After applying statsmodels.api.Logit I get the output of the logistic model.
LogModel = sm.Logit(y_01, Xdata_WithDummies).fit()
walds = LogModel.wald_test_terms()
Among the computed statistics there is a Wald Test table given as a pandas Dataframe (<class 'statsmodels.stats.contrast.WaldTestResults'>), that I can print and see it. However, I need to extract specific elements of this table for further analysis. According to the help page the Wald table is a pandas DataFrame.
I did not manage to transform this table into a list (list(wald), TypeError: 'WaldTestResults' object is not iterable) nor to see its values by wald.values (error: AttributeError: 'WaldTestResults' object has no attribute 'values') nor to extract a specific column (TypeError: 'WaldTestResults' object is not subscriptable), or even to extract specific values out of the table following relevant advice (e.g. here).
How could I read specific values out of this table? Or (equivalently) how could I transform this table into a list?
To convert it to a pandas.DataFrame you need to use the .summary_frame() method.
import statsmodels.api as sm
import numpy as np
np.random.seed(123)
y = np.random.randint(0, 2, 50)
x = np.random.randint(0, 2, (50, 3))
LogModel = sm.Logit(y, x).fit()
walds = LogModel.wald_test_terms()
df = walds.summary_frame()
# chi2 P>chi2 df constraint
#x1 0.0 1.0 1
#x2 0.0 1.0 1
#x3 0.0 1.0 1
type(df)
#pandas.core.frame.DataFrame