In research, we usually worry about endogeneity problem arising from reverse causality as it leads to biases in the estimates. So, researchers usually use the lag values of the endogenous covariate or use instruments to deal with the problem. However, these approaches are also not without próblems. So, why ís reverse causality as such a concern in research?
I know that if the reverse causality causes downward bias, that is a serious problem. My question is why do we worry about reverse causality when the bias is an upward bias as we can interpret the result simply as total effect?
I will answer my question as follows:
If we are sure that there is a first round effect, then reverse causality might not be a research concern if our goal is to estimate the total effect. However, there is no mechanism to check the presence or otherwise of a first round effect unless we control for the reverse causality. Hence, regardless of whether we want to estimate first round or total effect, we need to control for the reverse causality in our model
- Badges
- Science topic
- Similar topics
- Engineering
- Modeling