* Measurement Bias in OLS Regression * * Keywords: * regression, ols, measurement, error, bias * * Description: * We illustrate how to estimate a Linear OLS Model and show how * Measurement Errors create Biases in estimates * * Author(s): * Skif Pankov * * Source: * Damodar N. Gujarati and Dawn C. Porter, Basic Econometrics - 5th Edition * McGraw-Hill International Edition, Chapter 13, Example 13.2 (page 485) * sample 1 10 * Reading the datafile and naming variables read(data_13.2.shd) yt xt y x * Running an OLS regression of the "true" value of Y (yt) on the "true" * value of X (xt) ols yt xt * Running an OLS regression of the observed value of Y (y) on the "true" * value of X (xt) ols y xt * Running an OLS regression of the "true" value of Y (yt) on the "observed" * value of X (x) - this regression will produced biased estimates in * comparison with the previous two regressions ols yt x stop * Note: * the estimates of coefficients in the last regression will differ from * those in the book - it is likely that authors used different data