Learn more »
Push, build, and install
RubyGems
npm packages
Python packages
Maven artifacts
PHP packages
Go Modules
Bower components
Debian packages
RPM packages
NuGet packages
import numpy as np
from statsmodels.tools.testing import ParamsTableTestBunch
est = dict(
rank=3,
N=34,
ic=1,
k=3,
k_eq=1,
k_dv=1,
converged=1,
rc=0,
k_autoCns=0,
N_clust=5,
ll=-354.2436413025559,
k_eq_model=1,
ll_0=-356.2029100704882,
df_m=2,
chi2=5.204189583786304,
p=.0741181533729996,
r2_p=.0055004288638308,
cmdline="poisson accident yr_con op_75_79, vce(cluster ship)",
cmd="poisson",
predict="poisso_p",
estat_cmd="poisson_estat",
gof="poiss_g",
chi2type="Wald",
opt="moptimize",
vcetype="Robust",
clustvar="ship",
vce="cluster",
title="Poisson regression",
user="poiss_lf",
crittype="log pseudolikelihood",
ml_method="e2",
singularHmethod="m-marquardt",
technique="nr",
which="max",
depvar="accident",
properties="b V",
)
params_table = np.array([
-.02172061893549, .19933709357097, -.10896426022065, .91323083771076,
-.41241414311748, .36897290524649, np.nan, 1.9599639845401,
0, .22148585072024, .11093628220713, 1.9965140918162,
.04587799343723, .00405473301549, .43891696842499, np.nan,
1.9599639845401, 0, 2.2697077143215, 1.1048569901548,
2.054299999499, .03994666479943, .10422780555076, 4.4351876230922,
np.nan, 1.9599639845401, 0]).reshape(3, 9)
params_table_colnames = 'b se z pvalue ll ul df crit eform'.split()
params_table_rownames = 'yr_con op_75_79 _cons'.split()
cov = np.array([
.03973527687332, .00976206273414, -.21171095768584, .00976206273414,
.01230685870994, -.06297293767114, -.21171095768584, -.06297293767114,
1.2207089686939]).reshape(3, 3)
cov_colnames = 'yr_con op_75_79 _cons'.split()
cov_rownames = 'yr_con op_75_79 _cons'.split()
results_poisson_clu = ParamsTableTestBunch(
params_table=params_table,
params_table_colnames=params_table_colnames,
params_table_rownames=params_table_rownames,
cov=cov,
cov_colnames=cov_colnames,
cov_rownames=cov_rownames,
**est
)
est = dict(
rank=3,
N=34,
ic=1,
k=3,
k_eq=1,
k_dv=1,
converged=1,
rc=0,
k_autoCns=0,
ll=-354.2436413025559,
k_eq_model=1,
ll_0=-356.2029100704882,
df_m=2,
chi2=.1635672212515404,
p=.9214713337295277,
r2_p=.0055004288638308,
cmdline="poisson accident yr_con op_75_79, vce(robust)",
cmd="poisson",
predict="poisso_p",
estat_cmd="poisson_estat",
gof="poiss_g",
chi2type="Wald",
opt="moptimize",
vcetype="Robust",
vce="robust",
title="Poisson regression",
user="poiss_lf",
crittype="log pseudolikelihood",
ml_method="e2",
singularHmethod="m-marquardt",
technique="nr",
which="max",
depvar="accident",
properties="b V",
)
params_table = np.array([
-.02172061893549, .19233713248134, -.11292993014545, .91008610728406,
-.39869447148862, .35525323361764, np.nan, 1.9599639845401,
0, .22148585072024, .55301404772037, .400506735106,
.68878332380143, -.8624017657564, 1.3053734671969, np.nan,
1.9599639845401, 0, 2.2697077143215, .66532523368388,
3.4114258702533, .00064624070669, .96569421829539, 3.5737212103476,
np.nan, 1.9599639845401, 0]).reshape(3, 9)
params_table_colnames = 'b se z pvalue ll ul df crit eform'.split()
params_table_rownames = 'yr_con op_75_79 _cons'.split()
cov = np.array([
.03699357253114, -.01521223175214, -.09585501859714, -.01521223175214,
.30582453697607, -.1649339692102, -.09585501859714, -.1649339692102,
.44265766657651]).reshape(3, 3)
cov_colnames = 'yr_con op_75_79 _cons'.split()
cov_rownames = 'yr_con op_75_79 _cons'.split()
results_poisson_hc1 = ParamsTableTestBunch(
params_table=params_table,
params_table_colnames=params_table_colnames,
params_table_rownames=params_table_rownames,
cov=cov,
cov_colnames=cov_colnames,
cov_rownames=cov_rownames,
**est
)
est = dict(
rank=3,
N=34,
ic=4,
k=3,
k_eq=1,
k_dv=1,
converged=1,
rc=0,
k_autoCns=0,
ll=-91.28727940081573,
k_eq_model=1,
ll_0=-122.0974139280415,
df_m=2,
chi2=61.62026905445154,
p=4.16225408420e-14,
r2_p=.2523405986746273,
cmdline="poisson accident yr_con op_75_79, exposure(service)",
cmd="poisson",
predict="poisso_p",
estat_cmd="poisson_estat",
offset="ln(service)",
gof="poiss_g",
chi2type="LR",
opt="moptimize",
vce="oim",
title="Poisson regression",
user="poiss_lf",
crittype="log likelihood",
ml_method="e2",
singularHmethod="m-marquardt",
technique="nr",
which="max",
depvar="accident",
properties="b V",
)
params_table = np.array([
.30633819450439, .05790831365493, 5.290055523458, 1.222792336e-07,
.19283998533528, .4198364036735, np.nan, 1.9599639845401,
0, .35592229608495, .12151759298719, 2.9289775030556,
.00340079035234, .11775219034206, .59409240182785, np.nan,
1.9599639845401, 0, -6.974712802772, .13252425018256,
-52.629709605328, 0, -7.234455560208, -6.714970045336,
np.nan, 1.9599639845401, 0]).reshape(3, 9)
params_table_colnames = 'b se z pvalue ll ul df crit eform'.split()
params_table_rownames = 'yr_con op_75_79 _cons'.split()
cov = np.array([
.00335337279036, -.00315267340017, -.00589654294427, -.00315267340017,
.0147665254054, -.00165060980569, -.00589654294427, -.00165060980569,
.01756267688645]).reshape(3, 3)
cov_colnames = 'yr_con op_75_79 _cons'.split()
cov_rownames = 'yr_con op_75_79 _cons'.split()
results_poisson_exposure_nonrobust = ParamsTableTestBunch(
params_table=params_table,
params_table_colnames=params_table_colnames,
params_table_rownames=params_table_rownames,
cov=cov,
cov_colnames=cov_colnames,
cov_rownames=cov_rownames,
**est
)
est = dict(
rank=3,
N=34,
ic=4,
k=3,
k_eq=1,
k_dv=1,
converged=1,
rc=0,
k_autoCns=0,
ll=-91.28727940081573,
k_eq_model=1,
ll_0=-122.0974139280415,
df_m=2,
chi2=15.1822804640621,
p=.0005049050167458,
r2_p=.2523405986746273,
cmdline="poisson accident yr_con op_75_79, exposure(service) vce(robust)", # noqa:E501
cmd="poisson",
predict="poisso_p",
estat_cmd="poisson_estat",
offset="ln(service)",
gof="poiss_g",
chi2type="Wald",
opt="moptimize",
vcetype="Robust",
vce="robust",
title="Poisson regression",
user="poiss_lf",
crittype="log pseudolikelihood",
ml_method="e2",
singularHmethod="m-marquardt",
technique="nr",
which="max",
depvar="accident",
properties="b V",
)
params_table = np.array([
.30633819450439, .09144457613957, 3.3499875819514, .00080815183366,
.12711011868929, .48556627031949, np.nan, 1.9599639845401,
0, .35592229608495, .16103531267836, 2.2102127177276,
.02709040275274, .04029888299621, .67154570917369, np.nan,
1.9599639845401, 0, -6.974712802772, .2558675415017,
-27.259076168227, 1.29723387e-163, -7.4762039689282, -6.4732216366159,
np.nan, 1.9599639845401, 0]).reshape(3, 9)
params_table_colnames = 'b se z pvalue ll ul df crit eform'.split()
params_table_rownames = 'yr_con op_75_79 _cons'.split()
cov = np.array([
.00836211050535, .00098797681063, -.01860743122756, .00098797681063,
.02593237192942, -.02395236210603, -.01860743122756, -.02395236210603,
.06546819879413]).reshape(3, 3)
cov_colnames = 'yr_con op_75_79 _cons'.split()
cov_rownames = 'yr_con op_75_79 _cons'.split()
results_poisson_exposure_hc1 = ParamsTableTestBunch(
params_table=params_table,
params_table_colnames=params_table_colnames,
params_table_rownames=params_table_rownames,
cov=cov,
cov_colnames=cov_colnames,
cov_rownames=cov_rownames,
**est
)
est = dict(
rank=3,
N=34,
ic=4,
k=3,
k_eq=1,
k_dv=1,
converged=1,
rc=0,
k_autoCns=0,
N_clust=5,
ll=-91.28727940081573,
k_eq_model=1,
ll_0=-122.0974139280415,
df_m=2,
chi2=340.7343047354823,
p=1.02443835269e-74,
r2_p=.2523405986746273,
cmdline="poisson accident yr_con op_75_79, exposure(service) vce(cluster ship)", # noqa:E501
cmd="poisson",
predict="poisso_p",
estat_cmd="poisson_estat",
offset="ln(service)",
gof="poiss_g",
chi2type="Wald",
opt="moptimize",
vcetype="Robust",
clustvar="ship",
vce="cluster",
title="Poisson regression",
user="poiss_lf",
crittype="log pseudolikelihood",
ml_method="e2",
singularHmethod="m-marquardt",
technique="nr",
which="max",
depvar="accident",
properties="b V",
)
params_table = np.array([
.30633819450439, .03817694295902, 8.0241677504982, 1.022165435e-15,
.23151276126487, .38116362774391, np.nan, 1.9599639845401,
0, .35592229608495, .09213163536669, 3.8631930787765,
.00011191448109, .17534760892947, .53649698324044, np.nan,
1.9599639845401, 0, -6.974712802772, .0968656626603,
-72.003975518463, 0, -7.1645660129248, -6.7848595926192,
np.nan, 1.9599639845401, 0]).reshape(3, 9)
params_table_colnames = 'b se z pvalue ll ul df crit eform'.split()
params_table_rownames = 'yr_con op_75_79 _cons'.split()
cov = np.array([
.0014574789737, -.00277745275086, .00108765624666, -.00277745275086,
.00848823823534, -.00469929607507, .00108765624666, -.00469929607507,
.00938295660262]).reshape(3, 3)