# ESPN Prediction Performance for the NFL

[This article was first published on

Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.

**Graph of the Week**, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here)Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.

**Description**:

ESPN ‘experts’ predict the National Football League wins/losses each week. The above chart shows the percentage of their correct guesses and an overall trend, week by week.

**Data**:

http://espn.go.com/nfl/picks

**Analysis:**

The graph shows an interesting trend: the ‘experts’ get worse as the season progresses. More data would be accumulated each week, giving better indicators as to a team’s performance which should result in better predictions. However, this is not the case except for the “Pick ’em” predictions which started worse but trended upwards as the season progressed. In the game of American football, there are a great many variables involved in the outcome of a game, which would contribute to its unpredictability. Perhaps this explains the above phenomenon.

People watch the games for entertainment. If you knew beforehand who was going to win, then why watch the game? In fact, that is exactly the

*point*of watching a game – because you

*don’t*know the outcome. Therefore, it is baffling why so many sports networks insist on predicting games – if they ended up correct 100% of the time, nobody would bother to watch, thus shutting down the sports networks!

**Questions:**

- Why the experts unable to perform better as the season progressed?
- Would you trust the experts opinion over your own if money was involved?
- What are the main variables which determine the outcome of a game?

To

**leave a comment**for the author, please follow the link and comment on their blog:**Graph of the Week**.R-bloggers.com offers

**daily e-mail updates**about R news and tutorials about learning R and many other topics. Click here if you're looking to post or find an R/data-science job.

Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.