Analysis Flashcards
7 cards from real Data Science practice questions. Tap to flip, then mark Knew It or Still Learning — missed cards come back until you master them.
Read the first 7 Analysis flashcards as text
In a simple linear regression, the R-squared value represents:
Answer: The proportion of variance in the target explained by the model
R-squared measures how much of the target's variability the model accounts for.
A residual plot showing a clear curved pattern suggests:
Answer: The linear model may be misspecified
Structure in residuals indicates the linear form fails to capture the true relationship.
Which metric is most appropriate for evaluating a regression model's prediction error?
Answer: Root mean squared error (RMSE)
RMSE measures average prediction error magnitude for continuous targets.
On an imbalanced classification dataset, why can accuracy be misleading?
Answer: A model predicting the majority class can score high while ignoring the minority
With skewed classes, always predicting the common class yields high accuracy but poor minority detection.
What does precision measure in a classification model?
Answer: The fraction of predicted positives that are actually positive
Precision is true positives divided by all predicted positives.
An AUC-ROC value of 0.5 indicates a classifier that:
Answer: Performs no better than random guessing
An AUC of 0.5 means the model cannot distinguish classes better than chance.
Overfitting is best described as a model that:
Answer: Performs well on training data but poorly on unseen data
An overfit model memorizes training noise and fails to generalize to new data.