Pausanias Analysis

Connectedness feature reference

Maximum PageRank of a Large-Place Neighbor

The largest PageRank score found among the focal place's large operational neighbours.

Stored model field: large_place_max_pagerank

-0.131standardized coefficient
Does not survivecurrent direction
255observations summarized
Large-place connectionsfeature group

How It Is Calculated

For local neighbours that meet the large-place threshold, take the maximum weighted place-graph PageRank; use zero when none qualify.

What a higher value means

The focal place is connected to at least one more-central large place.

Important qualification. The score is relative to this release's graph and may be dominated by one neighbour.

Current Model Cohort

These descriptive statistics use the current labelled cohort after aliases have been collapsed to one row per MANTO place.

GroupN MinimumQ1 MedianMean Q3Maximum
All labelled places2550.0000.0000.0000.0020.0030.010
Survives2040.0000.0000.0000.0020.0020.010
Does not survive510.0000.0000.0000.0020.0030.010

Examples from the Current Data

Examples are descriptive checks on the calculated feature. Their outcome labels report what Pausanias says; they do not establish that the feature caused survival or abandonment.

Examples with high recorded values

PlaceMANTO ID ValuePausanias reports
🌍 Argos (city)82288530.010Survives
🌍 Brauron (Attica)113092680.010Survives
🌍 Chersonesos (Thrace)82544670.010Survives
🌍 Delphi (Phocis)82539720.010Survives
🌍 Elaia (Lydia)101494010.010Survives
🌍 Ephesos (Asia Minor)82540200.010Survives

Examples with low recorded values

PlaceMANTO ID ValuePausanias reports
🌍 Abia (Messenia)101135050.000Survives
🌍 Ace (Arcadia)102145170.000Survives
🌍 Acharnai (Attica)101530560.000Survives
🌍 Acriai (Laconia)101494180.000Survives
🌍 Aegina (Epidauria)113081850.000Survives
🌍 Agrai (Attica)101515480.000Survives

Interpretation in the Predictive Model

Its current standardized coefficient is -0.131, pointing toward does not survive. This means that a one-standard-deviation increase changes the fitted log odds in that direction while the other included features are held fixed.

Because the connectedness features are correlated and the model's out-of-fold performance is weak, this is a conditional associationβ€”not a standalone ranking, causal effect, or historical explanation.

Related Features

Data Scope

Return to all 41 features Β· Return to the predictive model