def test_missing(self):
"""
Test missing data handling for calling from the api. Missing
data handling does not currently work for formulas.
"""
endog = np.random.normal(size=100)
exog = np.random.normal(size=(100, 3))
exog[:, 0] = 1
groups = np.kron(lrange(20), np.ones(5))
endog[0] = np.nan
endog[5:7] = np.nan
exog[10:12, 1] = np.nan
mod1 = GEE(endog, exog, groups, missing='drop')
rslt1 = mod1.fit()
assert_almost_equal(len(mod1.endog), 95)
assert_almost_equal(np.asarray(mod1.exog.shape), np.r_[95, 3])
ii = np.isfinite(endog) & np.isfinite(exog).all(1)
mod2 = GEE(endog[ii], exog[ii, :], groups[ii], missing='none')
rslt2 = mod2.fit()
assert_almost_equal(rslt1.params, rslt2.params)
assert_almost_equal(rslt1.bse, rslt2.bse)
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_default_time(self):
"""
Check that the time defaults work correctly.
"""
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()
va = Autoregressive()
md1 = GEE(endog, exog, group, family=family, cov_struct=va)
mdf1 = md1.fit()
md2 = GEE(endog, exog, group, time=T, family=family, cov_struct=va)
mdf2 = md2.fit()
assert_almost_equal(mdf1.params, mdf2.params, decimal=6)
assert_almost_equal(mdf1.standard_errors(),
mdf2.standard_errors(),
decimal=6)
def test_missing(self):
#Test missing data handling for calling from the api. Missing
#data handling does not currently work for formulas.
endog = np.random.normal(size=100)
exog = np.random.normal(size=(100, 3))
exog[:, 0] = 1
groups = np.kron(lrange(20), np.ones(5))
endog[0] = np.nan
endog[5:7] = np.nan
exog[10:12, 1] = np.nan
mod1 = GEE(endog, exog, groups, missing='drop')
rslt1 = mod1.fit()
assert_almost_equal(len(mod1.endog), 95)
assert_almost_equal(np.asarray(mod1.exog.shape), np.r_[95, 3])
ii = np.isfinite(endog) & np.isfinite(exog).all(1)
mod2 = GEE(endog[ii], exog[ii, :], groups[ii], missing='none')
rslt2 = mod2.fit()
assert_almost_equal(rslt1.params, rslt2.params)
assert_almost_equal(rslt1.bse, rslt2.bse)
def test_nominal(self):
family = Multinomial(3)
endog, exog, groups = load_data("gee_nominal_1.csv",
icept=False)
# Test with independence correlation
v = Independence()
md = GEE(endog, exog, groups, None, family, v)
md.setup_nominal()
mdf1 = md.fit()
# From statsmodels.GEE (not an independent 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(mdf1.params, cf1, decimal=5)
assert_almost_equal(mdf1.standard_errors(), se1, decimal=5)
# Test with global odds ratio dependence
v = GlobalOddsRatio("nominal")
md = GEE(endog, exog, groups, None, family, v)
md.setup_nominal()
mdf2 = md.fit(start_params=mdf1.params)
# From statsmodels.GEE (not an independent test)
cf2 = np.r_[0.45397549, 0.42278345, -0.91997131, -0.50115943]
se2 = np.r_[0.09646057, 0.07405713, 0.1324629 , 0.09025019]
assert_almost_equal(mdf2.params, cf2, decimal=5)
assert_almost_equal(mdf2.standard_errors(), se2, decimal=5)
def test_nominal(self):
family = Multinomial(3)
endog, exog, groups = load_data("gee_nominal_1.csv", icept=False)
# Test with independence correlation
v = Independence()
md = GEE(endog, exog, groups, None, family, v)
md.setup_nominal()
mdf1 = md.fit()
# From statsmodels.GEE (not an independent 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(mdf1.params, cf1, decimal=5)
assert_almost_equal(mdf1.standard_errors(), se1, decimal=5)
# Test with global odds ratio dependence
v = GlobalOddsRatio("nominal")
md = GEE(endog, exog, groups, None, family, v)
md.setup_nominal()
mdf2 = md.fit(start_params=mdf1.params)
# From statsmodels.GEE (not an independent test)
cf2 = np.r_[0.45397549, 0.42278345, -0.91997131, -0.50115943]
se2 = np.r_[0.09646057, 0.07405713, 0.1324629, 0.09025019]
assert_almost_equal(mdf2.params, cf2, decimal=5)
assert_almost_equal(mdf2.standard_errors(), se2, decimal=5)
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_default_time(self):
# Check that the time defaults work correctly.
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()
va = Autoregressive()
md1 = GEE(endog, exog, group, family=family, cov_struct=va)
mdf1 = md1.fit()
md2 = GEE(endog, exog, group, time=T, family=family,
cov_struct=va)
mdf2 = md2.fit()
assert_almost_equal(mdf1.params, mdf2.params, decimal=6)
assert_almost_equal(mdf1.standard_errors(),
mdf2.standard_errors(), decimal=6)
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 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 test_ordinal(self):
family = Binomial()
endog_orig, exog_orig, groups = load_data("gee_ordinal_1.csv",
icept=False)
data = np.concatenate((endog_orig[:,None], exog_orig,
groups[:,None]), axis=1)
# Recode as cumulative indicators
endog, exog, intercepts, nlevel = gee_setup_ordinal(data, 0)
exog1 = np.concatenate((intercepts, exog), axis=1)
groups = exog1[:,-1]
exog1 = exog1[:,0:-1]
v = GlobalOddsRatio(nlevel, "ordinal")
beta = gee_ordinal_starting_values(endog_orig,
exog_orig.shape[1])
md = GEE(endog, exog1, groups, None, family, v)
mdf = md.fit(start_params = beta)
cf = np.r_[1.09238131, 0.02148193, -0.39879146, -0.01855666,
0.02983409, 1.18123172, 0.01845318, -1.10233886]
se = np.r_[0.10878752, 0.10326078, 0.11171241, 0.05488705,
0.05995019, 0.0916574, 0.05951445, 0.08539281]
assert_almost_equal(mdf.params, cf, decimal=5)
assert_almost_equal(mdf.bse, se, decimal=5)
def test_ordinal_pandas(self):
family = Binomial()
endog_orig, exog_orig, groups = load_data("gee_ordinal_1.csv",
icept=False)
data = np.concatenate(
(endog_orig[:, None], exog_orig, groups[:, None]), axis=1)
data = pd.DataFrame(data)
data.columns = ["endog", "x1", "x2", "x3", "x4", "x5", "group"]
# Recode as cumulative indicators
endog, exog, intercepts, nlevel = \
gee_setup_ordinal(data, "endog")
exog1 = np.concatenate((intercepts, exog), axis=1)
groups = exog1[:, -1]
exog1 = exog1[:, 0:-1]
v = GlobalOddsRatio(nlevel, "ordinal")
beta = gee_ordinal_starting_values(endog_orig, exog_orig.shape[1])
md = GEE(endog, exog1, groups, None, family, v)
mdf = md.fit(start_params=beta)
cf = np.r_[1.09238131, 0.02148193, -0.39879146, -0.01855666,
0.02983409, 1.18123172, 0.01845318, -1.10233886]
se = np.r_[0.10878752, 0.10326078, 0.11171241, 0.05488705, 0.05995019,
0.0916574, 0.05951445, 0.08539281]
assert_almost_equal(mdf.params, cf, decimal=2)
assert_almost_equal(mdf.bse, se, decimal=2)
def test_formulas(self):
"""
Check formulas, especially passing groups and time as either
variable names or arrays.
"""
n = 100
Y = np.random.normal(size=n)
X1 = np.random.normal(size=n)
mat = np.concatenate((np.ones((n, 1)), X1[:, None]), axis=1)
Time = np.random.uniform(size=n)
groups = np.kron(lrange(20), np.ones(5))
data = pd.DataFrame({"Y": Y, "X1": X1, "Time": Time, "groups": groups})
va = Autoregressive()
family = Gaussian()
mod1 = GEE(Y, mat, groups, time=Time, family=family, cov_struct=va)
rslt1 = mod1.fit()
mod2 = GEE.from_formula("Y ~ X1",
groups,
data,
time=Time,
family=family,
cov_struct=va)
rslt2 = mod2.fit()
mod3 = GEE.from_formula("Y ~ X1",
groups,
data,
time="Time",
family=family,
cov_struct=va)
rslt3 = mod3.fit()
mod4 = GEE.from_formula("Y ~ X1",
"groups",
data,
time=Time,
family=family,
cov_struct=va)
rslt4 = mod4.fit()
mod5 = GEE.from_formula("Y ~ X1",
"groups",
data,
time="Time",
family=family,
cov_struct=va)
rslt5 = mod5.fit()
assert_almost_equal(rslt1.params, rslt2.params, decimal=8)
assert_almost_equal(rslt1.params, rslt3.params, decimal=8)
assert_almost_equal(rslt1.params, rslt4.params, decimal=8)
assert_almost_equal(rslt1.params, rslt5.params, decimal=8)
check_wrapper(rslt2)
def test_missing():
# gh-1877
data = [['id', 'al', 'status', 'fake', 'grps'],
['4A', 'A', 1, 1, 0],
['5A', 'A', 1, 2.0, 1],
['6A', 'A', 1, 3, 2],
['7A', 'A', 1, 2.0, 3],
['8A', 'A', 1, 1, 4],
['9A', 'A', 1, 2.0, 5],
['11A', 'A', 1, 1, 6],
['12A', 'A', 1, 2.0, 7],
['13A', 'A', 1, 1, 8],
['14A', 'A', 1, 1, 9],
['15A', 'A', 1, 1, 10],
['16A', 'A', 1, 2.0, 11],
['17A', 'A', 1, 3.0, 12],
['18A', 'A', 1, 3.0, 13],
['19A', 'A', 1, 2.0, 14],
['20A', 'A', 1, 2.0, 15],
['2C', 'C', 0, 3.0, 0],
['3C', 'C', 0, 1, 1],
['4C', 'C', 0, 1, 2],
['5C', 'C', 0, 2.0, 3],
['6C', 'C', 0, 1, 4],
['9C', 'C', 0, 1, 5],
['10C', 'C', 0, 3, 6],
['12C', 'C', 0, 3, 7],
['14C', 'C', 0, 2.5, 8],
['15C', 'C', 0, 1, 9],
['17C', 'C', 0, 1, 10],
['22C', 'C', 0, 1, 11],
['23C', 'C', 0, 1, 12],
['24C', 'C', 0, 1, 13],
['32C', 'C', 0, 2.0, 14],
['35C', 'C', 0, 1, 15]]
df = pd.DataFrame(data[1:], columns=data[0])
df.ix[df.fake == 1, 'fake'] = np.nan
mod = smf.gee('status ~ fake', data=df, groups='grps',
cov_struct=sm.cov_struct.Independence(),
family=sm.families.Binomial())
df = df.dropna()
#df.loc[:, 'constant'] = 1
df['constant'] = 1
mod2 = GEE(df.status, df[['constant', 'fake']], groups=df.grps,
cov_struct=sm.cov_struct.Independence(),
family=sm.families.Binomial())
assert_equal(mod.endog, mod2.endog)
assert_equal(mod.exog, mod2.exog)
assert_equal(mod.groups, mod2.groups)
res = mod.fit()
res2 = mod2.fit()
assert_almost_equal(res.params.values, res2.params.values)
def test_missing():
# gh-1877
data = [['id', 'al', 'status', 'fake', 'grps'],
['4A', 'A', 1, 1, 0],
['5A', 'A', 1, 2.0, 1],
['6A', 'A', 1, 3, 2],
['7A', 'A', 1, 2.0, 3],
['8A', 'A', 1, 1, 4],
['9A', 'A', 1, 2.0, 5],
['11A', 'A', 1, 1, 6],
['12A', 'A', 1, 2.0, 7],
['13A', 'A', 1, 1, 8],
['14A', 'A', 1, 1, 9],
['15A', 'A', 1, 1, 10],
['16A', 'A', 1, 2.0, 11],
['17A', 'A', 1, 3.0, 12],
['18A', 'A', 1, 3.0, 13],
['19A', 'A', 1, 2.0, 14],
['20A', 'A', 1, 2.0, 15],
['2C', 'C', 0, 3.0, 0],
['3C', 'C', 0, 1, 1],
['4C', 'C', 0, 1, 2],
['5C', 'C', 0, 2.0, 3],
['6C', 'C', 0, 1, 4],
['9C', 'C', 0, 1, 5],
['10C', 'C', 0, 3, 6],
['12C', 'C', 0, 3, 7],
['14C', 'C', 0, 2.5, 8],
['15C', 'C', 0, 1, 9],
['17C', 'C', 0, 1, 10],
['22C', 'C', 0, 1, 11],
['23C', 'C', 0, 1, 12],
['24C', 'C', 0, 1, 13],
['32C', 'C', 0, 2.0, 14],
['35C', 'C', 0, 1, 15]]
df = pd.DataFrame(data[1:], columns=data[0])
df.ix[df.fake == 1, 'fake'] = np.nan
mod = smf.gee('status ~ fake', data=df, groups='grps',
cov_struct=sm.cov_struct.Independence(),
family=sm.families.Binomial())
df = df.dropna()
df['constant'] = 1
mod2 = GEE(df.status, df[['constant', 'fake']], groups=df.grps,
cov_struct=sm.cov_struct.Independence(),
family=sm.families.Binomial())
assert_equal(mod.endog, mod2.endog)
assert_equal(mod.exog, mod2.exog)
assert_equal(mod.groups, mod2.groups)
res = mod.fit()
res2 = mod2.fit()
assert_almost_equal(res.params.values, res2.params.values)
def test_weighted(self):
# Simple check where the answer can be computed by hand.
exog = np.ones(20)
weights = np.ones(20)
weights[0:10] = 2
endog = np.zeros(20)
endog[0:10] += 1
groups = np.kron(np.arange(10), np.r_[1, 1])
model = GEE(endog, exog, groups, weights=weights)
result = model.fit()
assert_allclose(result.params, np.r_[2/3.])
# Comparison against stata using groups with different sizes.
weights = np.ones(20)
weights[10:] = 2
endog = np.r_[1, 2, 3, 2, 3, 4, 3, 4, 5, 4, 5, 6, 5, 6, 7, 6,
7, 8, 7, 8]
exog1 = np.r_[1, 1, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3, 4, 4, 4, 4,
3, 3, 3, 3]
groups = np.r_[1, 1, 2, 2, 2, 2, 4, 4, 5, 5, 6, 6, 6, 6,
8, 8, 9, 9, 10, 10]
exog = np.column_stack((np.ones(20), exog1))
# Comparison using independence model
model = GEE(endog, exog, groups, weights=weights,
cov_struct=sm.cov_struct.Independence())
g = np.mean([2, 4, 2, 2, 4, 2, 2, 2])
fac = 20 / float(20 - g)
result = model.fit(ddof_scale=0, scaling_factor=fac)
assert_allclose(result.params, np.r_[1.247573, 1.436893], atol=1e-6)
assert_allclose(result.scale, 1.808576)
# Stata multiples robust SE by sqrt(N / (N - g)), where N is
# the total sample size and g is the average group size.
assert_allclose(result.bse, np.r_[0.895366, 0.3425498], atol=1e-5)
# Comparison using exchangeable model
# Smoke test for now
model = GEE(endog, exog, groups, weights=weights,
cov_struct=sm.cov_struct.Exchangeable())
result = model.fit(ddof_scale=0)
def test_weighted(self):
# Simple check where the answer can be computed by hand.
exog = np.ones(20)
weights = np.ones(20)
weights[0:10] = 2
endog = np.zeros(20)
endog[0:10] += 1
groups = np.kron(np.arange(10), np.r_[1, 1])
model = GEE(endog, exog, groups, weights=weights)
result = model.fit()
assert_allclose(result.params, np.r_[2/3.])
# Comparison against stata using groups with different sizes.
weights = np.ones(20)
weights[10:] = 2
endog = np.r_[1, 2, 3, 2, 3, 4, 3, 4, 5, 4, 5, 6, 5, 6, 7, 6,
7, 8, 7, 8]
exog1 = np.r_[1, 1, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3, 4, 4, 4, 4,
3, 3, 3, 3]
groups = np.r_[1, 1, 2, 2, 2, 2, 4, 4, 5, 5, 6, 6, 6, 6,
8, 8, 9, 9, 10, 10]
exog = np.column_stack((np.ones(20), exog1))
# Comparison using independence model
model = GEE(endog, exog, groups, weights=weights,
cov_struct=sm.cov_struct.Independence())
g = np.mean([2, 4, 2, 2, 4, 2, 2, 2])
fac = 20 / float(20 - g)
result = model.fit(ddof_scale=0, scaling_factor=fac)
assert_allclose(result.params, np.r_[1.247573, 1.436893], atol=1e-6)
assert_allclose(result.scale, 1.808576)
# Stata multiples robust SE by sqrt(N / (N - g)), where N is
# the total sample size and g is the average group size.
assert_allclose(result.bse, np.r_[0.895366, 0.3425498], atol=1e-5)
# Comparison using exchangeable model
# Smoke test for now
model = GEE(endog, exog, groups, weights=weights,
cov_struct=sm.cov_struct.Exchangeable())
result = model.fit(ddof_scale=0)
def test_post_estimation(self):
family = Gaussian()
endog, exog, group = load_data("gee_linear_1.csv")
ve = Exchangeable()
md = GEE(endog, exog, group, None, family, ve)
mdf = md.fit()
assert_almost_equal(np.dot(exog, mdf.params), mdf.fittedvalues)
assert_almost_equal(endog - np.dot(exog, mdf.params), mdf.resid)
def test_post_estimation(self):
family = Gaussian()
endog, exog, group = load_data("gee_linear_1.csv")
ve = Exchangeable()
md = GEE(endog, exog, group, None, family, ve)
mdf = md.fit()
assert_almost_equal(np.dot(exog, mdf.params), mdf.fittedvalues)
assert_almost_equal(endog - np.dot(exog, mdf.params), mdf.resid)
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_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_autoregressive(self):
dep_params_true = [0, 0.589208623896, 0.559823804948]
params_true = [[1.08043787, 1.12709319, 0.90133927],
[0.9613677, 1.05826987, 0.90832055],
[1.05370439, 0.96084864, 0.93923374]]
np.random.seed(342837482)
num_group = 100
ar_param = 0.5
k = 3
ga = Gaussian()
for gsize in 1,2,3:
ix = np.arange(gsize)[:,None] - np.arange(gsize)[None,:]
ix = np.abs(ix)
cmat = ar_param ** ix
cmat_r = np.linalg.cholesky(cmat)
endog = []
exog = []
groups = []
for i in range(num_group):
x = np.random.normal(size=(gsize,k))
exog.append(x)
expval = x.sum(1)
errors = np.dot(cmat_r, np.random.normal(size=gsize))
endog.append(expval + errors)
groups.append(i*np.ones(gsize))
endog = np.concatenate(endog)
groups = np.concatenate(groups)
exog = np.concatenate(exog, axis=0)
ar = Autoregressive()
md = GEE(endog, exog, groups, family=ga, cov_struct = ar)
mdf = md.fit()
assert_almost_equal(ar.dep_params, dep_params_true[gsize-1])
assert_almost_equal(mdf.params, params_true[gsize-1])
def test_autoregressive(self):
dep_params_true = [0, 0.589208623896, 0.559823804948]
params_true = [[1.08043787, 1.12709319, 0.90133927],
[0.9613677, 1.05826987, 0.90832055],
[1.05370439, 0.96084864, 0.93923374]]
np.random.seed(342837482)
num_group = 100
ar_param = 0.5
k = 3
ga = Gaussian()
for gsize in 1, 2, 3:
ix = np.arange(gsize)[:, None] - np.arange(gsize)[None, :]
ix = np.abs(ix)
cmat = ar_param**ix
cmat_r = np.linalg.cholesky(cmat)
endog = []
exog = []
groups = []
for i in range(num_group):
x = np.random.normal(size=(gsize, k))
exog.append(x)
expval = x.sum(1)
errors = np.dot(cmat_r, np.random.normal(size=gsize))
endog.append(expval + errors)
groups.append(i * np.ones(gsize))
endog = np.concatenate(endog)
groups = np.concatenate(groups)
exog = np.concatenate(exog, axis=0)
ar = Autoregressive()
md = GEE(endog, exog, groups, family=ga, cov_struct=ar)
mdf = md.fit()
assert_almost_equal(ar.dep_params, dep_params_true[gsize - 1])
assert_almost_equal(mdf.params, params_true[gsize - 1])
def test_formulas(self):
"""
Check formulas, especially passing groups and time as either
variable names or arrays.
"""
n = 100
Y = np.random.normal(size=n)
X1 = np.random.normal(size=n)
mat = np.concatenate((np.ones((n,1)), X1[:, None]), axis=1)
Time = np.random.uniform(size=n)
groups = np.kron(lrange(20), np.ones(5))
data = pd.DataFrame({"Y": Y, "X1": X1, "Time": Time, "groups": groups})
va = Autoregressive()
family = Gaussian()
mod1 = GEE(Y, mat, groups, time=Time, family=family,
cov_struct=va)
rslt1 = mod1.fit()
mod2 = GEE.from_formula("Y ~ X1", groups, data, time=Time,
family=family, cov_struct=va)
rslt2 = mod2.fit()
mod3 = GEE.from_formula("Y ~ X1", groups, data, time="Time",
family=family, cov_struct=va)
rslt3 = mod3.fit()
mod4 = GEE.from_formula("Y ~ X1", "groups", data, time=Time,
family=family, cov_struct=va)
rslt4 = mod4.fit()
mod5 = GEE.from_formula("Y ~ X1", "groups", data, time="Time",
family=family, cov_struct=va)
rslt5 = mod5.fit()
assert_almost_equal(rslt1.params, rslt2.params, decimal=8)
assert_almost_equal(rslt1.params, rslt3.params, decimal=8)
assert_almost_equal(rslt1.params, rslt4.params, decimal=8)
assert_almost_equal(rslt1.params, rslt5.params, decimal=8)
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 test_ordinal(self):
family = Binomial()
endog, exog, groups = load_data("gee_ordinal_1.csv", icept=False)
v = GlobalOddsRatio("ordinal")
md = GEE(endog, exog, groups, None, family, v)
md.setup_ordinal()
mdf = md.fit()
cf = np.r_[1.09238131, 0.02148193, -0.39879146, -0.01855666,
0.02983409, 1.18123172, 0.01845318, -1.10233886]
se = np.r_[0.10878752, 0.10326078, 0.11171241, 0.05488705, 0.05995019,
0.0916574, 0.05951445, 0.08539281]
assert_almost_equal(mdf.params, cf, decimal=5)
assert_almost_equal(mdf.bse, se, decimal=5)
def test_ordinal(self):
family = Binomial()
endog, exog, groups = load_data("gee_ordinal_1.csv",
icept=False)
v = GlobalOddsRatio("ordinal")
md = GEE(endog, exog, groups, None, family, v)
md.setup_ordinal()
mdf = md.fit()
cf = np.r_[1.09238131, 0.02148193, -0.39879146, -0.01855666,
0.02983409, 1.18123172, 0.01845318, -1.10233886]
se = np.r_[0.10878752, 0.10326078, 0.11171241, 0.05488705,
0.05995019, 0.0916574, 0.05951445, 0.08539281]
assert_almost_equal(mdf.params, cf, decimal=5)
assert_almost_equal(mdf.bse, se, decimal=5)
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 test_margins(self):
n = 300
exog = np.random.normal(size=(n, 4))
exog[:, 0] = 1
exog[:, 1] = 1 * (exog[:, 2] < 0)
group = np.kron(np.arange(n / 4), np.ones(4))
time = np.zeros((n, 1))
beta = np.r_[0, 1, -1, 0.5]
lpr = np.dot(exog, beta)
prob = 1 / (1 + np.exp(-lpr))
endog = 1 * (np.random.uniform(size=n) < prob)
fa = Binomial()
ex = Exchangeable()
md = GEE(endog, exog, group, time, fa, ex)
mdf = md.fit()
marg = GEEMargins(mdf, ())
marg.summary()
def test_margins(self):
n = 300
exog = np.random.normal(size=(n, 4))
exog[:,0] = 1
exog[:,1] = 1*(exog[:,2] < 0)
group = np.kron(np.arange(n/4), np.ones(4))
time = np.zeros((n, 1))
beta = np.r_[0, 1, -1, 0.5]
lpr = np.dot(exog, beta)
prob = 1 / (1 + np.exp(-lpr))
endog = 1*(np.random.uniform(size=n) < prob)
fa = Binomial()
ex = Exchangeable()
md = GEE(endog, exog, group, time, fa, ex)
mdf = md.fit()
marg = GEEMargins(mdf, ())
marg.summary()
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)
from statsmodels.genmod.families import Gaussian, Binomial, Poisson
from statsmodels.genmod.dependence_structures import (Exchangeable,
Independence, GlobalOddsRatio, Autoregressive, Nested)
from statsmodels.genmod.tests import gee_gaussian_simulation_check as gees
da,va = gees.gen_gendat_ar0(0.6)()
ga = Gaussian()
lhs = np.array([[0., 1, 1, 0, 0],])
rhs = np.r_[0.,]
example = []
if 'constraint' in example:
md = GEE(da.endog, da.exog, da.group, da.time, ga, va,
constraint=(lhs, rhs))
mdf = md.fit()
print(mdf.summary())
md2 = GEE(da.endog, da.exog, da.group, da.time, ga, va,
constraint=None)
mdf2 = md2.fit()
print('\n\n')
print(mdf2.summary())
mdf2.use_t = False
mdf2.df_resid = np.diff(mdf2.model.exog.shape)
tt2 = mdf2.t_test(np.eye(len(mdf2.params)))
# need master to get wald_test
#print mdf2.wald_test(np.eye(len(mdf2.params))[1:])
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)
for jg, gendat in enumerate(gendats):
dparams = []
params = []
std_errors = []
pvalues = []
for j in range(nrep):
da, va, mt, constraint = gendat()
beta = da.starting_values(0)
md = GEE(da.endog_ex, da.exog_ex, da.group_ex, None, mt, va)
mdf = md.fit(start_params=beta)
if mdf is None:
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, mt, constraint = gendat()
beta = da.starting_values(constraint[0].shape[0])
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 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",
D,
None,
groups=D.loc[:, "Id"],
family=family,
covstruct=v)
mdf = md.fit()
assert_almost_equal(mdf.params, cf[j], decimal=5)
assert_almost_equal(mdf.standard_errors(), se[j], decimal=6)
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()
# Loop over data generating models
for gendat in gendats:
pvalues = []
params = []
std_errors = []
dparams = []
for j in range(nrep):
da, va = gendat()
ga = Gaussian()
md = GEE(da.endog, da.exog, da.group, da.time, ga, va)
mdf = md.fit()
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 = Gaussian()
md = GEE(da.endog,
da.exog,
da.group,
da.time,
ga,
va,
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",
D,
None,
groups=D.loc[:, "Id"],
family=family,
covstruct=v)
mdf = md.fit()
assert_almost_equal(mdf.params, cf[j], decimal=10)
assert_almost_equal(mdf.standard_errors(), se[j], decimal=10)
from statsmodels.genmod.families import Gaussian, Binomial, Poisson
from statsmodels.genmod.dependence_structures import (Exchangeable,
Independence, GlobalOddsRatio, Autoregressive, Nested)
from statsmodels.genmod.tests import gee_gaussian_simulation_check as gees
da,va = gees.gen_gendat_ar0(0.6)()
ga = Gaussian()
lhs = np.array([[0., 1, 1, 0, 0],])
rhs = np.r_[0.,]
example = []
if 'constraint' in example:
md = GEE(da.endog, da.exog, da.group, da.time, ga, va,
constraint=(lhs, rhs))
mdf = md.fit()
print mdf.summary()
md2 = GEE(da.endog, da.exog, da.group, da.time, ga, va,
constraint=None)
mdf2 = md2.fit()
print '\n\n'
print mdf2.summary()
mdf2.use_t = False
mdf2.df_resid = np.diff(mdf2.model.exog.shape)
tt2 = mdf2.t_test(np.eye(len(mdf2.params)))
# need master to get wald_test
#print mdf2.wald_test(np.eye(len(mdf2.params))[1:])
for jg,gendat in enumerate(gendats):
dparams = []
params = []
std_errors = []
pvalues = []
for j in range(nrep):
da, va, mt, constraint = gendat()
beta = da.starting_values(0)
md = GEE(da.endog_ex, da.exog_ex, da.group_ex, None,
mt, va)
mdf = md.fit(start_params = beta)
if mdf is None:
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, mt, constraint = gendat()
beta = da.starting_values(constraint[0].shape[0])
from statsmodels.genmod.generalized_estimating_equations import GEE, GEEMargins
from statsmodels.genmod.families import Gaussian, Binomial, Poisson
from statsmodels.genmod.dependence_structures import Exchangeable, Independence, GlobalOddsRatio, Autoregressive, Nested
from statsmodels.genmod.tests import gee_gaussian_simulation_check as gees
da, va = gees.gen_gendat_ar0(0.6)()
ga = Gaussian()
lhs = np.array([[0.0, 1, 1, 0, 0]])
rhs = np.r_[0.0,]
example = []
if "constraint" in example:
md = GEE(da.endog, da.exog, da.group, da.time, ga, va, constraint=(lhs, rhs))
mdf = md.fit()
print(mdf.summary())
md2 = GEE(da.endog, da.exog, da.group, da.time, ga, va, constraint=None)
mdf2 = md2.fit()
print("\n\n")
print(mdf2.summary())
mdf2.use_t = False
mdf2.df_resid = np.diff(mdf2.model.exog.shape)
tt2 = mdf2.t_test(np.eye(len(mdf2.params)))
# need master to get wald_test
# print mdf2.wald_test(np.eye(len(mdf2.params))[1:])
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] = range(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",
D,
None,
groups=D.loc[:, "Id"],
family=family,
covstruct=v)
mdf = md.fit()
assert_almost_equal(mdf.params, cf[j], decimal=6)
assert_almost_equal(mdf.standard_errors(), se[j], decimal=6)
# Check for run-time exceptions in summary
print mdf.summary()
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()
# Loop over data generating models
for gendat in gendats:
pvalues = []
params = []
std_errors = []
dep_params = []
for j in range(nrep):
da,va = gendat()
ga = Gaussian()
md = GEE(da.endog, da.exog, da.group, da.time, ga, va)
mdf = md.fit()
scale_inv = 1 / md.estimate_scale()
dep_params.append(np.r_[va.dep_params, scale_inv])
params.append(np.asarray(mdf.params))
std_errors.append(np.asarray(mdf.standard_errors()))
da,va = gendat()
ga = Gaussian()
md = GEE(da.endog, da.exog, da.group, da.time, ga, va,
constraint=(lhs, rhs))
mdf = md.fit()
score = md.score_test_results
pvalue = score["p-value"]
pvalues.append(pvalue)
