Explanation

All three statements are correct:

Statement I: Homoskedasticity means that the variance of the error terms is constant for all independent variables. This is the definition of homoskedasticity in regression analysis.

Statement II: Heteroskedasticity means that the variance of error terms varies over the sample. This is the opposite of homoskedasticity, where the variance of residuals is not constant across observations.

Statement III: The presence of conditional heteroskedasticity leads to biased standard error estimates. This is a critical issue because:

• It introduces bias into the estimators of the standard error of regression coefficients
• It typically understates the standard errors
• This can lead to incorrect inference about the statistical significance of coefficients

When the variance of residuals is constant across all observations, the regression is homoskedastic. When it varies, the regression exhibits heteroskedasticity. Conditional heteroskedasticity (where variance depends on the values of independent variables) is particularly problematic as it violates the assumptions of ordinary least squares regression, making standard error estimates unreliable.