Heteroskedasticity Quiz

What is the consequence of heteroscedasticity in regression analysis?

• Coefficient estimates become biased

• Standard errors are correctly estimated

• Standard errors are biased, leading to incorrect inference

• R-squared value is unaffected

In a residual plot, heteroscedasticity is indicated when:

• Residuals are randomly scattered around zero

• Residuals form a pattern such as a funnel or cone

• Residuals are clustered near the origin

• Residuals follow a straight line

What is the main assumption violated when heteroscedasticity is present in a regression model?

• Linearity

• Independence

• Homoscedasticity

• Normality

In which of the following cases is heteroscedasticity likely?

• Salaries across different levels of education

• Annual temperature measurements in a city

• House prices in different neighborhoods

• Number of books read by children in a class

In which of the following cases is heteroscedasticity likely?

• Monthly electricity consumption in similar-sized apartments

• Income levels among employees in a large corporation with various job positions

• Daily temperature fluctuations in a controlled laboratory environment

• Heights of children in a single classroom

In which of the following cases is homoscedasticity likely?

• The residuals show constant variance across all levels of the independent variable

• The residuals increase in variance as the value of the independent variable increases

• The residuals decrease in variance as the value of the independent variable increases

• The residuals have a random, non-constant variance pattern across levels of the independent variable

In which of the following cases is heteroscedasticity likely?

• Scores on a standardized test for students from a single school

• Weekly sales of a single product in a small, local store

• Travel expenses of business professionals with varying roles and travel frequencies

• Number of hours worked by employees in a department with a fixed schedule

Which of the following methods can be used to correct for heteroscedasticity?

• Using dummy variables

• Applying logarithmic transformation

• Increasing the sample size

• Adding more predictor variables