Percentile scoring for teams. #21

New Issue

2025-04-28T17:32:29-04:00

Cutieguwu commented

2025-04-28 17:32:29 -04:00

(Migrated from github.com)

Given some kind of scoring calculation, calculate a percentile for each team as part of their ranking statistics.

This percentile could be applied to:

the team's overall score
avg. score each game
avg. plays per game
frequency of running a given action (in relation to other team's utilization of that action)
avg. terrain gain, loss, and delta
and much more

This percentile ranking could be extended to providing Box and Whisker Plots to demonstrate the data.

Formulae for reference:

v = value
p = percentile
R = percentile rank
n = population size
E = # of instances of value in population
L = # of instances < value in population

Q_1 = First Quartile
Q_2 = Second Quartile
Q_3 = Third Quartile
IQR = Interquartile Range
SIQR = Semi-Interquartile Range

p = 100[ (L + 0.5E) / n ]
R = (p / 100)(n + 1)

Q_1 = median of lower half of n
Q_2 = median of n
Q_3 = median of upper half of n

IQR = Q_3 - Q_1
SIQR = IQR / 2

Outliers Under:
any data < Q_1 - 1.5IQR

Outliers Over:
any data > Q_3 + 1.5IQR

Given some kind of scoring calculation, calculate a percentile for each team as part of their ranking statistics. This percentile could be applied to: - the team's overall score - avg. score each game - avg. plays per game - frequency of running a given action (in relation to other team's utilization of that action) - avg. terrain gain, loss, and delta - and much more This percentile ranking could be extended to providing Box and Whisker Plots to demonstrate the data. Formulae for reference: v = value p = percentile R = percentile rank n = population size E = # of instances of value in population L = # of instances < value in population Q_1 = First Quartile Q_2 = Second Quartile Q_3 = Third Quartile IQR = Interquartile Range SIQR = Semi-Interquartile Range p = 100[ (L + 0.5E) / n ] R = (p / 100)(n + 1) Q_1 = median of lower half of n Q_2 = median of n Q_3 = median of upper half of n IQR = Q_3 - Q_1 SIQR = IQR / 2 Outliers Under: any data < Q_1 - 1.5IQR Outliers Over: any data > Q_3 + 1.5IQR

This repo is archived. You cannot comment on issues.

1 Participants

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: Cutieguwu/miller#21