Describe › Standalone plots

P-P normal plot

A P-P plot draws the empirical CDF against the theoretical Normal(μ̂, σ̂) CDF, so points on the y = x line indicate a normal fit.

What is P-P normal plot?

P-P plots map empirical to theoretical *probabilities* — both axes are bounded [0, 1]. Q-Q plots map empirical to theoretical *quantiles* — both axes are on the data's units. The two plots show essentially the same departure from Normal but with different sensitivity profiles.

P-P is more sensitive in the centre of the distribution (where most of the probability mass is); Q-Q is more sensitive in the tails. Both have a y = x reference line for visual checking.

When should I use P-P normal plot?

Visual normality check, alternative to or complement of Q-Q.
When you care specifically about distribution centre vs tail behaviour.

What data does it need?

One numeric column.

What does it report?

ECharts scatter (theoretical Φ vs empirical CDF) with y = x reference.

How do I interpret the result?

S-shaped departure ⇒ tail-shape mismatch; arch ⇒ centre shift. Pair with a formal normality test (Shapiro-Wilk) for an objective verdict.