Skip to main content
light editing & formatting
Source Link
gung - Reinstate Monica
  • 147.5k
  • 89
  • 406
  • 717

Let me use an example:

Say you want to quantify the (causal) effect of education on income. You You take education years and income data and regress one against the other. Did Did you recover what you wanted? Probably not! This This is because the income is also caused by things other than education, but which are correlated to education. Let's Let's call them "skill": We can safely assume that education years are affected by "skill", as the more skilled you are, the easier it is to gain education. So So, if you regress education years on income, the estimator for the education effect absorbs the effect of "skill" and you get an overly optimistic estimate of return to education. This is to say, education's effect on income is (upward) biased because education is not exogenous to income.

EndogeintyEndogeneity is only a problem if you want to recover causal effects (unlike mere correlations). Also Also- if you can design an experiment, you can guarantee that $Cov(X,\epsilon)=0$${\rm Cov}(X,\epsilon)=0$ by random assignment. Sadly, this is typically impossible in social sciences.

Let me use an example:

Say you want to quantify the (causal) effect of education on income. You take education years and income data and regress one against the other. Did you recover what you wanted? Probably not! This is because the income is also caused by things other than education, but which are correlated to education. Let's call them "skill": We can safely assume that education years are affected by "skill", as the more skilled you are, the easier it is to gain education. So, if you regress education years on income, the estimator for the education effect absorbs the effect of "skill" and you get an overly optimistic estimate of return to education. This is to say, education's effect on income is (upward) biased because education is not exogenous to income.

Endogeinty is only a problem if you want to recover causal effects (unlike mere correlations). Also- if you can design an experiment, you can guarantee that $Cov(X,\epsilon)=0$ by random assignment. Sadly, this is typically impossible in social sciences.

Let me use an example:

Say you want to quantify the (causal) effect of education on income. You take education years and income data and regress one against the other. Did you recover what you wanted? Probably not! This is because the income is also caused by things other than education, but which are correlated to education. Let's call them "skill": We can safely assume that education years are affected by "skill", as the more skilled you are, the easier it is to gain education. So, if you regress education years on income, the estimator for the education effect absorbs the effect of "skill" and you get an overly optimistic estimate of return to education. This is to say, education's effect on income is (upward) biased because education is not exogenous to income.

Endogeneity is only a problem if you want to recover causal effects (unlike mere correlations). Also- if you can design an experiment, you can guarantee that ${\rm Cov}(X,\epsilon)=0$ by random assignment. Sadly, this is typically impossible in social sciences.

Let me use an example:

Say you want to quantify the (causal) effect of education on income. You take education years and income data and regress one against the other. Did you recover what you wanted? Probably not! This is because the income is also caused by things other than education, but which are correlated to education. Let's call them "skill": We can safely assume that education years are affected by "skill", as the more skilled you are, the easier it is to gain education. So, if you regress education years on income, the estimator for the education effect absorbs the effect of "skill" and you get an overly optimistic estimate of return to education. This is to say, education's effect on income is (upward) biased because education is not exogenous to income.

You willEndogeinty is only have endogeintya problem if you want to recover causal effects (unlike mere correlations). Also- if you can design an experiment, you can guarantee that $Cov(X,\epsilon)=0$ by random assignment. Sadly, this is typically impossible in social sciences.

Let me use an example:

Say you want to quantify the (causal) effect of education on income. You take education years and income data and regress one against the other. Did you recover what you wanted? Probably not! This is because the income is also caused by things other than education, but which are correlated to education. Let's call them "skill": We can safely assume that education years are affected by "skill", as the more skilled you are, the easier it is to gain education. So, if you regress education years on income, the estimator for the education effect absorbs the effect of "skill" and you get an overly optimistic estimate of return to education. This is to say, education's effect on income is (upward) biased because education is not exogenous to income.

You will only have endogeinty if you want to recover causal effects (unlike mere correlations). Also- if you can design an experiment, you can guarantee that $Cov(X,\epsilon)=0$ by random assignment. Sadly, this is typically impossible in social sciences.

Let me use an example:

Say you want to quantify the (causal) effect of education on income. You take education years and income data and regress one against the other. Did you recover what you wanted? Probably not! This is because the income is also caused by things other than education, but which are correlated to education. Let's call them "skill": We can safely assume that education years are affected by "skill", as the more skilled you are, the easier it is to gain education. So, if you regress education years on income, the estimator for the education effect absorbs the effect of "skill" and you get an overly optimistic estimate of return to education. This is to say, education's effect on income is (upward) biased because education is not exogenous to income.

Endogeinty is only a problem if you want to recover causal effects (unlike mere correlations). Also- if you can design an experiment, you can guarantee that $Cov(X,\epsilon)=0$ by random assignment. Sadly, this is typically impossible in social sciences.

Source Link
JohnRos
  • 5.8k
  • 35
  • 59

Let me use an example:

Say you want to quantify the (causal) effect of education on income. You take education years and income data and regress one against the other. Did you recover what you wanted? Probably not! This is because the income is also caused by things other than education, but which are correlated to education. Let's call them "skill": We can safely assume that education years are affected by "skill", as the more skilled you are, the easier it is to gain education. So, if you regress education years on income, the estimator for the education effect absorbs the effect of "skill" and you get an overly optimistic estimate of return to education. This is to say, education's effect on income is (upward) biased because education is not exogenous to income.

You will only have endogeinty if you want to recover causal effects (unlike mere correlations). Also- if you can design an experiment, you can guarantee that $Cov(X,\epsilon)=0$ by random assignment. Sadly, this is typically impossible in social sciences.