def test_scoretest(self):
# Regression tests
np.random.seed(6432)
n = 200 # Must be divisible by 4
exog = np.random.normal(size=(n, 4))
endog = exog[:, 0] + exog[:, 1] + exog[:, 2]
endog += 3*np.random.normal(size=n)
group = np.kron(np.arange(n/4), np.ones(4))
# Test under the null.
L = np.array([[1., -1, 0, 0]])
R = np.array([0.,])
family = Gaussian()
va = Independence()
mod1 = GEE(endog, exog, group, family=family,
cov_struct=va, constraint=(L, R))
rslt1 = mod1.fit()
assert_almost_equal(mod1.score_test_results["statistic"],
1.08126334)
assert_almost_equal(mod1.score_test_results["p-value"],
0.2984151086)
# Test under the alternative.
L = np.array([[1., -1, 0, 0]])
R = np.array([1.0,])
family = Gaussian()
va = Independence()
mod2 = GEE(endog, exog, group, family=family,
cov_struct=va, constraint=(L, R))
rslt2 = mod2.fit()
assert_almost_equal(mod2.score_test_results["statistic"],
3.491110965)
assert_almost_equal(mod2.score_test_results["p-value"],
0.0616991659)
# Compare to Wald tests
exog = np.random.normal(size=(n, 2))
L = np.array([[1, -1]])
R = np.array([0.])
f = np.r_[1, -1]
for i in range(10):
endog = exog[:, 0] + (0.5 + i/10.)*exog[:, 1] +\
np.random.normal(size=n)
family = Gaussian()
va = Independence()
mod0 = GEE(endog, exog, group, family=family,
cov_struct=va)
rslt0 = mod0.fit()
family = Gaussian()
va = Independence()
mod1 = GEE(endog, exog, group, family=family,
cov_struct=va, constraint=(L, R))
rslt1 = mod1.fit()
se = np.sqrt(np.dot(f, np.dot(rslt0.cov_params(), f)))
wald_z = np.dot(f, rslt0.params) / se
wald_p = 2*norm.cdf(-np.abs(wald_z))
score_p = mod1.score_test_results["p-value"]
assert_array_less(np.abs(wald_p - score_p), 0.02)
def setup_class(cls):
endog, exog, group_n = load_data("gee_poisson_1.csv")
family = Poisson()
vi = Independence()
# Test with formulas
D = np.concatenate((endog[:, None], group_n[:, None], exog[:, 1:]),
axis=1)
D = pd.DataFrame(D)
D.columns = [
"Y",
"Id",
] + ["X%d" % (k + 1) for k in range(exog.shape[1] - 1)]
cls.mod = GEE.from_formula("Y ~ X1 + X2 + X3 + X4 + X5",
"Id",
D,
family=family,
cov_struct=vi)
cls.start_params = np.array([
-0.03644504, -0.05432094, 0.01566427, 0.57628591, -0.0046566,
-0.47709315
])
def test_nested_linear(self):
family = Gaussian()
endog, exog, group = load_data("gee_nested_linear_1.csv")
group_n = []
for i in range(endog.shape[0] // 10):
group_n.extend([
0,
] * 5)
group_n.extend([
1,
] * 5)
group_n = np.array(group_n)[:, None]
dp = Independence()
md = GEE(endog, exog, group, None, family, dp)
mdf1 = md.fit()
# From statsmodels.GEE (not an independent test)
cf = np.r_[-0.1671073, 1.00467426, -2.01723004, 0.97297106]
se = np.r_[0.08629606, 0.04058653, 0.04067038, 0.03777989]
assert_almost_equal(mdf1.params, cf, decimal=6)
assert_almost_equal(mdf1.standard_errors(), se, decimal=6)
ne = Nested()
md = GEE(endog, exog, group, None, family, ne, dep_data=group_n)
mdf2 = md.fit(start_params=mdf1.params)
# From statsmodels.GEE (not an independent test)
cf = np.r_[-0.16655319, 1.02183688, -2.00858719, 1.00101969]
se = np.r_[0.08632616, 0.02913582, 0.03114428, 0.02893991]
assert_almost_equal(mdf2.params, cf, decimal=6)
assert_almost_equal(mdf2.standard_errors(), se, decimal=6)
def test_compare_poisson(self):
vs = Independence()
family = Poisson()
Y = np.ceil(-np.log(np.random.uniform(size=100)))
X1 = np.random.normal(size=100)
X2 = np.random.normal(size=100)
X3 = np.random.normal(size=100)
groups = np.random.randint(0, 4, size=100)
D = pd.DataFrame({"Y": Y, "X1": X1, "X2": X2, "X3": X3})
mod1 = GEE.from_formula("Y ~ X1 + X2 + X3",
groups,
D,
family=family,
cov_struct=vs)
rslt1 = mod1.fit()
mod2 = sm.poisson("Y ~ X1 + X2 + X3", data=D)
rslt2 = mod2.fit(disp=False)
assert_almost_equal(rslt1.params.values,
rslt2.params.values,
decimal=10)
def test_nominal(self):
family = Multinomial(3)
endog, exog, groups = load_data("gee_nominal_1.csv", icept=False)
# Test with independence correlation
va = Independence()
mod1 = NominalGEE(endog, exog, groups, None, family, va)
rslt1 = mod1.fit()
# Regression test
cf1 = np.r_[0.44944752, 0.45569985, -0.92007064, -0.46766728]
se1 = np.r_[0.09801821, 0.07718842, 0.13229421, 0.08544553]
assert_almost_equal(rslt1.params, cf1, decimal=5)
assert_almost_equal(rslt1.standard_errors(), se1, decimal=5)
# Test with global odds ratio dependence
va = GlobalOddsRatio("nominal")
mod2 = NominalGEE(endog, exog, groups, None, family, va)
rslt2 = mod2.fit(start_params=rslt1.params)
# Regression test
cf2 = np.r_[0.45448248, 0.41945568, -0.92008924, -0.50485758]
se2 = np.r_[0.09632274, 0.07433944, 0.13264646, 0.0911768]
assert_almost_equal(rslt2.params, cf2, decimal=5)
assert_almost_equal(rslt2.standard_errors(), se2, decimal=5)
# Make sure we get the correct results type
assert_equal(type(rslt1), NominalGEEResultsWrapper)
assert_equal(type(rslt1._results), NominalGEEResults)
def test_compare_OLS(self):
#Gaussian GEE with independence correlation should agree
#exactly with OLS for parameter estimates and standard errors
#derived from the naive covariance estimate.
vs = Independence()
family = Gaussian()
Y = np.random.normal(size=100)
X1 = np.random.normal(size=100)
X2 = np.random.normal(size=100)
X3 = np.random.normal(size=100)
groups = np.kron(lrange(20), np.ones(5))
D = pd.DataFrame({"Y": Y, "X1": X1, "X2": X2, "X3": X3})
md = GEE.from_formula("Y ~ X1 + X2 + X3", groups, D,
family=family, cov_struct=vs)
mdf = md.fit()
ols = smf.ols("Y ~ X1 + X2 + X3", data=D).fit()
# don't use wrapper, asserts_xxx don't work
ols = ols._results
assert_almost_equal(ols.params, mdf.params, decimal=10)
se = mdf.standard_errors(cov_type="naive")
assert_almost_equal(ols.bse, se, decimal=10)
naive_tvalues = mdf.params / \
np.sqrt(np.diag(mdf.cov_naive))
assert_almost_equal(naive_tvalues, ols.tvalues, decimal=10)
def test_nominal(self):
endog, exog, groups = load_data("gee_nominal_1.csv",
icept=False)
# Test with independence correlation
va = Independence()
mod1 = NominalGEE(endog, exog, groups, cov_struct=va)
rslt1 = mod1.fit()
# Regression test
cf1 = np.r_[0.450009, 0.451959, -0.918825, -0.468266]
se1 = np.r_[0.08915936, 0.07005046, 0.12198139, 0.08281258]
assert_allclose(rslt1.params, cf1, rtol=1e-5, atol=1e-5)
assert_allclose(rslt1.standard_errors(), se1, rtol=1e-5, atol=1e-5)
# Test with global odds ratio dependence
va = GlobalOddsRatio("nominal")
mod2 = NominalGEE(endog, exog, groups, cov_struct=va)
rslt2 = mod2.fit(start_params=rslt1.params)
# Regression test
cf2 = np.r_[0.455365, 0.415334, -0.916589, -0.502116]
se2 = np.r_[0.08803614, 0.06628179, 0.12259726, 0.08411064]
assert_allclose(rslt2.params, cf2, rtol=1e-5, atol=1e-5)
assert_allclose(rslt2.standard_errors(), se2, rtol=1e-5, atol=1e-5)
# Make sure we get the correct results type
assert_equal(type(rslt1), NominalGEEResultsWrapper)
assert_equal(type(rslt1._results), NominalGEEResults)
def test_poisson_epil(self):
cur_dir = os.path.dirname(os.path.abspath(__file__))
fname = os.path.join(cur_dir, "results", "epil.csv")
data = pd.read_csv(fname)
fam = Poisson()
ind = Independence()
mod1 = GEE.from_formula("y ~ age + trt + base",
data["subject"],
data,
cov_struct=ind,
family=fam)
rslt1 = mod1.fit()
# Coefficients should agree with GLM
from statsmodels.genmod.generalized_linear_model import GLM
from statsmodels.genmod import families
mod2 = GLM.from_formula("y ~ age + trt + base",
data,
family=families.Poisson())
rslt2 = mod2.fit(scale="X2")
# don't use wrapper, asserts_xxx don't work
rslt1 = rslt1._results
rslt2 = rslt2._results
assert_almost_equal(rslt1.params, rslt2.params, decimal=6)
assert_almost_equal(rslt1.scale, rslt2.scale, decimal=6)
def gendat_overdispersed():
exs = Overdispersed_simulator()
exs.params = np.r_[2., 0.2, 0.2, -0.1, -0.2]
exs.ngroups = 200
exs.scale_inv = 2.
exs.dparams = []
exs.simulate()
return exs, Independence()
def BuildPoissonModels(hist_data, feature_list, comp_data=None):
''' Build score predictions via (linear) poisson regression. '''
hist_data_1 = hist_data[["team_1_score"] + feature_list]
hist_data_2 = hist_data[["team_2_score"] + feature_list]
formula_1 = "team_1_score ~ " + " + ".join(feature_list)
formula_2 = "team_2_score ~ " + " + ".join(feature_list)
# using the GEE package along with independance assumptions to fit poisson model.
# Am assuming this is using a maximum likleyhood approach?
fam = Poisson()
ind = Independence()
model_1 = GEE.from_formula(formula_1,
"team_1_score",
hist_data,
cov_struct=ind,
family=fam)
model_2 = GEE.from_formula(formula_2,
"team_2_score",
hist_data,
cov_struct=ind,
family=fam)
model_1_fit = model_1.fit()
model_2_fit = model_2.fit()
print(model_1_fit.summary())
hist_data['team_1_score_pred'] = model_1_fit.predict(hist_data)
hist_data['team_2_score_pred'] = model_2_fit.predict(hist_data)
# return historical data if comp_data wasn't passed.
if comp_data is None:
return hist_data
# prepare comp data
comp_data['team_1_score_pred'] = model_1_fit.predict(
comp_data[feature_list])
comp_data['team_2_score_pred'] = model_2_fit.predict(
comp_data[feature_list])
comp_data['team_1_prob'] = comp_data[[
'team_1_score_pred', 'team_2_score_pred'
]].apply(
lambda x: 1 - skellam.cdf(0, x['team_1_score_pred'], x[
'team_2_score_pred']), 1)
comp_data['team_tie_prob'] = comp_data[[
'team_1_score_pred', 'team_2_score_pred'
]].apply(
lambda x: skellam.pmf(0, x['team_1_score_pred'], x['team_2_score_pred']
), 1)
comp_data['team_2_prob'] = comp_data[[
'team_1_score_pred', 'team_2_score_pred'
]].apply(
lambda x: skellam.cdf(-1, x['team_1_score_pred'], x['team_2_score_pred'
]), 1)
return hist_data, comp_data
def setup_class(cls):
endog, exog, groups = load_data("gee_nominal_1.csv", icept=False)
# Test with independence correlation
va = Independence()
cls.mod = NominalGEE(endog, exog, groups, cov_struct=va)
cls.start_params = np.array(
[0.44944752, 0.45569985, -0.92007064, -0.46766728])
def test_wrapper(self):
endog, exog, groups = load_data("gee_nominal_1.csv", icept=False)
endog = pd.Series(endog, name='yendog')
exog = pd.DataFrame(exog)
groups = pd.Series(groups, name='the_group')
va = Independence()
mod = NominalGEE(endog, exog, groups, cov_struct=va)
rslt2 = mod.fit()
check_wrapper(rslt2)
def setup_class(cls):
endog, exog, group_n = load_data("gee_poisson_1.csv")
family = Poisson()
vi = Independence()
cls.mod = GEE(endog, exog, group_n, None, family, vi)
cls.start_params = np.array([-0.03644504, -0.05432094, 0.01566427,
0.57628591, -0.0046566, -0.47709315])
def test_wrapper(self):
endog, exog, group_n = load_data("gee_poisson_1.csv", icept=False)
endog = pd.Series(endog)
exog = pd.DataFrame(exog)
group_n = pd.Series(group_n)
family = Poisson()
vi = Independence()
mod = GEE(endog, exog, group_n, None, family, vi)
rslt2 = mod.fit()
check_wrapper(rslt2)
def test_linear_constrained(self):
family = Gaussian()
exog = np.random.normal(size=(300, 4))
exog[:, 0] = 1
endog = np.dot(exog, np.r_[1, 1, 0, 0.2]) +\
np.random.normal(size=300)
group = np.kron(np.arange(100), np.r_[1, 1, 1])
vi = Independence()
ve = Exchangeable()
L = np.r_[[[0, 0, 0, 1]]]
R = np.r_[0, ]
for j, v in enumerate((vi, ve)):
md = GEE(endog, exog, group, None, family, v, constraint=(L, R))
mdf = md.fit()
assert_almost_equal(mdf.params[3], 0, decimal=10)
def setup_class(cls):
vs = Independence()
family = families.Gaussian()
np.random.seed(987126)
Y = np.random.normal(size=100)
X1 = np.random.normal(size=100)
X2 = np.random.normal(size=100)
X3 = np.random.normal(size=100)
groups = np.kron(np.arange(20), np.ones(5))
D = pd.DataFrame({"Y": Y, "X1": X1, "X2": X2, "X3": X3})
md = GEE.from_formula("Y ~ X1 + X2 + X3",
groups,
D,
family=family,
cov_struct=vs)
cls.result1 = md.fit()
cls.result2 = GLM.from_formula("Y ~ X1 + X2 + X3", data=D).fit()
def setup_class(cls):
vs = Independence()
family = families.Poisson()
np.random.seed(987126)
Y = np.exp(1 + np.random.normal(size=100))
X1 = np.random.normal(size=100)
X2 = np.random.normal(size=100)
X3 = np.random.normal(size=100)
groups = np.random.randint(0, 4, size=100)
D = pd.DataFrame({"Y": Y, "X1": X1, "X2": X2, "X3": X3})
mod1 = GEE.from_formula("Y ~ X1 + X2 + X3",
groups,
D,
family=family,
cov_struct=vs)
cls.result1 = mod1.fit()
mod2 = GLM.from_formula("Y ~ X1 + X2 + X3", data=D, family=family)
cls.result2 = mod2.fit(disp=False)
def setup_class(cls):
# adjusted for Gamma, not in test_gee.py
vs = Independence()
family = families.Gamma(link=links.log)
np.random.seed(987126)
#Y = np.random.normal(size=100)**2
Y = np.exp(0.1 + np.random.normal(size=100)) # log-normal
X1 = np.random.normal(size=100)
X2 = np.random.normal(size=100)
X3 = np.random.normal(size=100)
groups = np.random.randint(0, 4, size=100)
D = pd.DataFrame({"Y": Y, "X1": X1, "X2": X2, "X3": X3})
mod1 = GEE.from_formula("Y ~ X1 + X2 + X3",
groups,
D,
family=family,
cov_struct=vs)
cls.result1 = mod1.fit()
mod2 = GLM.from_formula("Y ~ X1 + X2 + X3", data=D, family=family)
cls.result2 = mod2.fit(disp=False)
def test_logistic(self):
"""
R code for comparing results:
library(gee)
Z = read.csv("results/gee_logistic_1.csv", header=FALSE)
Y = Z[,2]
Id = Z[,1]
X1 = Z[,3]
X2 = Z[,4]
X3 = Z[,5]
mi = gee(Y ~ X1 + X2 + X3, id=Id, family=binomial,
corstr="independence")
smi = summary(mi)
u = coefficients(smi)
cfi = paste(u[,1], collapse=",")
sei = paste(u[,4], collapse=",")
me = gee(Y ~ X1 + X2 + X3, id=Id, family=binomial,
corstr="exchangeable")
sme = summary(me)
u = coefficients(sme)
cfe = paste(u[,1], collapse=",")
see = paste(u[,4], collapse=",")
ma = gee(Y ~ X1 + X2 + X3, id=Id, family=binomial,
corstr="AR-M")
sma = summary(ma)
u = coefficients(sma)
cfa = paste(u[,1], collapse=",")
sea = paste(u[,4], collapse=",")
sprintf("cf = [[%s],[%s],[%s]]", cfi, cfe, cfa)
sprintf("se = [[%s],[%s],[%s]]", sei, see, sea)
"""
endog, exog, group = load_data("gee_logistic_1.csv")
# Time values for the autoregressive model
T = np.zeros(len(endog))
idx = set(group)
for ii in idx:
jj = np.flatnonzero(group == ii)
T[jj] = lrange(len(jj))
family = Binomial()
ve = Exchangeable()
vi = Independence()
va = Autoregressive()
# From R gee
cf = [[
0.0167272965285882, 1.13038654425893, -1.86896345082962,
1.09397608331333
],
[
0.0178982283915449, 1.13118798191788, -1.86133518416017,
1.08944256230299
],
[
0.0109621937947958, 1.13226505028438, -1.88278757333046,
1.09954623769449
]]
se = [[
0.127291720283049, 0.166725808326067, 0.192430061340865,
0.173141068839597
],
[
0.127045031730155, 0.165470678232842, 0.192052750030501,
0.173174779369249
],
[
0.127240302296444, 0.170554083928117, 0.191045527104503,
0.169776150974586
]]
for j, v in enumerate((vi, ve, va)):
md = GEE(endog, exog, group, T, family, v)
mdf = md.fit()
if id(v) != id(va):
assert_almost_equal(mdf.params, cf[j], decimal=6)
assert_almost_equal(mdf.standard_errors(), se[j], decimal=6)
# Test with formulas
D = np.concatenate((endog[:, None], group[:, None], exog[:, 1:]),
axis=1)
D = pd.DataFrame(D)
D.columns = [
"Y",
"Id",
] + ["X%d" % (k + 1) for k in range(exog.shape[1] - 1)]
for j, v in enumerate((vi, ve)):
md = GEE.from_formula("Y ~ X1 + X2 + X3",
"Id",
D,
family=family,
cov_struct=v)
mdf = md.fit()
assert_almost_equal(mdf.params, cf[j], decimal=6)
assert_almost_equal(mdf.standard_errors(), se[j], decimal=6)
def run_permutation_test(dependent, network, number_of_permutations,
output_path):
nodes = pd.DataFrame.from_dict(dict(network.nodes(data=True)),
orient='index')
degree = pd.DataFrame.from_dict(dict(network.degree()), orient='index')
centrality = pd.DataFrame.from_dict(dict(
nx.betweenness_centrality(network)),
orient='index')
h1 = pd.concat([nodes, degree, centrality], axis=1).reset_index(0)
h1.columns = [
'ID', 'Age', 'Species', 'type', 'Location', 'Sex', 'degree',
'centrality'
]
h1['degree_dist'] = h1.degree / float(h1.degree.max())
equation = dependent + "~ Age + Sex"
from statsmodels.genmod.generalized_estimating_equations import GEE
from statsmodels.genmod.cov_struct import (Exchangeable, Independence,
Autoregressive)
from statsmodels.genmod.families import Poisson
fam = Poisson()
ind = Independence()
model = GEE.from_formula(equation,
"Location",
h1,
cov_struct=ind,
family=fam)
main_model_result = model.fit()
main_result = pd.DataFrame(main_model_result.params).T
degree_random_coeff = []
for i in range(number_of_permutations):
rand_h1 = h1.copy()
rand_h1[dependent] = np.random.permutation(h1[dependent])
fam = Poisson()
ind = Independence()
model = GEE.from_formula(equation,
"Location",
rand_h1,
cov_struct=ind,
family=fam)
result = model.fit()
degree_random_coeff.append(result.params)
d = pd.DataFrame.from_records(degree_random_coeff)
import seaborn as sns
f, (ax1, ax2, ax3) = plt.subplots(1, 3, sharey=True)
ax1.hist(d['Age[T.HY]'], bins=100)
ax1.axvline(x=main_result['Age[T.HY]'].values[0], color='#fc9272')
p = (d['Age[T.HY]'] > main_result['Age[T.HY]'].values[0]
).sum() / float(number_of_permutations)
if p > 0.5:
p = 1 - p
else:
p = p
ax1.set_xlabel(
'Coefficient Age: Hatch Year\n(ref: After Hatch Year)\np= ' +
'{0:.2f}'.format(p))
ax1.set_ylabel('Frequency')
ax2.hist(d['Age[T.UNK]'], bins=100)
ax2.axvline(x=main_result['Age[T.UNK]'].values[0], color='#fc9272')
p = (d['Age[T.UNK]'] > main_result['Age[T.UNK]'].values[0]
).sum() / float(number_of_permutations)
if p > 0.5:
p = 1 - p
else:
p = p
ax2.set_xlabel('Coefficient Age: Unknown\n(ref: After Hatch Year)\np= ' +
'{0:.2f}'.format(p))
ax3.hist(d['Sex[T.M]'], bins=100)
ax3.axvline(x=main_result['Sex[T.M]'].values[0], color='#fc9272')
p = (d['Sex[T.M]'] > main_result['Sex[T.M]'].values[0]
).sum() / float(number_of_permutations)
if p > 0.5:
p = 1 - p
else:
p = p
ax3.set_xlabel('Coefficient Sex: Male\n (ref: Female)\np= ' +
'{0:.2f}'.format(p))
title = 'permutation test for ' + dependent
f.suptitle(title)
plt.tight_layout()
plt.savefig(output_path + '/' + dependent + '_Permutation_test.png',
dpi=300)
plt.show()
# Loop over data generating models
for gendat in gendats:
pvalues = []
params = []
std_errors = []
dparams = []
for j in range(nrep):
da, va = gendat()
ga = Poisson()
# Poisson seems to be more sensitive to starting values,
# so we run the independence model first.
md = GEE(da.endog, da.exog, da.group, da.time, ga, Independence())
mdf = md.fit()
md = GEE(da.endog, da.exog, da.group, da.time, ga, va)
mdf = md.fit(start_params=mdf.params)
if mdf is None or (not mdf.converged):
print("Failed to converge")
continue
scale_inv = 1. / md.estimate_scale()
dparams.append(np.r_[va.dparams, scale_inv])
params.append(np.asarray(mdf.params))
std_errors.append(np.asarray(mdf.standard_errors))
da, va = gendat()
ga = Poisson()
for gendat in gendats:
pvalues = []
params = []
std_errors = []
dparams = []
for j in range(nrep):
da, va = gendat()
ga = Poisson()
# Poisson seems to be more sensitive to starting values,
# so we run the independence model first.
md = GEE(da.endog, da.exog, da.group, da.time, ga,
Independence())
mdf = md.fit()
md = GEE(da.endog, da.exog, da.group, da.time, ga, va)
mdf = md.fit(start_params = mdf.params)
if mdf is None or (not mdf.converged):
print("Failed to converge")
continue
scale_inv = 1. / md.estimate_scale()
dparams.append(np.r_[va.dparams, scale_inv])
params.append(np.asarray(mdf.params))
std_errors.append(np.asarray(mdf.standard_errors))
da,va = gendat()
ga = Poisson()
def test_poisson(self):
"""
library(gee)
Z = read.csv("results/gee_poisson_1.csv", header=FALSE)
Y = Z[,2]
Id = Z[,1]
X1 = Z[,3]
X2 = Z[,4]
X3 = Z[,5]
X4 = Z[,6]
X5 = Z[,7]
mi = gee(Y ~ X1 + X2 + X3 + X4 + X5, id=Id, family=poisson,
corstr="independence", scale.fix=TRUE)
smi = summary(mi)
u = coefficients(smi)
cfi = paste(u[,1], collapse=",")
sei = paste(u[,4], collapse=",")
me = gee(Y ~ X1 + X2 + X3 + X4 + X5, id=Id, family=poisson,
corstr="exchangeable", scale.fix=TRUE)
sme = summary(me)
u = coefficients(sme)
cfe = paste(u[,1], collapse=",")
see = paste(u[,4], collapse=",")
sprintf("cf = [[%s],[%s]]", cfi, cfe)
sprintf("se = [[%s],[%s]]", sei, see)
"""
family = Poisson()
endog, exog, group_n = load_data("gee_poisson_1.csv")
vi = Independence()
ve = Exchangeable()
# From R gee
cf = [[
-0.0364450410793481, -0.0543209391301178, 0.0156642711741052,
0.57628591338724, -0.00465659951186211, -0.477093153099256
],
[
-0.0315615554826533, -0.0562589480840004, 0.0178419412298561,
0.571512795340481, -0.00363255566297332, -0.475971696727736
]]
se = [[
0.0611309237214186, 0.0390680524493108, 0.0334234174505518,
0.0366860768962715, 0.0304758505008105, 0.0316348058881079
],
[
0.0610840153582275, 0.0376887268649102, 0.0325168379415177,
0.0369786751362213, 0.0296141014225009, 0.0306115470200955
]]
for j, v in enumerate((vi, ve)):
md = GEE(endog, exog, group_n, None, family, v)
mdf = md.fit()
assert_almost_equal(mdf.params, cf[j], decimal=5)
assert_almost_equal(mdf.standard_errors(), se[j], decimal=6)
# Test with formulas
D = np.concatenate((endog[:, None], group_n[:, None], exog[:, 1:]),
axis=1)
D = pd.DataFrame(D)
D.columns = [
"Y",
"Id",
] + ["X%d" % (k + 1) for k in range(exog.shape[1] - 1)]
for j, v in enumerate((vi, ve)):
md = GEE.from_formula("Y ~ X1 + X2 + X3 + X4 + X5",
"Id",
D,
family=family,
cov_struct=v)
mdf = md.fit()
assert_almost_equal(mdf.params, cf[j], decimal=5)
assert_almost_equal(mdf.standard_errors(), se[j], decimal=6)
# -*- coding: utf-8 -*-
"""
Created on Fri Aug 12 11:36:51 2016
@author: emg
"""
import numpy as np
import pandas as pd
from statsmodels.genmod.generalized_estimating_equations import GEE
from statsmodels.genmod.cov_struct import (Exchangeable, Independence,
Autoregressive)
from statsmodels.genmod.families import Poisson
fam = Poisson()
ind = Independence()
model1 = GEE.from_formula("author_count ~ top + mod",
"author",
authors,
cov_struct=ind,
family=fam)
result1 = model1.fit()
print(result1.summary())
def test_linear(self):
"""
library(gee)
Z = read.csv("results/gee_linear_1.csv", header=FALSE)
Y = Z[,2]
Id = Z[,1]
X1 = Z[,3]
X2 = Z[,4]
X3 = Z[,5]
mi = gee(Y ~ X1 + X2 + X3, id=Id, family=gaussian,
corstr="independence", tol=1e-8, maxit=100)
smi = summary(mi)
u = coefficients(smi)
cfi = paste(u[,1], collapse=",")
sei = paste(u[,4], collapse=",")
me = gee(Y ~ X1 + X2 + X3, id=Id, family=gaussian,
corstr="exchangeable", tol=1e-8, maxit=100)
sme = summary(me)
u = coefficients(sme)
cfe = paste(u[,1], collapse=",")
see = paste(u[,4], collapse=",")
sprintf("cf = [[%s],[%s]]", cfi, cfe)
sprintf("se = [[%s],[%s]]", sei, see)
"""
family = Gaussian()
endog, exog, group = load_data("gee_linear_1.csv")
vi = Independence()
ve = Exchangeable()
# From R gee
cf = [[
-0.01850226507491, 0.81436304278962, -1.56167635393184,
0.794239361055003
],
[
-0.0182920577154767, 0.814898414022467, -1.56194040106201,
0.793499517527478
]]
se = [[
0.0440733554189401, 0.0479993639119261, 0.0496045952071308,
0.0479467597161284
],
[
0.0440369906460754, 0.0480069787567662, 0.049519758758187,
0.0479760443027526
]]
for j, v in enumerate((vi, ve)):
md = GEE(endog, exog, group, None, family, v)
mdf = md.fit()
assert_almost_equal(mdf.params, cf[j], decimal=10)
assert_almost_equal(mdf.standard_errors(), se[j], decimal=10)
# Test with formulas
D = np.concatenate((endog[:, None], group[:, None], exog[:, 1:]),
axis=1)
D = pd.DataFrame(D)
D.columns = [
"Y",
"Id",
] + ["X%d" % (k + 1) for k in range(exog.shape[1] - 1)]
for j, v in enumerate((vi, ve)):
md = GEE.from_formula("Y ~ X1 + X2 + X3",
"Id",
D,
family=family,
cov_struct=v)
mdf = md.fit()
assert_almost_equal(mdf.params, cf[j], decimal=10)
assert_almost_equal(mdf.standard_errors(), se[j], decimal=10)
