Correlation in Bernoulli trial

148 Views Asked by At

I have a large dataset of tennis-points (who served and if they won etc).

Now I would like to check if the points have any correlation with each other (does winning/losing the previous point affect the current or the one after this?).

I also have an "estimate" of each players serve-winning probability as well as his "actual" serve-winning probability in the game (calculated from the dataset).

Ive tried looking into autocorrelation but I honestly dont know where to start. Does anyone have any idea how to test if Point X have any effect on the outcome of Point X+1?

Any help is greatly appreciated

PS. I tried asking a similar question describing how I thought and the only answer I get was "You are lacking fundamental understanding about probability-theory", hence this time I havent included any of my own thought-process, but feel free to ask for more info if I have excluded something important DS.