Computational Genomics Group
  • Home
  • Research
  • Publications
  • Teaching
  • Blog
  • Group Members
  • News
  • Computational Biology Book
  • Data Analysis with R Book
  • CG2 github
  • Fiction

A first take on Footballomics: Analysis of footbal data

3/30/2017

0 Comments

 
What we are doing

Being in science combines a number of rewarding activities that make the daily working routine fulfilling in many ways. You get to learn new things everyday, you (sometimes) even understand how things work (or even better how nature works) and you get to interact, through teaching, with young people that are full of contagious optimism and aspiration. Last but not least, you have the freedom to make your own working schedule and, more often than in other jobs, find time to apply what you learn in things you were always curious about.

Footballomics: Take #1

And I am, I ’ve always been, curious (nay! crazy) about football in all aspects of it. Playing, whatching, talking, thinking and dreaming about it. Over the years, job, family and age have caught up with me and thus I have now grown a more mature way of appreciating the “beautiful game”, from worshiping players to admiring managers and from chanting on the stands to reading about football tactics. My professional involvement to data analysis and statistics, has also lead to my developing of a more “quantitative” approach about football and thus I have always wanted to try to use some of the simple (or not simple) principles of my everyday work routine, which includes making sense of data for biological problems to more “mundane” questions regarding football. In this, my first ever, attempt to analyze football data, I took the opportunity (OK, I took advantage) of teaching a (hopefully) interesting graduate class on “R for Bioinformatics” at the University of Crete, Medical School. After having introduced the basic concepts of R to the students I thought of giving them an example of how we can use it to attack simple questions based on data. And since they are (or will soon be) fed up with biological problems I thought of giving them a different kind of a puzzle,which brings us to:

The Question: Are Liverpool performing significantly better with top-flight teams than with bottom-table “minnows”?

Being a big (OK, huge) fan of Liverpool Football Club in the post-90s era can be exhilarating and frustrating at the same time. You get to experience glorious moments like the Miracle in Instabul or last year’s come-back against Borussia Dortmund, but you also get to see them miss on league after league campaigns by unexpected losses to “lesser” teams like Crystal Palace in 2014. This year in particular, this trend of being imperious in big games, only to lose nerve against teams like Burnley, Bournemouth or Swansea has been more apparent than ever. Liverpool are doing very well when playing big opponents that are title challengers and somehow sink when they find themselves against tough-to-crack defenses. I am, of course, not the first to address this issue, brought up by former managers and former players turned football pundits. The question, though, when it comes to punchlines such as “Liverpool sink against lesser sides” is how well they are founded on real data and this is exactly the question I posed to my (patient) students. What they had to do was to test whether Liverpool indeed performed worse than expected against teams at the end of the table, the word “expected” being the key.

If you are ready for a long read on football, data mining and some medium level R code you can see the rest of the details here
0 Comments



Leave a Reply.

    RSS Feed

    It's all about...

    Bioinformatics and computational biology with a focus on chromatin and genome architecture, plus a little bit of football and occasional aspects of  University education.

    Archives

    April 2021
    December 2020
    March 2020
    November 2018
    September 2017
    April 2017
    March 2017
    December 2016
    November 2016
    February 2016
    May 2015
    November 2014
    September 2014
    July 2014
    February 2014
    November 2013
    October 2013

    Categories

    All
    Academic Life
    Bioinformatics
    ChIPSeq
    ChIPSeq Bias
    Cpg Islands
    Data Analysis
    Exons
    Football
    Footballomics
    Gene Regulation
    Genetic Diseases
    Genome Architecture
    Genome Structure
    Inflammation
    Journalism
    Math Illiteracy
    NGS
    Nucleosome Positioning
    Nucleotide Composition
    Nucleotide Skews
    Promoters
    R
    Splicing
    Statistics
    Systems Biology
    Tnf
    Transcriptome
    Variation
    Whole Exome

Powered by Create your own unique website with customizable templates.