def setupClass(cls):
data = longley.load()
data.exog = add_constant(data.exog)
ols_res = OLS(data.endog, data.exog).fit()
gls_res = GLS(data.endog, data.exog).fit()
cls.res1 = gls_res
cls.res2 = ols_res
def __init__(self):
from scikits.statsmodels.datasets.sunspots import load
self.data = load()
self.rho, self.sigma = yule_walker(self.data.endog, order=4,
method="mle")
self.R_params = [1.2831003105694765, -0.45240924374091945,
-0.20770298557575195, 0.047943648089542337]
def setupClass(cls):
data = longley.load()
data.exog = add_constant(data.exog)
ols_res = OLS(data.endog, data.exog).fit()
gls_res = GLS(data.endog, data.exog).fit()
cls.res1 = gls_res
cls.res2 = ols_res
def __init__(self):
from scikits.statsmodels.datasets.longley import load
data = load()
data.exog = add_constant(data.exog)
self.res1 = OLS(data.endog, data.exog).fit()
R = np.identity(7)[:-1,:]
self.Ftest = self.res1.f_test(R)
def __init__(self):
from scikits.statsmodels.datasets.longley import load
data = load()
data.exog = add_constant(data.exog)
ols_res = OLS(data.endog, data.exog).fit()
gls_res = GLS(data.endog, data.exog).fit()
self.res1 = gls_res
self.res2 = ols_res
def setupClass(cls):
data = longley.load()
data.exog = add_constant(data.exog)
res1 = OLS(data.endog, data.exog).fit()
R = np.array([[0, 1, 1, 0, 0, 0, 0], [0, 1, 0, 1, 0, 0, 0],
[0, 1, 0, 0, 0, 0, 0], [0, 0, 0, 0, 1, 0, 0],
[0, 0, 0, 0, 0, 1, 0]])
q = np.array([0, 0, 0, 1, 0])
cls.Ftest1 = res1.f_test(R, q)
def __init__(self):
from scikits.statsmodels.datasets.longley import load
from results.results_regression import Longley
data = load()
data.exog = add_constant(data.exog)
res1 = OLS(data.endog, data.exog).fit()
res2 = Longley()
res2.wresid = res1.wresid # workaround hack
self.res1 = res1
self.res2 = res2
def setupClass(cls):
data = longley.load()
data.exog = add_constant(data.exog)
res1 = OLS(data.endog, data.exog).fit()
R = np.array([[0,1,1,0,0,0,0],
[0,1,0,1,0,0,0],
[0,1,0,0,0,0,0],
[0,0,0,0,1,0,0],
[0,0,0,0,0,1,0]])
q = np.array([0,0,0,1,0])
cls.Ftest1 = res1.f_test(R,q)
def setupClass(cls):
from results.results_glm import Cpunish
from scikits.statsmodels.datasets.cpunish import load
data = load()
data.exog[:,3] = np.log(data.exog[:,3])
data.exog = add_constant(data.exog)
exposure = [100] * len(data.endog)
cls.res1 = GLM(data.endog, data.exog, family=sm.families.Poisson(),
exposure=exposure).fit()
cls.res1.params[-1] += np.log(100) # add exposure back in to param
# to make the results the same
cls.res2 = Cpunish()
def setupClass(cls):
from results.results_glm import Cpunish
from scikits.statsmodels.datasets.cpunish import load
data = load()
data.exog[:, 3] = np.log(data.exog[:, 3])
data.exog = add_constant(data.exog)
exposure = [100] * len(data.endog)
cls.res1 = GLM(data.endog, data.exog, family=sm.families.Poisson(), exposure=exposure).fit()
cls.res1.params[-1] += np.log(100) # add exposure back in to param
# to make the results the same
cls.res2 = Cpunish()
def setupClass(cls):
from results.results_regression import Longley
data = longley.load()
data.exog = add_constant(data.exog)
res1 = OLS(data.endog, data.exog).fit()
res2 = Longley()
res2.wresid = res1.wresid # workaround hack
cls.res1 = res1
cls.res2 = res2
res_qr = OLS(data.endog, data.exog).fit(method="qr")
cls.res_qr = res_qr
def setupClass(cls):
from results.results_regression import Longley
data = longley.load()
data.exog = add_constant(data.exog)
res1 = OLS(data.endog, data.exog).fit()
res2 = Longley()
res2.wresid = res1.wresid # workaround hack
cls.res1 = res1
cls.res2 = res2
res_qr = OLS(data.endog, data.exog).fit(method="qr")
cls.res_qr = res_qr
def setupClass(cls):
from results.results_regression import LongleyGls
data = longley.load()
exog = add_constant(np.column_stack((data.exog[:, 1], data.exog[:, 4])))
tmp_results = OLS(data.endog, exog).fit()
rho = np.corrcoef(tmp_results.resid[1:], tmp_results.resid[:-1])[0][1] # by assumption
order = toeplitz(np.arange(16))
sigma = rho ** order
GLS_results = GLS(data.endog, exog, sigma=sigma).fit()
cls.res1 = GLS_results
cls.res2 = LongleyGls()
def __init__(self):
from scikits.statsmodels.datasets.longley import load
data = load()
self.data = data
data.exog = add_constant(data.exog)
self.res1 = OLS(data.endog, data.exog).fit()
# def setup(self):
# if skipR:
# raise SkipTest, "Rpy not installed"
# else:
R = np.identity(7)
self.Ttest = self.res1.t_test(R)
def setupClass(cls):
from results.results_regression import LongleyGls
data = longley.load()
exog = add_constant(np.column_stack(\
(data.exog[:,1],data.exog[:,4])))
tmp_results = OLS(data.endog, exog).fit()
rho = np.corrcoef(tmp_results.resid[1:],
tmp_results.resid[:-1])[0][1] # by assumption
order = toeplitz(np.arange(16))
sigma = rho**order
GLS_results = GLS(data.endog, exog, sigma=sigma).fit()
cls.res1 = GLS_results
cls.res2 = LongleyGls()
def __init__(self):
'''
Tests Poisson family with canonical log link.
Test results were obtained by R.
'''
from results.results_glm import Cpunish
from scikits.statsmodels.datasets.cpunish import load
self.data = load()
self.data.exog[:,3] = np.log(self.data.exog[:,3])
self.data.exog = add_constant(self.data.exog)
self.res1 = GLM(self.data.endog, self.data.exog,
family=sm.families.Poisson()).fit()
self.res2 = Cpunish()
def setupClass(cls):
# if skipR:
# raise SkipTest, "Rpy not installed"
# try:
# r.library('car')
# except RPyRException:
# raise SkipTest, "car library not installed for R"
R = np.zeros(7)
R[4:6] = [1, -1]
# self.R = R
data = longley.load()
data.exog = add_constant(data.exog)
res1 = OLS(data.endog, data.exog).fit()
cls.Ttest1 = res1.t_test(R)
def __init__(self):
'''
Tests Poisson family with canonical log link.
Test results were obtained by R.
'''
from results.results_glm import Cpunish
from scikits.statsmodels.datasets.cpunish import load
self.data = load()
self.data.exog[:,3] = np.log(self.data.exog[:,3])
self.data.exog = add_constant(self.data.exog)
self.res1 = GLM(self.data.endog, self.data.exog,
family=sm.families.Poisson()).fit()
self.res2 = Cpunish()
def setupClass(cls):
# if skipR:
# raise SkipTest, "Rpy not installed"
# try:
# r.library('car')
# except RPyRException:
# raise SkipTest, "car library not installed for R"
R = np.zeros(7)
R[4:6] = [1,-1]
# self.R = R
data = longley.load()
data.exog = add_constant(data.exog)
res1 = OLS(data.endog, data.exog).fit()
cls.Ttest1 = res1.t_test(R)
def __init__(self):
from scikits.statsmodels.datasets.longley import load
from results.results_regression import LongleyGls
data = load()
exog = add_constant(np.column_stack(\
(data.exog[:,1],data.exog[:,4])))
tmp_results = OLS(data.endog, exog).fit()
rho = np.corrcoef(tmp_results.resid[1:],
tmp_results.resid[:-1])[0][1] # by assumption
order = toeplitz(np.arange(16))
sigma = rho**order
GLS_results = GLS(data.endog, exog, sigma=sigma).fit()
self.res1 = GLS_results
self.res2 = LongleyGls()
def __init__(self):
'''
Test Gaussian family with canonical identity link
'''
# Test Precisions
self.decimal_resids = DECIMAL_3
self.decimal_params = DECIMAL_2
self.decimal_bic = DECIMAL_0
self.decimal_bse = DECIMAL_3
from scikits.statsmodels.datasets.longley import load
self.data = load()
self.data.exog = add_constant(self.data.exog)
self.res1 = GLM(self.data.endog, self.data.exog,
family=sm.families.Gaussian()).fit()
from results.results_glm import Longley
self.res2 = Longley()
def __init__(self):
'''
Test Gaussian family with canonical identity link
'''
# Test Precisions
self.decimal_resids = DECIMAL_3
self.decimal_params = DECIMAL_2
self.decimal_bic = DECIMAL_0
self.decimal_bse = DECIMAL_3
from scikits.statsmodels.datasets.longley import load
self.data = load()
self.data.exog = add_constant(self.data.exog)
self.res1 = GLM(self.data.endog, self.data.exog,
family=sm.families.Gaussian()).fit()
from results.results_glm import Longley
self.res2 = Longley()
def __init__(self):
'''
Test Binomial family with canonical logit link using star98 dataset.
'''
self.decimal_resids = DECIMAL_1
self.decimal_bic = DECIMAL_2
from scikits.statsmodels.datasets.star98 import load
from results.results_glm import Star98
data = load()
data.exog = add_constant(data.exog)
self.res1 = GLM(data.endog, data.exog, \
family=sm.families.Binomial()).fit()
#NOTE: if you want to replicate with RModel
#res2 = RModel(data.endog[:,0]/trials, data.exog, r.glm,
# family=r.binomial, weights=trials)
self.res2 = Star98()
def __init__(self):
'''
Test Binomial family with canonical logit link using star98 dataset.
'''
self.decimal_resids = DECIMAL_1
self.decimal_bic = DECIMAL_2
from scikits.statsmodels.datasets.star98 import load
from results.results_glm import Star98
data = load()
data.exog = add_constant(data.exog)
self.res1 = GLM(data.endog, data.exog, \
family=sm.families.Binomial()).fit()
#NOTE: if you want to replicate with RModel
#res2 = RModel(data.endog[:,0]/trials, data.exog, r.glm,
# family=r.binomial, weights=trials)
self.res2 = Star98()
def __init__(self):
'''
Tests Gamma family with canonical inverse link (power -1)
'''
# Test Precisions
self.decimal_aic_R = -1 #TODO: off by about 1, we are right with Stata
self.decimal_resids = DECIMAL_2
from scikits.statsmodels.datasets.scotland import load
from results.results_glm import Scotvote
data = load()
data.exog = add_constant(data.exog)
res1 = GLM(data.endog, data.exog, \
family=sm.families.Gamma()).fit()
self.res1 = res1
# res2 = RModel(data.endog, data.exog, r.glm, family=r.Gamma)
res2 = Scotvote()
res2.aic_R += 2 # R doesn't count degree of freedom for scale with gamma
self.res2 = res2
def __init__(self):
'''
Tests Gamma family with canonical inverse link (power -1)
'''
# Test Precisions
self.decimal_aic_R = -1 #TODO: off by about 1, we are right with Stata
self.decimal_resids = DECIMAL_2
from scikits.statsmodels.datasets.scotland import load
from results.results_glm import Scotvote
data = load()
data.exog = add_constant(data.exog)
res1 = GLM(data.endog, data.exog, \
family=sm.families.Gamma()).fit()
self.res1 = res1
# res2 = RModel(data.endog, data.exog, r.glm, family=r.Gamma)
res2 = Scotvote()
res2.aic_R += 2 # R doesn't count degree of freedom for scale with gamma
self.res2 = res2
def __init__(self):
'''
Test Negative Binomial family with canonical log link
'''
# Test Precision
self.decimal_resid = DECIMAL_1
self.decimal_params = DECIMAL_3
self.decimal_resids = -1 # 1 % mismatch at 0
self.decimal_fittedvalues = DECIMAL_1
from scikits.statsmodels.datasets.committee import load
self.data = load()
self.data.exog[:,2] = np.log(self.data.exog[:,2])
interaction = self.data.exog[:,2]*self.data.exog[:,1]
self.data.exog = np.column_stack((self.data.exog,interaction))
self.data.exog = add_constant(self.data.exog)
self.res1 = GLM(self.data.endog, self.data.exog,
family=sm.families.NegativeBinomial()).fit()
from results.results_glm import Committee
res2 = Committee()
res2.aic_R += 2 # They don't count a degree of freedom for the scale
self.res2 = res2
def __init__(self):
'''
Test Negative Binomial family with canonical log link
'''
# Test Precision
self.decimal_resid = DECIMAL_1
self.decimal_params = DECIMAL_3
self.decimal_resids = -1 # 1 % mismatch at 0
self.decimal_fittedvalues = DECIMAL_1
from scikits.statsmodels.datasets.committee import load
self.data = load()
self.data.exog[:,2] = np.log(self.data.exog[:,2])
interaction = self.data.exog[:,2]*self.data.exog[:,1]
self.data.exog = np.column_stack((self.data.exog,interaction))
self.data.exog = add_constant(self.data.exog)
self.res1 = GLM(self.data.endog, self.data.exog,
family=sm.families.NegativeBinomial()).fit()
from results.results_glm import Committee
res2 = Committee()
res2.aic_R += 2 # They don't count a degree of freedom for the scale
self.res2 = res2
"""Example: scikits.statsmodels.OLS
"""
from scikits.statsmodels.datasets.longley import load
import scikits.statsmodels.api as sm
from scikits.statsmodels.iolib.table import (SimpleTable, default_txt_fmt,
default_latex_fmt,
default_html_fmt)
import numpy as np
data = load()
data_orig = (data.endog.copy(), data.exog.copy())
#Note: In this example using zscored/standardized variables has no effect on
# regression estimates. Are there no numerical problems?
rescale = 0
#0: no rescaling, 1:demean, 2:standardize, 3:standardize and transform back
rescale_ratio = data.endog.std() / data.exog.std(0)
if rescale > 0:
# rescaling
data.endog -= data.endog.mean()
data.exog -= data.exog.mean(0)
if rescale > 1:
data.endog *= 1. / data.endog.std()
#data.exog *= 1000./data.exog.var(0)
data.exog /= data.exog.std(0)
#rescale_ratio = data.exog.var(0)/data.endog.var()
#skip because mean has been removed, but dimension is hardcoded in table
"""Example: scikits.statsmodels.OLS
"""
from scikits.statsmodels.datasets.longley import load
import scikits.statsmodels as sm
from scikits.statsmodels.iolib.table import (SimpleTable, default_txt_fmt,
default_latex_fmt, default_html_fmt)
import numpy as np
data = load()
data_orig = (data.endog.copy(), data.exog.copy())
#Note: In this example using zscored/standardized variables has no effect on
# regression estimates. Are there no numerical problems?
rescale = 0
#0: no rescaling, 1:demean, 2:standardize, 3:standardize and transform back
rescale_ratio = data.endog.std()/data.exog.std(0)
if rescale > 0:
# rescaling
data.endog -= data.endog.mean()
data.exog -= data.exog.mean(0)
if rescale > 1:
data.endog *= 1./data.endog.std()
#data.exog *= 1000./data.exog.var(0)
data.exog /= data.exog.std(0)
#rescale_ratio = data.exog.var(0)/data.endog.var()
#skip because mean has been removed, but dimension is hardcoded in table
data.exog = sm.tools.add_constant(data.exog)
def setupClass(cls):
data = longley.load()
data.exog = add_constant(data.exog)
cls.res1 = OLS(data.endog, data.exog).fit()
cls.res2 = WLS(data.endog, data.exog).fit()
def __init__(self):
from scikits.statsmodels.datasets.ccard import load
data = load()
self.res1 = WLS(data.endog, data.exog, weights = 1/data.exog[:,2]).fit()
self.res2 = GLS(data.endog, data.exog, sigma = data.exog[:,2]).fit()
def setupClass(cls):
data = longley.load()
data.exog = add_constant(data.exog)
cls.res1 = OLS(data.endog, data.exog).fit()
R = np.identity(7)
cls.Ttest = cls.res1.t_test(R)
def setupClass(cls):
data = longley.load()
data.exog = add_constant(data.exog)
res1 = OLS(data.endog, data.exog).fit()
R2 = [[0,1,-1,0,0,0,0],[0, 0, 0, 0, 1, -1, 0]]
cls.Ftest1 = res1.f_test(R2)
def setupClass(cls):
data = longley.load()
data.exog = add_constant(data.exog)
res1 = OLS(data.endog, data.exog).fit()
R2 = [[0, 1, -1, 0, 0, 0, 0], [0, 0, 0, 0, 1, -1, 0]]
cls.Ftest1 = res1.f_test(R2)
def setupClass(cls):
data = longley.load()
data.exog = add_constant(data.exog)
cls.res1 = OLS(data.endog, data.exog).fit()
R = np.identity(7)
cls.Ttest = cls.res1.t_test(R)
def setupClass(cls):
data = longley.load()
data.exog = add_constant(data.exog)
cls.res1 = OLS(data.endog, data.exog).fit()
cls.res2 = WLS(data.endog, data.exog).fit()
