6533b85efe1ef96bd12bfccd

RESEARCH PRODUCT

BALANCED VARIABLE ADDITION IN LINEAR MODELS

Jan R. MagnusFranco PeracchiGiuseppe De Luca

subject

Economics and EconometricsBias amplificationMean squared errorOmitted variable05 social sciencesLinear modelEstimatorSettore SECS-P/05 - EconometriaProxy variableProxy variablesInconsistencyRegressionVariable (computer science)0502 economics and businessLeast-squares estimatorsEconometricsEconomicsMean squared errorLeast-squares estimatorOmitted variables050207 economics050205 econometrics

description

This paper studies what happens when we move from a short regression to a long regression in a setting where both regressions are subject to misspecification. In this setup, the least-squares estimator in the long regression may have larger inconsistency than the least-squares estimator in the short regression. We provide a simple interpretation for the comparison of the inconsistencies and study under which conditions the additional regressors in the long regression represent a “balanced addition” to the short regression.

yearjournalcountryeditionlanguage
2018-09-01
10.1111/joes.12245https://research.vu.nl/en/publications/a5ef450d-97b7-4f57-8ad5-a27b4c38ed6b