[,1] [,2]
[1,] "Q" "R"
[2,] "0" "Ia"
Stochastic process where at each time the process is considered to be in one of n phases
Major aspect: probability of nth stage is solely dependent on (n-1)th stage

Probabilities of going from state i to state k represented by matrix

Markov chains are considered to be in the jth state, transitioning from the ith state at time n
Nth phase is computed by putting the initial transition matrix to the nth power

If a state can be re-entered again once it has left, it is called recurrent
If a state cannot be re-entered after having being left, it is considered transient
A state is absorbing if it can not travel to another state from itself

If a chain is recurrent completely, there are long-run averages (pi) representing the probability over the entire duration of the chain of transferring to state i

[,1] [,2]
[1,] "Q" "R"
[2,] "0" "Ia"
With t transient states and a absorbing states:
Q is a t * t matrix
0 is a a * t matrix
R is a t * a matrix
Ia is the identity matrix a * a
[,1] [,2]
[1,] "Q^n" "*"
[2,] "0" "Ia"
24 possible states per at bat: 8 arrangements of any player on base, 3 arrangement of outs (0,1,2) [being that a player cannot bat with 3 outs]
25th state: 3 outs, zero men left on base
26,27,28th state(s): 3 outs, 1:2:3 men left on base
Events Occurrences Probabilities
[1,] "Single" "355" "0.197"
[2,] "Walk/HBP" "228" "0.127"
[3,] "Single/Walk/HBP" "583" "0.324"
[4,] "Double" "117" "0.065"
[5,] "Triple" "14" "0.008"
[6,] "Home-Run" "23" "0.013"
[7,] "Single Out Plays" "1062" "0.59"
[8,] "Double Play" "26" "0.014"
Testing if this matrix helps predict individual statistics
Using the expected amount of runs from the total team from the model was 375, this matrix clearly over-predicts individual statistics.
Sacrifice bunt: a direct at bats where the batter attempts to bunt themselves out in order to move a base runner over to another base
Despite the fact that this may be helpful, it may also be detrimental to the inning as well by taking away one of your outs
Number.of.Outs.Base.Occuppied zero.out one.out two.out
[1,] "xxx" "0.784" "0.413" "0.145"
[2,] "1xx" "1.265" "0.736" "0.297"
[3,] "x2x" "1.48" "0.959" "0.471"
[4,] "xx3" "1.481" "0.959" "0.471"
[5,] "12x" "1.975" "1.294" "0.632"
[6,] "1x3" "1.984" "1.294" "0.632"
[7,] "x23" "2.196" "1.521" "0.806"
[8,] "123" "2.771" "1.94" "1.042"
League Bunt.Attempt.Prob No.Bunt.Attempt.Prob
[1,] "Wooster" "0.476" "0.37"
[2,] "MLB" "0.37" "0.348"
Situation Wooster MLB
[1,] "Man on First, No Outs" "0.558" "0.46"
[2,] "Man on First, 1 Out" "0.416" "0.335"
[3,] "Man on First, 2 Outs" "0.234" "0.182"
Situation Wooster MLB
[1,] "Man on First, No Outs" "0.486" "0.348"
[2,] "Man on First, 1 Out" "0.326" "0.224"
[3,] "Man on First, 2 Outs" "0.151" "0.102"
Situation Expected.Runs Prob.One.Run
[1,] "Man on First, No Outs" "0.7985" "0.5704"
[2,] "Man on First, One Out" "0.7265" "0.5211"
[3,] "Man on First, Two Outs" "0.6301" "0.4649"