Question

Discuss how each of the following concerns may affect the results from a regression:

a) Omitted variable bias

b) Simultaneous causality bias

c) Measurement error in the independent variable

d) Measurement error in the dependent variable

Answer 1

(a) Omitted Variable Bias (OVB) occurs when the regression model leaves out one or more relevant variables. The bias results in the model attributing the effect of the missing variables to the estimated effects of the included variables.

(b) Simultaneously causality bias occurs when the explanatory variable is jointly determined with the dependent variable. It is a term for the unexpected results that happen when the explanatory variable is correlated with the error term $\varepsilon$ , called the residual disturbance term because of simultaneity.

(c) Measurement error in the independent variable occurs if we observe X* = X + $\delta$ instead of just X. The measurement error in an independent variable will tend to bias its estimated slope coefficient towards zero in Ordinary Least Square (OLS).

(d) Measurement error in the dependent variable occurs if we observe values y_i^* that are produced as:

$y^{*}_{i}=y_{i}+\delta _{i}$ ,

where $\delta _{i}$ is the measurement error for case i, and y_i is the true value of the dependent variable for this case.The effect of measurement error in the dependent variable is to increase the unexplainable part of the regression.