* Heteroskedasticity in the Monthly Credit Card Expenditure Model * * Keywords: * regression, ols, heteroskedasticity, credit card, expenditure, graph * * Description: * We illustrate how to estimate an OLS Model for Monthly Credit Card * Expenditure and, by plotting its estimated residuals, we show that * it's likely to suffer from Heteroskedasticity * * Author(s): * Noel Roy * Skif Pankov * * Source: * William H. Greene, Econometric Analysis - 7th Edition * Pearson International Edition, Chapter 9, Example 9.1 (page 309) * * Reading the datafile and retrieving names of the variables read (TableF9-1.shd) / names * Generating the square of the variable income genr income2=income**2 * Using only those observations for which avgexp is nonzero. * The skipif (expression) command will cause subsequent commands to skip * observations for which the value of the expression is positive or true set nowarnskip skipif (avgexp .eq. 0) * Running the OLS regression of avgexp on age, ownrent, income and income2 ?ols avgexp age ownrent income income2 / resid=u * Replicating figure 9.1 by plotting the residuals u against income. * The skipped observations have missing u, so turn off the warnings set nowarnmiss graph u income / nokey stop