fairly_random

Data and code for Fairly Random: The Effect of Winning the Toss on Winning the Match. Journal of Sports Analytics. 2023.

https://github.com/outside-edge/fairly_random

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (5.3%) to scientific vocabulary

Keywords

cricket natural-experiments toss
Last synced: 6 months ago · JSON representation ·

Repository

Data and code for Fairly Random: The Effect of Winning the Toss on Winning the Match. Journal of Sports Analytics. 2023.

Basic Info
  • Host: GitHub
  • Owner: outside-edge
  • Language: TeX
  • Default Branch: master
  • Homepage:
  • Size: 32.8 MB
Statistics
  • Stars: 1
  • Watchers: 2
  • Forks: 0
  • Open Issues: 0
  • Releases: 1
Topics
cricket natural-experiments toss
Created over 10 years ago · Last pushed over 2 years ago
Metadata Files
Readme Citation

README.md

Fairly Random: The Effect of Winning the Toss on Winning the Match

We analyze data from over 35,000 first-class men's cricket matches played over the course of more than one hundred fifty years---a near census of the relevant population---to estimate the effect of winning the toss on winning the match. We estimate the average effect of winning the toss on winning the match to be 1.8 percentage points: toss winners win 39.2% of the time and lose 37.4% of the time, with the remaining being drawn (mainly due test and first-class cricket). The effect of winning the toss is largest in tests, where it is 4.9 percentage points, and is lowest in ODIs and T20s, where it is essentially zero. That being said, in ODIs and T20s that are day/night matches, the effect of winning the toss is 3.3 percentage points, whereas in day-time matches the effect is a precise zero.

Scripts

  1. Helper Functions The file contains some helper functions that are sourced in the analysis script.

  2. Data preparation. Reads in data/rankings_odi.csv, data/rankings_test.csv and data/grounds.csv and produces data/regression_sample.rds

  3. Analysis Reads in data/regression_sample.rds and produces materials in the output folder.

  4. We explain the issues around using toss as IV at length in the manuscript. And that is why none of the analyses make it to the ms. But if you want to see how IV analysis would run, check out scripts/03_iv.R which produces materials in output/iv/ folder.

Manuscript

Authors

Apoorva Lal, Derek Willis, Gaurav Sood, and Avidit Acharya

Owner

  • Name: Outside Edge
  • Login: outside-edge
  • Kind: organization

Citation (citation.cff)

cff-version: 1.2.0
message: "Please cite it as below."
authors:
- family-names: "Lal"
  given-names: "Apoorva"
- family-names: "Willis"
  given-names: "Derek"
- family-names: "Sood"
  given-names: "Gaurav"
- family-names: "Acharya"
  given-names: "Avidit"
title: "Fairly Random: The Effect of Winning the Toss on Winning the Match"
version: 1.0.0
doi: 10.5281/zenodo.1234
date-released: 2023-10-23
url: "https://github.com/outside-edge/fairly_random"
year: 2023
journal: "Journal of Sports Analytics"

GitHub Events

Total
Last Year