Endogeneity Issues
There is a concern that the variable representing relinquished exchanges, EXRELQ,
is not exogenous with respect to selling price. For example, an omitted factor such as
extreme price appreciation, which is correlated with both the probability for a sale to be
part of a relinquished exchange as well as selling price, could cause a significant
relationship between the variable representing that the sale is part of a relinquished
exchange and the selling price. To address these concerns, I perform a Durbin-Wu-
Hausman (DWH) test for endogeneity. I estimate the base OLS Model II using two-stage
least squares regressions, where EXRELQ is an endogenous variable. The DWH test first
estimates the endogenous variable as a function of all exogenous variables. In the second
stage it regresses the dependent variable (in this case, natural log of price) on all variables
and includes the residuals of the endogenous variable. The second stage coefficient
estimates, when performing this procedure, are not different from the coefficients
estimated in the original model. Also the DWH test shows that there is no severe bias in
the OLS model estimates. Therefore, the results from the OLS model appear to be robust
to endogeneity concerns.