def get_table3(df):
### regressions:
rslt = smf.ols(formula="stdgrade ~ treat + pol1+ pol1t",
data=df,
weights=df["kwgt"]).fit(
cov_type='cluster',
cov_kwds={'groups': df["studentid"]})
rslt1 = rslt
formula2 = "stdgrade ~ treat + treatmentvol + treatmentfor + volcourse + forcourse + pol1 + pol1t + pol1vol + pol1tvol + pol1for + pol1tfor"
rslt = smf.ols(formula=formula2, data=df, weights=df["kwgt"]).fit(
cov_type='cluster', cov_kwds={'groups': df["studentid"]})
rslt2 = rslt
### Table stargazer:
stargazer = Stargazer([rslt1, rslt2])
stargazer.custom_columns(["column 1", "column 4"], [1, 1])
stargazer.title("Table 3 - Effects on standardized grades")
stargazer.show_model_numbers(False)
stargazer.significant_digits(2)
stargazer.covariate_order(["treat", "treatmentvol", "treatmentfor"])
stargazer.rename_covariates({
"treat":
"1st-year GPA is below 7",
"treatmentvol":
"Attendance is voluntary x treatment",
"treatmentfor":
"Absence is penalized x treatment"
})
stargazer.show_degrees_of_freedom(False)
stargazer.add_line('Fixed Effects', ['No', 'No'])
return stargazer
reg_df = pd.merge(reg_df, ff_df, left_index=True, right_index=True)
strategy_name_list = list(strategy_ret_df.columns)
results_list = []
for name in strategy_name_list:
# to have the same name for all variables
reg_df_tmp = reg_df.rename({name: "ret"}, axis=1)
results_list.append(
smf.ols(formula="ret ~ MKT + SMB + HML + CMA + RMW",
data=reg_df_tmp * 12).fit())
# Outputting short regression results:
stargazer = Stargazer([results_list[0], results_list[3], results_list[6]])
stargazer.custom_columns(['D 30', 'prob 20', 'prob 40'], [1, 1, 1])
stargazer.covariate_order(['Intercept', 'MKT', 'SMB', 'HML', 'RMW', 'CMA'])
stargazer.show_degrees_of_freedom(False)
f = open(
"/Users/rsigalov/Dropbox/2019_Revision/Writing/Predictive Regressions/tables/disaster_sort_reg_on_ff.tex",
"w")
f.write(stargazer.render_latex())
f.close()
# Doing extended regression table where I do regressions of strategy return on
# (1) just the market, (2) FF 3 factors and (3) FF 5 factors.
results_list = []
for name in ["D_30", "p_20_30"]:
# to have the same name for all variables
reg_df_tmp = reg_df.rename({name: "ret"}, axis=1)
results_list.append(
smf.ols(formula="ret ~ MKT", data=reg_df_tmp * 12).fit())
results_list.append(
def ols_regression_formatted(data,
specifications,
as_latex=False,
covariates_names=None,
covariates_order=None):
"""
Creates formatted tables for different dependent variables and specifications
Input:
data (df): Dataframe containing all necessary variables for OLS regression
specifications (dictionary): dependent variables as keys and list of specifications
as values
as_latex (bool): specify whether Output as table or Latex code
covariate_names (dict): dictionary with covariate names as in "data" as keys and new
covariate names as values
Output:
list_of_tables (list of stargazer tables): list of formatted tables
"""
# Create dictionary which connects dependent variables with formatted tables
dict_regression_tables = {}
# Generate regressions
for depvar in specifications.keys():
regression_list = []
specification_list = specifications[depvar]
list_all_covariates = []
for specification in specification_list:
estimation_equation = depvar + " ~ " + specification
regression = smf.ols(data=data, formula=estimation_equation).fit()
regression_list.append(regression)
# Create set of all variables for this dependent variable
list_all_covariates = list(
set(list_all_covariates +
regression.params.index.values.tolist()))
# Format table with stargazer
formatted_table = Stargazer(regression_list)
# No dimension of freedoms and blank dependent variable
formatted_table.show_degrees_of_freedom(False)
formatted_table.dependent_variable_name("")
# Optional: Change order of covariates
if covariates_order is not None:
covariates_order_depvar = list(
OrderedSet(covariates_order).intersection(list_all_covariates))
list_remaining_covariates = list(
OrderedSet(list_all_covariates).difference(
OrderedSet(covariates_order_depvar)))
covariates_sorted = list(
OrderedSet(covariates_order_depvar).union(
list_remaining_covariates))
covariates_sorted.remove("Intercept")
covariates_sorted = covariates_sorted + ["Intercept"]
formatted_table.covariate_order(covariates_sorted)
# Optional: Change name of covariates
if covariates_names is not None:
formatted_table.rename_covariates(covariates_names)
# Add table or latex code to dictionary
if as_latex is True:
dict_regression_tables[depvar] = formatted_table.render_latex()
# Delete tabular environment around it
dict_regression_tables[depvar] = dict_regression_tables[
depvar].replace("\\begin{table}[!htbp] \\centering\n", "")
dict_regression_tables[depvar] = dict_regression_tables[
depvar].replace("\\end{table}", "")
else:
dict_regression_tables[depvar] = formatted_table
return dict_regression_tables