FirstStageDiagnostics

FirstStageDiagnostics(f_stat, p_value, eff_f)

Instrument-strength diagnostics of a 2SLS first stage.

Parameters

Name Type Description Default
f_stat float Wald F statistic of the joint null that every excluded instrument has a zero first-stage coefficient. It inherits the first stage’s covariance estimator, so it is heteroskedasticity- or cluster-robust whenever the second stage is. required
p_value float P-value of f_stat. required
eff_f float or None Effective F statistic of Olea and Pflueger (2013), computed against a heteroskedasticity-robust first stage. None until IV_Diag() or eff_F() computes it. required

Examples

import pyfixest as pf

fit = pf.feols("Y ~ X2 | f1 | X1 ~ Z1", pf.get_data())
fit.first_stage.diagnostics
FirstStageDiagnostics(f_stat=647.2703851604911, p_value=8.76497162841603e-143, eff_f=None)