def main_reg(df):
# store (exogenous) regressors for first and second stage in a list
regressors_base = ['const', 'mean_hvac_share', 'mean_unempl', 'munempldiff', 'mskattekrdiff', 'mbefdiff', 'ekbistandpc_diff',
'dsmastad', 'dstorstad', 'dsv_maj_1', 'dseatsmp_1', 'dseatsop_1', 'panel8891', 'panel9194', 'flyktingandel']
exog_base = ['const', 'mean_hvac_share', 'mean_unempl', 'munempldiff', 'mskattekrdiff', 'mbefdiff', 'ekbistandpc_diff', 'dsmastad',
'dstorstad', 'dsv_maj_1', 'dseatsmp_1', 'dseatsop_1', 'panel8891', 'panel9194']
### standard errors clustered at municipality level
# first stage
reg1 = mt.reg(df, y_name = 'nonOECDshare_diff', x_name = regressors_base, cluster = 'kommun')
# second stage
iv1 = mt.ivreg(df, y_name = 'soc_bidr_diff', x_name = 'nonOECDshare_diff', z_name = 'flyktingandel', w_name = exog_base,
iv_method = '2sls', cluster = 'kommun')
### standard errors clustered at county level
# first stage
reg2 = mt.reg(df, y_name = 'nonOECDshare_diff', x_name = regressors_base, cluster = 'countykod')
# second stage
iv2 = mt.ivreg(df, y_name = 'soc_bidr_diff', x_name = 'nonOECDshare_diff', z_name = 'flyktingandel',
w_name = exog_base, iv_method = '2sls', cluster = 'countykod')
# call function from auxiliary file that creates Latex table fragments for Table 2
get_table2(df, reg1, iv1, reg2, iv2)
# perform F-test for relevance of the instrument
F_stat1 = reg1.Ftest('flyktingandel')[0]
F_stat2 = reg2.Ftest('flyktingandel')[0]
return(reg1, iv1, reg2, iv2, F_stat1, F_stat2)
def reg_ivtable7(df, y, var_basic, var_add):
"""
Parameters:
df (DataFrame) – Data with any relevant variables.
y_name (str) – Column name in df of the dependent variable.
x_name (str or list) – Column name(s) in df of the endogenous regressor(s).
z_name (str or list) – Column name(s) in df of the excluded instrument(s)
w_name (str or list) – Column name(s) in df of the included instruments/exogenous regressors
awt_name (str) – Column name in df to use for analytic weights in regression.
cluster (str) – Column name in df used to cluster standard errors.
"""
ydict = {
"chrswork": "Usual hours | H > 0 ",
"work50": "P(Hours >= 50)",
"work60": "P(Hours >= 60)"
}
x = ['indep'] # endogenous regressor
ins = ['ins'] # excluded instrument(s)
wt = 'perwt' # Weight
clt = 'metaready' # Cluster
# OLS regression for outcome Y
formulaOLS = y + ' ~ indep +' + ' + '.join(var_basic[0:])
OLS = wls_cluster(formulaOLS, df, wt, clt)
# Intrumental variables basic
IVb = emt.ivreg(df,
y_name=y,
x_name=x,
z_name=ins,
w_name=var_basic,
awt_name=wt,
cluster=clt,
addcons=True)
#Intrumental variables additonal
IVa = emt.ivreg(df,
y_name=y,
x_name=x,
z_name=ins,
w_name=var_add,
awt_name=wt,
cluster=clt,
addcons=True)
# Extract regression results
ivtable7 = pd.DataFrame(np.full((3, 3), ""))
ivtable7.iloc[0, :] = [
"{:.3f}".format(OLS.params['indep']),
"{:.3f}".format(IVb.beta['indep']), "{:.3f}".format(IVa.beta['indep'])
]
ivtable7.iloc[1, :] = [
"({:.3f})".format(OLS.bse['indep']),
"({:.3f})".format(IVb.se['indep']), "({:.3f})".format(IVa.se['indep'])
]
ivtable7.iloc[2, :] = ["Basic", "Basic", "Additional"]
ivtable7.columns = pd.MultiIndex.from_product([[ydict[y]],
["OLS", "IV", "IV"]])
return ivtable7
def placebo_reg(df_placebo):
# store (exogenous) regressors for first and second stage in a list
regr = ['const', 'mean_hvac_share', 'mean_unempl', 'munempldiff', 'mskattekrdiff', 'mbefdiff', 'ekbistandpc_diff', 'dsmastad',
'dstorstad', 'dsv_maj_1', 'dseatsmp_1', 'dseatsop_1', 'flyktingandel_tplus1', 'flyktingandel_tplus2', 'flyktingandel_tplus3']
exog = ['const', 'mean_hvac_share', 'mean_unempl', 'munempldiff', 'mskattekrdiff', 'mbefdiff', 'ekbistandpc_diff', 'dsmastad',
'dstorstad', 'dsv_maj_1', 'dseatsmp_1', 'dseatsop_1']
# first stage
reg_placebo1 = mt.reg(df_placebo, y_name = 'nonOECDshare_diff_tplus1', x_name = regr, cluster = 'kommun')
reg_placebo2 = mt.reg(df_placebo, y_name = 'nonOECDshare_diff_tplus2', x_name = regr, cluster = 'kommun')
reg_placebo3 = mt.reg(df_placebo, y_name = 'nonOECDshare_diff_tplus3', x_name = regr, cluster = 'kommun')
# second stage
iv_placebo = mt.ivreg(df_placebo, y_name = 'soc_bidr_diff', x_name = ['nonOECDshare_diff_tplus1', 'nonOECDshare_diff_tplus2',
'nonOECDshare_diff_tplus3'], z_name = ['flyktingandel_tplus1', 'flyktingandel_tplus2', 'flyktingandel_tplus3'], w_name = exog,
iv_method = '2sls', cluster = 'kommun')
# call function from auxiliary file that creates LaTex table fragments for Table 6
get_table6(df_placebo, reg_placebo1, reg_placebo2, reg_placebo3, iv_placebo)
# perform joint test of the three placebo treatments in the second stage regression
# return p-value of the test
pvalue = iv_placebo.Ftest(['nonOECDshare_diff_tplus1', 'nonOECDshare_diff_tplus2', 'nonOECDshare_diff_tplus3'])[1]
return(reg_placebo1, reg_placebo2, reg_placebo3, pvalue)
def reg_tableA1(df, clt, var_basic):
x = ['indep'] # endogenous regressor(s)
ins = ['ins'] # excluded instrument(s)
wt = 'perwt' # Weight
#Intrumental variables
IV_ch = emt.ivreg(df,
y_name="chrswork",
x_name=x,
z_name=ins,
w_name=var_basic,
awt_name=wt,
cluster=clt,
addcons=True)
IV_w50 = emt.ivreg(df,
y_name="work50",
x_name=x,
z_name=ins,
w_name=var_basic,
awt_name=wt,
cluster=clt,
addcons=True)
IV_w60 = emt.ivreg(df,
y_name="work60",
x_name=x,
z_name=ins,
w_name=var_basic,
awt_name=wt,
cluster=clt,
addcons=True)
tableA1 = pd.DataFrame(np.full((2, 3), ""))
tableA1.iloc[0, :] = [
"{:.3f}".format(IV_ch.beta['indep']),
"{:.3f}".format(IV_w50.beta['indep']),
"{:.3f}".format(IV_w60.beta['indep'])
]
tableA1.iloc[1, :] = [
"({:.3f})".format(IV_ch.se['indep']),
"({:.3f})".format(IV_w50.se['indep']),
"({:.3f})".format(IV_w60.se['indep'])
]
tableA1.columns = [
"Usual hours|H > 0", "P (Hours >= 50)", "P (Hours >= 60)"
]
return tableA1
def reg4iv(year,data,control):
for i in data["year"]:
if i == year:
regiv= mt.ivreg(df=data.loc[(data["year"]==i)], # DataFrame to use
y_name="dNazi_share", # Outcome
x_name="lis_share",
z_name="ss_nl",
w_name=control, # Indep. Variables
fe_name="wkr", # Fixed-effects
cluster='wkr')
return regiv.beta["lis_share"],regiv.se["lis_share"], regiv.N
def reg_ext(df, y, wt, var_basic):
x = ['indep', 'indepmarried'] # endogenous regressor(s)
ins = ['ins', 'insmarried'] # excluded instrument(s)
clt = 'metaready' # Cluster
pndict = {
'chrswork': "A1.Usual market hours worked/week(census)",
'weekhswork': "A2. Hours per week spent doing household chores",
'dum340310c1': "B1. Dummy for expenditures >0",
'avcost340310': "B2. Level of expenditures(unconditional)"
}
# OLS
formulaOLS = y + ' ~ indep + indepmarried +' + ' + '.join(var_basic[0:])
OLS = wls_cluster(formulaOLS, df, wt, clt)
#Intrumental variables
IV = emt.ivreg(df,
y_name=y,
x_name=x,
z_name=ins,
w_name=var_basic,
awt_name=wt,
cluster=clt,
addcons=True)
# Regression results
ext = pd.DataFrame(np.full((4, 2), ""))
ext.iloc[0, :] = [
"{:.3f}".format(OLS.params['indep']), "{:.3f}".format(IV.beta['indep'])
]
ext.iloc[1, :] = [
"({:.3f})".format(OLS.bse['indep']), "({:.3f})".format(IV.se['indep'])
]
ext.iloc[2, :] = [
"{:.3f}".format(OLS.params['indepmarried']),
"{:.3f}".format(IV.beta['indepmarried'])
]
ext.iloc[3, :] = [
"({:.3f})".format(OLS.bse['indepmarried']),
"({:.3f})".format(IV.se['indepmarried'])
]
ext.index = [
'ln((LS Imm. + LS Nat.)/LF)', "",
'ln((LS Imm. + LS Nat.)/LF) x married', ""
]
ext.columns = pd.MultiIndex.from_product([[pndict[y]], ["OLS", " IV "]])
return ext
def sens1_reg(df, df_sens1):
# run regression without dummy for large-sized municipal population as we excluded big city counties
# otherwise all values of that variable are zero and we cannot invert the regressor matrix
regressors_sens1 = ['const', 'mean_hvac_share', 'mean_unempl', 'munempldiff', 'mskattekrdiff', 'mbefdiff', 'ekbistandpc_diff', 'dsmastad',
'dsv_maj_1', 'dseatsmp_1', 'dseatsop_1', 'panel8891', 'panel9194', 'flyktingandel']
exog_sens1 = ['const', 'mean_hvac_share', 'mean_unempl', 'munempldiff', 'mskattekrdiff', 'mbefdiff', 'ekbistandpc_diff', 'dsmastad',
'dsv_maj_1', 'dseatsmp_1', 'dseatsop_1', 'panel8891', 'panel9194']
# first stage
reg_sens1 = mt.reg(df_sens1, y_name = 'nonOECDshare_diff', x_name = regressors_sens1, cluster = 'kommun')
# second stage
iv_sens1 = mt.ivreg(df_sens1, y_name = 'soc_bidr_diff', x_name = 'nonOECDshare_diff', z_name = 'flyktingandel',
w_name = exog_sens1, iv_method = '2sls', cluster = 'kommun')
# call function from auxiliary file that creates LaTex table fragments for Table 7
get_table7(df, reg_sens1, iv_sens1)
return(reg_sens1, iv_sens1)
def IV_regression(variable):
if variable == 'Income < p15':
df['regressor'] = df['Income < p15']
df['interaction_first'] = df['Refugee inflow * (y < p15)']
df['interaction_second'] = df['DeltaIM * (y < p15)']
elif variable == 'Income < p40':
df['regressor'] = df['Income < p40']
df['interaction_first'] = df['Refugee inflow * (y < p40)']
df['interaction_second'] = df['DeltaIM * (y < p40)']
elif variable == 'Income > p85':
df['regressor'] = df['Income > p85']
df['interaction_first'] = df['Refugee inflow * (y > p85)']
df['interaction_second'] = df['DeltaIM * (y > p85)']
elif variable == 'Wealth < p40':
df['regressor'] = df['Wealth < p40']
df['interaction_first'] = df['Refugee inflow * (w < p40)']
df['interaction_second'] = df['DeltaIM * (w < p40)']
elif variable == 'Wealth < p60':
df['regressor'] = df['Wealth < p60']
df['interaction_first'] = df['Refugee inflow * (w < p60)']
df['interaction_second'] = df['DeltaIM * (w < p60)']
elif variable == 'Wealth > p85':
df['regressor'] = df['Wealth > p85']
df['interaction_first'] = df['Refugee inflow * (w > p85)']
df['interaction_second'] = df['DeltaIM * (w > p85)']
elif variable == 'tjman_t_1':
df['regressor'] = df['tjman_t_1']
df['interaction_first'] = df['Refugee inflow * white-collar']
df['interaction_second'] = df['DeltaIM * white-collar']
elif variable == 'arbetare_t_1':
df['regressor'] = df['arbetare_t_1']
df['interaction_first'] = df['Refugee inflow * blue-collar']
df['interaction_second'] = df['DeltaIM * blue-collar']
exog = ['const', 'mean_hvac_share', 'mean_unempl', 'munempldiff', 'mskattekrdiff', 'mbefdiff', 'ekbistandpc_diff', 'dsmastad',
'dstorstad', 'dsv_maj_1', 'dseatsmp_1', 'dseatsop_1', 'panel8891', 'panel9194', 'regressor']
endog = ['nonOECDshare_diff', 'interaction_second']
instr = ['flyktingandel', 'interaction_first']
second_stage = mt.ivreg(df, y_name = 'soc_bidr_diff', x_name = endog, z_name = instr, w_name = exog, iv_method = '2sls',
cluster = 'kommun')
return second_stage
def sens2_reg(df, df_sens2):
# run regression without dummy for panel period 1991/94 as we excluded the observations of that panel
# otherwise all values of that variable are zero and we cannot invert the regressor matrix
regressors_sens2 = ['const', 'mean_hvac_share', 'mean_unempl', 'munempldiff', 'mskattekrdiff', 'mbefdiff', 'ekbistandpc_diff',
'dsmastad', 'dstorstad', 'dsv_maj_1', 'dseatsmp_1', 'dseatsop_1', 'panel8891', 'flyktingandel']
exog_sens2 = ['const', 'mean_hvac_share', 'mean_unempl', 'munempldiff', 'mskattekrdiff', 'mbefdiff', 'ekbistandpc_diff', 'dsmastad',
'dstorstad', 'dsv_maj_1', 'dseatsmp_1', 'dseatsop_1', 'panel8891']
# first stage
reg_sens2 = mt.reg(df_sens2, y_name = 'nonOECDshare_diff', x_name = regressors_sens2, cluster = 'kommun')
# second stage
iv_sens2 = mt.ivreg(df_sens2, y_name = 'soc_bidr_diff', x_name = 'nonOECDshare_diff', z_name = 'flyktingandel', w_name = exog_sens2,
iv_method = '2sls', cluster = 'kommun')
# call function from auxiliary file that creates LaTex table fragments for Table 8
get_table8(df, reg_sens2, iv_sens2)
# perform F-test for relevance of the instrument
F_stat = reg_sens2.Ftest('flyktingandel')[0]
return(reg_sens2, iv_sens2, F_stat)
def reg_tableA3(df, y, wt, var_basic):
x_coll = ['indep', 'indepCollegeplus'] # endogenous regressor(s)
x_grad = ['indep', 'indepGraduate']
ins_coll = ['ins', 'insCollegeplus'] # excluded instrument(s)
ins_grad = ['ins', 'insGraduate']
var_coll = ['collegeplus'] + var_basic # exogenous regressor(s)
var_grad = ['graduate'] + var_basic
clt = 'metaready' # Cluster
pndict = {
'uhrswork': "A1.Usual market hours worked/week(census)",
'weekhswork': "A2. Hours per week spent doing household chores",
'dum340310c1': "B1. Dummy for expenditures >0",
'avcost340310': "B2. Level of expenditures(unconditional)"
}
# OLS
formulaOLS = y + ' ~ indep + indepCollegeplus + collegeplus +' + ' + '.join(
var_basic[0:])
OLS = wls_cluster(formulaOLS, df, wt, clt)
#Intrumental variables
IV_coll = emt.ivreg(df,
y_name=y,
x_name=x_coll,
z_name=ins_coll,
w_name=var_coll,
awt_name=wt,
cluster=clt,
addcons=True)
IV_grad = emt.ivreg(df,
y_name=y,
x_name=x_grad,
z_name=ins_grad,
w_name=var_grad,
awt_name=wt,
cluster=clt,
addcons=True)
# Regression results
tableA3 = pd.DataFrame(np.full((6, 3), ""))
tableA3.iloc[0, :] = [
"{:.3f}".format(OLS.params['indep']),
"{:.3f}".format(IV_coll.beta['indep']),
"{:.3f}".format(IV_grad.beta['indep'])
]
tableA3.iloc[1, :] = [
"({:.3f})".format(OLS.bse['indep']),
"({:.3f})".format(IV_coll.se['indep']),
"({:.3f})".format(IV_grad.se['indep'])
]
tableA3.iloc[2, 0:2] = [
"{:.3f}".format(OLS.params['indepCollegeplus']),
"{:.3f}".format(IV_coll.beta['indepCollegeplus'])
]
tableA3.iloc[3, 0:2] = [
"({:.3f})".format(OLS.bse['indepCollegeplus']),
"({:.3f})".format(IV_coll.se['indepCollegeplus'])
]
tableA3.iloc[4, 2] = "{:.3f}".format(IV_grad.beta['indepGraduate'])
tableA3.iloc[5, 2] = "({:.3f})".format(IV_grad.se['indepGraduate'])
tableA3.index = [
'ln((LS Imm. + LS Nat.)/LF)', "",
'ln((LS Imm. + LS Nat.)/LF)xCollege or more', "",
'ln((LS Imm. + LS Nat.)/LF)xGraduate education ', ""
]
tableA3.columns = pd.MultiIndex.from_product([[pndict[y]],
["OLS", " IV ", "IV"]])
return tableA3
def reg_tableA2(df, var_basic, edu):
idict = {
"grad": "Graduate education",
'Advanced': "Professionals and PhDs",
'Master': "Master’s degree ",
'College': "College graduates",
'SomeCollege': "Some college ",
"Highschool": "HS grad less "
}
x = ['indep'] # endogenous regressor(s)
ins = ['ins'] # excluded instrument(s)
wt = 'perwt' # Weight
clt = 'metaready'
IV_uh = emt.ivreg(df,
y_name="uhrswork",
x_name=x,
z_name=ins,
w_name=var_basic,
awt_name=wt,
cluster=clt,
addcons=True)
IV_lf = emt.ivreg(df,
y_name="lflw",
x_name=x,
z_name=ins,
w_name=var_basic,
awt_name=wt,
cluster=clt,
addcons=True)
IV_ch = emt.ivreg(df,
y_name="chrswork",
x_name=x,
z_name=ins,
w_name=var_basic,
awt_name=wt,
cluster=clt,
addcons=True)
IV_w50 = emt.ivreg(df,
y_name="work50",
x_name=x,
z_name=ins,
w_name=var_basic,
awt_name=wt,
cluster=clt,
addcons=True)
IV_w60 = emt.ivreg(df,
y_name="work60",
x_name=x,
z_name=ins,
w_name=var_basic,
awt_name=wt,
cluster=clt,
addcons=True)
tableA2 = pd.DataFrame(np.full((2, 5), ""))
tableA2.iloc[0, :] = [
"{:.3f}".format(IV_uh.beta['indep']),
"{:.3f}".format(IV_lf.beta['indep']),
"{:.3f}".format(IV_ch.beta['indep']),
"{:.3f}".format(IV_w50.beta['indep']),
"{:.3f}".format(IV_w60.beta['indep'])
]
tableA2.iloc[1, :] = [
"({:.3f})".format(IV_uh.se['indep']),
"({:.3f})".format(IV_lf.se['indep']),
"({:.3f})".format(IV_ch.se['indep']),
"({:.3f})".format(IV_w50.se['indep']),
"({:.3f})".format(IV_w60.se['indep'])
]
tableA2.columns = [
"Usual hours", " LFP", "Usual hours|H > 0", "P (Hours >= 50)",
"P (Hours >= 60)"
]
tableA2.index = [idict[edu], ""]
return tableA2
def reg_ivtable10(df, panel, var_add):
x = ['indep', 'indepFemale'] # endogenous regressor(s)
ins = ['ins', 'insFemale'] # excluded instrument(s)
wt = 'perwt' # Weight
clt = 'metaready' # Cluster
pdict = {
"p90100": "90 - 100",
"p75100": "75 - 100",
"p5075": " 50 - 75",
"p2550": " 25 - 50",
"p025": "0 - 25"
}
#Intrumental variables additional
# Usual hours|H>0
IVch = emt.ivreg(df,
y_name='chrswork',
x_name=x,
z_name=ins,
w_name=var_add,
awt_name=wt,
cluster=clt,
addcons=True)
#log(Usual hours|H>0)
IVlh = emt.ivreg(df,
y_name="lhrswork",
x_name=x,
z_name=ins,
w_name=var_add,
awt_name=wt,
cluster=clt,
addcons=True)
#log(wage)
IVlw = emt.ivreg(df,
y_name="lwage",
x_name=x,
z_name=ins,
w_name=var_add,
awt_name=wt,
cluster=clt,
addcons=True)
# Extract regression results
ivtable10 = pd.DataFrame(np.full((2, 6), ""))
ivtable10.iloc[:, 0] = [
"{:.3f}".format(IVch.beta['indep']),
"({:.3f})".format(IVch.se['indep'])
]
ivtable10.iloc[:, 1] = [
"{:.3f}".format(IVch.beta['indepFemale']),
"({:.3f})".format(IVch.se['indepFemale'])
]
ivtable10.iloc[:, 2] = [
"{:.3f}".format(IVlh.beta['indep']),
"({:.3f})".format(IVlh.se['indep'])
]
ivtable10.iloc[:, 3] = [
"{:.3f}".format(IVlh.beta['indepFemale']),
"({:.3f})".format(IVlh.se['indepFemale'])
]
ivtable10.iloc[:, 4] = [
"{:.3f}".format(IVlw.beta['indep']),
"({:.3f})".format(IVlw.se['indep'])
]
ivtable10.iloc[:, 5] = [
"{:.3f}".format(IVlw.beta['indepFemale']),
"({:.3f})".format(IVlw.se['indepFemale'])
]
ivtable10.columns = pd.MultiIndex.from_product(
[["Usual hours|H>0 ", "log(Usual hours|H>0)", "log(Wage)"],
["Ln(LS Skilled)", "Ln(LS Skilled)xFemale"]])
ivtable10.index = [pdict[panel], ""]
return ivtable10
def reg_table9(df, panel, var_add):
pdict = {
"p90100": "90 - 100",
"p75100": "75 - 100",
"p5075": " 50 - 75",
"p2550": " 25 - 50",
"p025": "0 - 25"
}
x = ['indep', 'indepchild5'] # endogenous regressor(s)
ins = ['ins', 'inschild5'] # excluded instrument(s)
wt = 'perwt' # Weight
clt = 'metaready' # Cluster
#Intrumental variables additonal
#work50: P (Hours >= 50)
IVw50 = emt.ivreg(df,
y_name='work50',
x_name=x,
z_name=ins,
w_name=var_add,
awt_name=wt,
cluster=clt,
addcons=True)
#work60: P (Hours >= 60)
IVw60 = emt.ivreg(df,
y_name='work60',
x_name=x,
z_name=ins,
w_name=var_add,
awt_name=wt,
cluster=clt,
addcons=True)
#chrswork: Usual hours|H > 0
IVchr = emt.ivreg(df,
y_name='chrswork',
x_name=x,
z_name=ins,
w_name=var_add,
awt_name=wt,
cluster=clt,
addcons=True)
# Extract regression results
ivtable9 = pd.DataFrame(np.full((2, 6), ""))
ivtable9.iloc[:, 0] = [
"{:.3f}".format(IVchr.beta['indep']),
"({:.3f})".format(IVchr.se['indep'])
]
ivtable9.iloc[:, 1] = [
"{:.3f}".format(IVchr.beta['indepchild5']),
"({:.3f})".format(IVchr.se['indepchild5'])
]
ivtable9.iloc[:, 2] = [
"{:.3f}".format(IVw50.beta['indep']),
"({:.3f})".format(IVw50.se['indep'])
]
ivtable9.iloc[:, 3] = [
"{:.3f}".format(IVw50.beta['indepchild5']),
"({:.3f})".format(IVw50.se['indepchild5'])
]
ivtable9.iloc[:, 4] = [
"{:.3f}".format(IVw60.beta['indep']),
"({:.3f})".format(IVw60.se['indep'])
]
ivtable9.iloc[:, 5] = [
"{:.3f}".format(IVw60.beta['indepchild5']),
"({:.3f})".format(IVw60.se['indepchild5'])
]
ivtable9.columns = pd.MultiIndex.from_product(
[["Usual hours|H>0 ", "P(Hours>= 50)", "P(Hours>= 60)"],
["Ln(LS Skilled)", "Ln(LS Skilled)x child 0-5"]])
ivtable9.index = [pdict[panel], ""]
return ivtable9
def reg8(df, var_add, panel, ydict):
x = ['indep'] # endogenous regressor
ins = ['ins'] # excluded instrument(s)
wt = 'perwt' # Weight
clt = 'metaready' # Cluster
#Intrumental variables additonal
#uhrswork: Usual hours|week
IVuhr = emt.ivreg(df,
y_name='uhrswork',
x_name=x,
z_name=ins,
w_name=var_add,
awt_name=wt,
cluster=clt,
addcons=True)
#lflw:Labor Force Participation
IVlfp = emt.ivreg(df,
y_name='lflw',
x_name=x,
z_name=ins,
w_name=var_add,
awt_name=wt,
cluster=clt,
addcons=True)
#work50: P (Hours>= 50)
IVw50 = emt.ivreg(df,
y_name='work50',
x_name=x,
z_name=ins,
w_name=var_add,
awt_name=wt,
cluster=clt,
addcons=True)
#work60: P (Hours>= 60)
IVw60 = emt.ivreg(df,
y_name='work60',
x_name=x,
z_name=ins,
w_name=var_add,
awt_name=wt,
cluster=clt,
addcons=True)
#chrswork:Usual hours|H >0
IVchr = emt.ivreg(df,
y_name='chrswork',
x_name=x,
z_name=ins,
w_name=var_add,
awt_name=wt,
cluster=clt,
addcons=True)
ivtable8 = pd.DataFrame(np.full((2, 5), ""))
ivtable8.iloc[:, 0] = [
"{:.3f}".format(IVuhr.beta['indep']),
"({:.3f})".format(IVuhr.se['indep'])
]
ivtable8.iloc[:, 1] = [
"{:.3f}".format(IVlfp.beta['indep']),
"({:.3f})".format(IVlfp.se['indep'])
]
ivtable8.iloc[:, 2] = [
"{:.3f}".format(IVchr.beta['indep']),
"({:.3f})".format(IVchr.se['indep'])
]
ivtable8.iloc[:, 3] = [
"{:.3f}".format(IVw50.beta['indep']),
"({:.3f})".format(IVw50.se['indep'])
]
ivtable8.iloc[:, 4] = [
"{:.3f}".format(IVw60.beta['indep']),
"({:.3f})".format(IVw60.se['indep'])
]
ivtable8.index = [ydict[panel], ""]
ivtable8.columns = [
"Usual hours per week ", "LFP", "Usual hours|H>0 ", "P (Hours>=50)",
"P (Hours>=60)"
]
return ivtable8
