CramX Logo

Q
QuestionStatistics

"SSE can never be A. larger than SST B. smaller than SST C. equal to 1 D. equal to zero"
12 months agoReport content

Answer

Full Solution Locked

Sign in to view the complete step-by-step solution and unlock all study resources.

Step 1:
Let me solve this step by step, focusing on the statistical concept of Sum of Squared Errors (SSE) and Total Sum of Squares (SST).

Step 2:
: Understanding SSE and SST

- SSE (Sum of Squared Errors) measures the total deviation of predicted values from actual observed values - SST (Total Sum of Squares) measures the total variance in the dependent variable

Step 3:
: Recall the Relationship Between SSE and SST

The fundamental relationship is: $$R^{2} = 1 - \frac{SSE}{SST}

Step 4:
: Analyzing the Possible Scenarios

- By definition, $$0 \leq \frac{SSE}{SST} \leq 1
- SSE represents the unexplained variation - SST represents the total variation

Step 5:
: Evaluating Each Option

A. SSE larger than SST: IMPOSSIBLE B. SSE smaller than SST: POSSIBLE C. SSE/SST equal to 1: IMPOSSIBLE D. SSE equal to zero: POSSIBLE (perfect model prediction)

Final Answer

SSE can NEVER be larger than SST. The key insight is that SSE represents a portion of the total variation (SST), so it cannot exceed the total variation.