I am excited to share my first working paper! @PHuenermund and I address why the interpretation of control variables in regression analysis should be avoided.
“On the Nuisance of Control variables in Regression Analysis”
arxiv.org/abs/2005.10314
#econometrics #causalinference /1
“On the Nuisance of Control variables in Regression Analysis”
arxiv.org/abs/2005.10314
#econometrics #causalinference /1
2/The interpretation of control variables is widespread within our research field. We checked the last five years of SMJ issues and found that 47% of papers that use parametric regression models with control variables also interpret or mention the results of their controls.
3/ We argue that this practice should be avoided because control variable estimates are unlikely to have causal interpretation themselves.
4/ In order to get accurate estimates for control variables in regression analysis, all confounding factors that are themselves direct influence factors of the outcome needs to be accounted for.
5/ Since this is rarely the case, control variable estimates are likely to be biased because the estimates capture the spurious relationships it shares with other confounding factors that also influence the outcome. Its interpretation thus leads to misleading conclusions.
6/ So while control variables are important for identification, we recommend to not report them in the paper (or relegate them to the appendix at least).
