diving: Olympic Diving Data
In shabbychef/ohenery: Modeling of Ordinal Random Variables via Softmax Regression

diving

R Documentation

Olympic Diving Data

Description

One hundred years of Men's Olympic Platform Diving records.

Usage

data(diving)

Format

A data.frame object with 695 observations and 13 columns.

The columns are defined as follows:

Name: The participant's name.
Age: The age of the participant at the time of the Olympics. Some values missing.
Height: The height of the participant at the time of the Olympics, in centimeters. Many values missing.
Weight: The height of the participant at the time of the Olympics, in kilograms. Many values missing.
Team: The string name of the team (country) which the participant represented.
NOC: The string name of the National Olympic Committee which the participant represented. This is a three character code.
Games: The string name of the Olympic games, including a year.
Year: The integer year of the Olympics. These range from 1906 through 2016.
City: The string name of the host city.
Medal: A string of “Gold”, “Silver”, “Bronze” or NA.
EventId: A unique integer ID for each Olympics.
AthleteId: A unique integer ID for each participant.
HOST_NOC: The string name of the National Olympic Committee of the nation hosting the Olympics. This is a three character code.

Note

The author makes no guarantees regarding correctness of this data.

Please attribute this data to the upstream harvester.

Author(s)

Steven E. Pav shabbychef@gmail.com

Source

Data were collected by Randi Griffin from the website “sports-reference.com”, and staged on Kaggle at https://www.kaggle.com/heesoo37/120-years-of-olympic-history-athletes-and-results.

Examples


library(dplyr)
library(forcats)
data(diving)

fitdat <- diving %>%
  mutate(Finish=case_when(grepl('Gold',Medal)   ~ 1,
                          grepl('Silver',Medal) ~ 2,
                          grepl('Bronze',Medal) ~ 3,
                          TRUE ~ 4)) %>%
  mutate(weight=ifelse(Finish <= 3,1,0)) %>%
  mutate(cut_age=cut(coalesce(Age,22.0),c(12,19.5,21.5,22.5,25.5,99),include.lowest=TRUE)) %>%
  mutate(country=forcats::fct_relevel(forcats::fct_lump(factor(NOC),n=5),'Other')) %>%
  mutate(home_advantage=NOC==HOST_NOC)

hensm(Finish ~ cut_age + country + home_advantage,data=fitdat,weights=weight,group=EventId,ngamma=3)

shabbychef/ohenery documentation built on Oct. 19, 2023, 12:08 p.m.