Instrument-free inference under confined regressor endogeneity; derivations and applications
Stellenbosch Working Paper Series No. WP09/2020Publication date: June 2020
Author(s):
Instead of exploiting instruments and claiming these to be uncorrelated with the disturbances, in an instrument-free approach one may adopt flexible bounds on the correlation between the endogenous regressors and the disturbances. Such an alternative to Two-Stage Least-Squares (TSLS) inference is developed here for general linear models with endogenous possibly time-dependent regressors. Earlier results enabled this just for rather restrictive mesokurtic i.i.d. cross-section data. In three empirical replication studies their underlying exclusion restrictions are shown to be most doubtful. Next, incredible (weak-instrument robust) TSLS inference is replaced by more reliable remarkably narrow instrument-free asymptotically conservative confidence intervals.
JEL Classification:C12, C13, C21, C22, C26
Keywords:endogeneity robust least-squares inference, new exclusion restrictions test, replication studies, sensitivity analysis of two-stage least-squares
Download: PDF (739 KB)Login
(for staff & registered students)
BER Weekly
19 Apr 2024There was good news for global growth this week – with China's Q1 GDP beating expectations (see international section) and the IMF lifting its global growth forecast for 2024 once more. SA economic data releases, however, were mixed, with a welcome downtick in CPI inflation but relatively poor internal trade data. Most of the world’s economic policymakers...
Read the full issue
BER Weekly
19 Apr 2024There was good news for global growth this week – with China's Q1 GDP beating expectations (see international section) and the IMF lifting its global growth forecast for 2024 once more. SA economic data releases, however, were mixed, with a welcome downtick in CPI inflation but relatively poor internal trade data. Most of the world’s economic policymakers...
Read the full issue