm.bse * np.exp(res_glm.params),
np.exp(res_glm.conf_int())))
assert_allclose(rates.summary_frame().values, rates2, rtol=1e-13)
from statsmodels.genmod.families import links
# with identity transform
pt = params_transform_univariate(res_glm.params, res_glm.cov_params(), link=links.identity())
assert_allclose(pt.tvalues, res_glm.tvalues, rtol=1e-13)
assert_allclose(pt.se_mean, res_glm.bse, rtol=1e-13)
ptt = pt.t_test()
assert_allclose(ptt[0], res_glm.tvalues, rtol=1e-13)
assert_allclose(ptt[1], res_glm.pvalues, rtol=1e-13)
# prediction with exog and no weights does not error
res_glm = mod_glm.fit()
pred_glm = res_glm.get_prediction(X)
# check that list works, issue 4437
x = res_glm.model.exog.mean(0)
pred_res3 = res_glm.get_prediction(x)
ci3 = pred_res3.conf_int()
pred_res3b = res_glm.get_prediction(x.tolist())
ci3b = pred_res3b.conf_int()
assert_allclose(pred_res3b.se_mean, pred_res3.se_mean, rtol=1e-13)
assert_allclose(ci3b, ci3, rtol=1e-13)
res_df = pred_res3b.summary_frame()
assert_equal(res_df.index.values, [0])
x = res_glm.model.exog[-2:]
pred_res3 = res_glm.get_prediction(x)
ci3 = pred_res3.conf_int()
pred_res3b = res_glm.get_prediction(x.tolist())
ci3b = pred_res3b.conf_int()
assert_allclose(pred_res3b.se_mean, pred_res3.se_mean, rtol=1e-13)
assert_allclose(ci3b, ci3, rtol=1e-13)
res_df = pred_res3b.summary_frame()
assert_equal(res_df.index.values, [0, 1])
w_sqrt = np.sqrt(w)
mod_glm = GLM(y/w_sqrt, X/w_sqrt[:,None])
res_glm = mod_glm.fit()
pred_glm = res_glm.get_prediction()
print(pred_glm.summary_frame().head())
res_glm_t = mod_glm.fit(use_t=True)
pred_glm_t = res_glm_t.get_prediction()
print(pred_glm_t.summary_frame().head())
rates = params_transform_univariate(res_glm.params, res_glm.cov_params())
print('\nRates exp(params)')
print(rates.summary_frame())
rates2 = np.column_stack((np.exp(res_glm.params),
res_glm.bse * np.exp(res_glm.params),
np.exp(res_glm.conf_int())))
assert_allclose(rates.summary_frame().values, rates2, rtol=1e-13)
from statsmodels.genmod.families import links
# with identity transform
pt = params_transform_univariate(res_glm.params, res_glm.cov_params(), link=links.identity())
print(pt.tvalues)
assert_allclose(pt.tvalues, res_glm.tvalues, rtol=1e-13)
assert_allclose(pt.se_mean, res_glm.bse, rtol=1e-13)
ptt = pt.t_test()
assert_allclose(ptt[0], res_glm.tvalues, rtol=1e-13)
assert_allclose(ptt[1], res_glm.pvalues, rtol=1e-13)
res_glm = mod_glm.fit()
pred_glm = res_glm.get_prediction()
print(pred_glm.summary_frame().head())
res_glm_t = mod_glm.fit(use_t=True)
pred_glm_t = res_glm_t.get_prediction()
print(pred_glm_t.summary_frame().head())
rates = params_transform_univariate(res_glm.params, res_glm.cov_params())
print('\nRates exp(params)')
print(rates.summary_frame())
rates2 = np.column_stack(
(np.exp(res_glm.params), res_glm.bse * np.exp(res_glm.params),
np.exp(res_glm.conf_int())))
assert_allclose(rates.summary_frame().values, rates2, rtol=1e-13)
from statsmodels.genmod.families import links
# with identity transform
pt = params_transform_univariate(res_glm.params,
res_glm.cov_params(),
link=links.identity())
print(pt.tvalues)
assert_allclose(pt.tvalues, res_glm.tvalues, rtol=1e-13)
assert_allclose(pt.se_mean, res_glm.bse, rtol=1e-13)
ptt = pt.t_test()
assert_allclose(ptt[0], res_glm.tvalues, rtol=1e-13)
assert_allclose(ptt[1], res_glm.pvalues, rtol=1e-13)
