Accéder au contenu principal

Win Probability Over Time (Continued)


Allright, I will continue to show and explain what I found while toying with the data.

A)  Trailing by 2

 
So now, we’ll continue our journey. 

 
The graph is really interesting. Despite no strong correlation, we can see that there are two sorts of sub-graphs. After the thirtieth minute, winning chances drop significantly from 21,05% to 7,69%. Then we see that the data are close. We have a R² of 0.71 for [35-90] minutes. The first 30 minutes are more interesting. Even if the number of events is low, because it’s not usual to concede 2 goals quickly in the game we can still draw some conclusions from this.
We have an odd phenomenon around the twentieth minute, with winning chances increasing then dropping.  As previously observed, the winning chance increases after the twentieth minute so the manager effect hypothesis is starting to seem likely.


B)  Trailing by 3


Not much to say here, as there is so few teams that came back from such a scenario. 

 
It’s hard to develop a model for this situation without overstating winning chances.


C)   Trailing by 4


Same story as before, not much to analyze.

 
There are no data for earlier than the thirtieth minute, because teams are not bad and don’t let opponents score too easily. Of the ten times a team was trailing by 4, only one achieved to tie the game.  


D)  Trailing by 5 and 6


No need to put the graphs here, as the Win% is 0% whatever how much is left. One could say that a 4 goal lead when away is 100% sure to yield the three points.

Commentaires

Enregistrer un commentaire

Posts les plus consultés de ce blog

Goals created and Wins created

Like many others, I have the MCFC data set. I used it to toy with data and created two new statistics. In fact three, I'll explain later. The main thing I tried to do is to assess the impact of a player on the season in terms of scoring opportunities and wins. So first of all, I did some computation, and selected the data I needed:  - Appearances  - Assists  - Big Chances  - Goals  - Key Passes  - Time Played  - Shots I have to say that I'm not too happy with the data set. Many events are not recorded with a name, so you have data that cannot be used when you look at player production. But I managed to do what I wanted with the data. All data are from the MCFC data set, I rely on them for accuracy. First thing I looked at: topscorers. Rank Player full name Goals 1 Robin van Persie 30 2 Wayne Rooney 27 3 Sergio Agüero 23 4 Clint
Enregistrer un commentaire
Lire la suite
Win Probability Over Time It is often said that in football a two-goal lead will always yield a victory. But is that really true, and if yes to what extent? Well, this is the aim of my study, thanks to seven seasons of data. What we will basically do is analyze every possible situation, from trailing by 6 to leading by 6. Of course the timing will play a huge role. Because my data set is relatively small, I decided to regroup every result in 5 minutes brackets. Then this will give us the possibility to know the value of a goal in terms of winning chance. Of course in football there is the possibility of a draw so I will have two curves for each game situation. The first one with winning and draw percentage and the second with the simple formula: This will give us a good idea on a team chance of securing the three points. So with this second graph, a basic trend curve will allow us to calculate the Winning% at every point
Enregistrer un commentaire
Lire la suite

One-goal and two-goals lead analysis

Continuing on my football resultss analysis, I want to analyze 1-goal and 2-goals lead. The main question is : does every score yields the same winning chance? Of course we keep scores with the same differential, for example home team is one goal up. So I ploted on the same graph the Win% for 1-0, 2-1 and 3-2. First thing you will see in the graph below is that 2-1 data starts at the 15th minute and the 3-2 data starts at the 45th minute. All data points are regrouped in 5-minutes window to correct for the sample size. What you see is that basically, Win% increases over time. But something more interesting is the trend. It seems that when the score is 2-1, the home team has less of winning (or to draw, as I count a draw as half a win). The difference is slighlty over 5%. When the score is 3-2, the curve is also below the 1-0 curve for most points. When building nice fitting curve for 1-0 and 2-1, the trebd is clearer. Even if the effect is not huge, it is interesting to no
Enregistrer un commentaire
Lire la suite