Heteroskedasticity

What are the possible consequences of heteroscedasticity for OLS estimator?

• It becomes inconsistent

• It becomes biased

• It becomes inefficient

• It becomes not linear

If you performed White's test and got the p-value of 0.02. At 5% significance level you would:

• reject the null hypothesis of heteroscedasticity

• reject the null hypothesis of homoscedasticity

• do not reject the null hypothesis of heteroscedasticity

• do not reject the null hypothesis of homoscedasticity

In the presence of heteroscedasticity if White's robust standard errors are used, usually

• Coefficients change, the standard errors are the same.

• Coefficients change, the standard errors become smaller.

• Coefficients do not change, standard errors become greater.

• Coefficients do not change, standard errors become smaller.

Heteroscedasticity is associated with:

• Time series data

• Cross-sectional data

• Panel Data

• Unbalanced Panel Data

A formula to compute White Test statistics is:

• N*R

• N*R²

• N*2R

• N*adjusted R²

White Test is used to detecting:

• Heteroscedasticity

• Autocorrelation

• Correlation

• Homoscedasticity

What is the tradeoff that a researcher faces when deciding how to deal with         heteroskedasticity?

• Goldfeld-Quandt overstates heteroskedasticity, but LM leads to more Type I errors.

• White’s robust estimator should be used for hypothesis testing, but GLS is better for interval estimation.

• GLS gives minimum variance, but results are more difficult to interpret.

• White’s robust estimator requires no assumptions about the structure of the variance, but it is not as efficient as GLS estimates when the right structure is imposed on the variance.

A linear probability model is likely to violate which assumption of MR most of the time?

• The values of each x_ik are not random and are not exact linear functions of the other                        explanatory variables.

If you run an LM test for heteroskedasiticity and reject the null hypothesis, what should you conclude?

• There is heteroskedasticity present, and it is correctly specified as tested.

• There is heteroskedasticity, but it is not linear in the explanatory variables.

• The original econometric model when estimated using the White correction technique

• The average from all the auxiliary regressions estimated with each explanatory variable as a function of the other explanatory variables

• The original econometric model before any test of heteroskedasticity has been performed

• The auxiliary regression of residuals as a function of the explanatory variables generating the heteroskedasticity