A regression model produces residuals that exhibit a funnel shape when plotted against fitted values. Which diagnostic does this indicate and what remediation is recommended?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Here's the deal — b is correct because a funnel-shaped residual plot (variance increasing with fitted values) is the hallmark of heteroscedasticity. Remediation includes log or Box-Cox transformation of the target, or weighted least squares where weights are inversely proportional to variance.
Full explanation below image
Full Explanation
B is correct because a funnel-shaped residual plot (variance increasing with fitted values) is the hallmark of heteroscedasticity. Remediation includes log or Box-Cox transformation of the target, or weighted least squares where weights are inversely proportional to variance. A (multicollinearity) presents as inflated standard errors, not funnel residuals. C (autocorrelation) appears as patterns in residuals ordered by time, not by fitted values. D (high leverage) identifies individual influential points, not a systematic variance pattern.