Data Visualization MCQs

Human color discrimination and legend lookup are limited.
Faceting, filtering, or highlighting selected groups may communicate more clearly.

Power equals one minus the Type II error probability for a specified effect.
Higher power makes meaningful effects more likely to be detected.

Adding clusters always reduces within-cluster variation.
The elbow is a point beyond which additional clusters offer diminishing improvement.

A Q-Q plot pairs empirical quantiles with theoretical quantiles.
Agreement near a line supports the proposed distributional form.

Standard symmetric kernels place mass on both sides of an observation.
Near zero or another boundary, this can assign density to impossible values.

Positive covariance indicates that variables tend to move together, while negative covariance indicates opposite movement.
Its magnitude depends on the variables' measurement units.

A correlation matrix summarizes linear associations for all variable pairs.
It is often visualized as a colored correlogram.

More observations reduce standard errors and improve signal detection.
Power also increases with larger effects and lower variability.

Silhouette compares within-cluster cohesion with nearest-cluster separation.
Higher values generally indicate clearer cluster structure.

Nonlinear patterns indicate differences in skewness or tail behavior.
Random small deviations are expected, but systematic curvature is diagnostic.

Log transformation moves a positive boundary to an unbounded scale, while specialized kernels correct leakage.
The choice should preserve a meaningful interpretation.

Covariance is positive when paired deviations from their means are usually of the same sign.
It indicates direction of linear co-movement, not causation.