Heteroscedasticity of residuals in regression suggests that there is:
A)nonconstant variation in the errors.
B)multicollinearity among the predictors.
C)non-normality in the errors.
D)lack of independence in successive errors.

Question

Quizplus · Accepted Answer

Heteroscedasticity of residuals in regression indicates that the variance of the errors is not constant across all levels of the independent variable(s), which violates one of the assumptions of regression. Therefore, option A is the correct choice. Multicollinearity (option B) pertains to the issue of high correlation between independent variables, while non-normality (option C) reflects the distribution of residuals that may not approximate a normal distribution. Lack of independence (option D) would suggest a pattern in the residuals that may lead to biased and inefficient estimates.

Heteroscedasticity of Residuals in Regression Suggests That There Is