Academic Integrity: tutoring, explanations, and feedback — we don’t complete graded work or submit on a student’s behalf.

The researcher suspects that the original regression errors might exhibit ARCH-t

ID: 3270024 • Letter: T

Question

The researcher suspects that the original regression errors might exhibit ARCH-type heteroskedasticity thus she runs the regression below, where the variable RESID contains the residuals from the regression above, the variable RESID^2 contains the squared residuals, and the variable RESID^(-1) contains the squared residuals at time t-1. Use these results to test for heteroskedasticity, stating very clearly the null and alternative hypotheses for your test, the auxiliary regression, the test statistic and its distribution under the null.

Explanation / Answer

ho: the assumption of homogenity of variance is valid

h1: the assumption of homogenity of variance is NOT valid

with F = 22.8 and p-value < .05 i reject ho and conclude that the assumption of homogenity of variance is NOT valid