Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Modeling Dynamic Incentivesan Application to Basketball Games
Arthur Charpentier1, Nathalie Colombier2 & Romuald Elie3
1UQAM 2Universite de Rennes 1 & CREM 3Universite Paris Est & CREST
http ://freakonometrics.hypotheses.org/
GERAD Seminar, June 2014
1
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Why such an interest in basketball ?
Berger and Pope (2011) βCan Losing Lead to Winning ? β (preprint in 2009).
See also A Slight Deficit Can Actually Be an Edge nytimes.com, When Being
Down at Halftime Is a Good Thing, wsj.com, etc.
Focus on winning probability in basketball games, logistic regression
logP[wini]
1β P[wini]= Ξ²0 + Ξ²1(score difference at half time)i + Ξ³TXi + Ξ΅i
Xi is a matrix of control variables for game i s(e.g. home vs. visitor effect).
β40 β20 0 20 40
0.0
0.2
0.4
0.6
0.8
1.0
2
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Modeling dynamic incentives ?
They did focus on score at half time, but the original dataset had much more
information : score difference from halftime until the end (per minute).
=β a dynamic model to understand when losing lead to losing
At the same time, talk on βPoint Record Incentives, Moral Hazard and Dynamic
Data β by Dionne, Pinquet, Maurice & Vanasse (2011)
Study on incentive mechanisms for road safety, with time-dependent disutility of
effort.
3
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Agenda of the talk
β’ From basketball to labor economics
β’ Understanding the dynamics : modeling processes
β¦ Long term dynamics (over a season)
β¦ Short term dynamics (over a game)
β’ An optimal effort control problem
β¦ A simple control problem
β¦ Nash equilibrium of a stochastic game
β¦ Numerical computations
β’ Understanding the dynamics : modeling processes
β¦ The score difference process
β¦ A proxy for the effort process
β’ Modeling the probability to win a game
4
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Incentives and tournament in labor economics
The pay schemes : Flat wage pay versus rank-order tournament (relative
performance evaluation).
Impact of relative performance evaluation, see Lazear (1989) :
β’ motivate employees to work harder
β’ demoralizing and create excessively competitive workplace
5
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Incentives and tournament in labor economics
For a given pay scheme : how intensively should the organization provide his
employees with information about their relative performance ?
β’ An employee who is informed he is an underdog
β¦ may be discouraged and lower his performance
β¦ works harder to preserve to avoid shame
β’ A frontrunner who learns that he is well ahead
β¦ may think that he can afford to slack
β¦ becomes more enthusiastic and increases his effort
6
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Incentives and tournament in labor economics
β impact on overall perfomance ?
β’ Theoritical models conclude to a positive impact, see Lizzeri, Meyer &
Persico (2002), Ederer (2004)
β’ Empirical literature :
β¦ if payment is independant of the otherβs performance : positive impact to
observe each otherβs effort, see Kandel & Lazear (1992).
β¦ in relative performance (both tournament and piece rate) : does not lead
frontrunners to slack off but significantly reduces the performance of
underdogs (quantity vs. quality), see Eriksson, Poulsen & Villeval (2009).
7
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
The dataset for 2008/2009 NBA match
8
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
The dataset for 2008/2009 NBA match
Atlantic Division W L Northwest Division W L
Boston Celtics 62 20 Denver Nuggets 54 28
Philadelphia 76ers 41 41 Portland Trail Blazers 54 28
New Jersey Nets 34 48 Utah Jazz 48 34
Toronto Raptors 33 49 Minnesota Timberwolves 24 58
New York Knicks 32 50 Oklahoma City Thunder 23 59
DCentral Division W L Pacific Division W L
Cleveland Cavaliers 66 16 Los Angeles Lakers 65 17
Chicago Bulls 41 41 Phoenix Suns 46 36
Detroit Pistons 39 43 Golden State Warriors 29 53
Indiana Pacers 36 46 Los Angeles Clippers 19 63
Milwaukee Bucks 34 48 Sacramento Kings 17 65
SoutheastDivision W L Southwest Division W L
Orlando Magic 59 23 San Antonio Spurs 54 28
Atlanta Hawks 47 35 Houston Rockets 53 29
Miami Heat 43 39 Dallas Mavericks 50 32
Charlotte Bobcats 35 47 New Orleans Hornets 49 33
Washington Wizards 19 63 Memphis Grizzlies 24 58
9
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
A Brownian process to model the season (LT) ?
Variance of the process (tβ1/2St), (St) being the cumulated score over the season,
after t games (+1 winning, -1 losing)
time in the season t 20 games 40 games 60 games 80 games
Var(tβ1/2St
)3.627 5.496 7.23 9.428
(2.06,5.193) (3.122,7.87) (3.944,4.507) (3.296,3.766)
10
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
A Brownian process to model the season (LT) ?
β ββ β β β β β β β
β β ββ
ββ
β ββ β
ββ
β β ββ β β
β β β β β β ββ β β β β
β β β ββ β β
β β β ββ β
ββ β β β
β β ββ β β β β β
ββ
β β β β β β ββ
β β β
0 20 40 60 80
02
46
810
1214
Var(St
t)
Time (t) in the season (number of games)
11
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
A Brownian process to model the score difference (ST) ?
Variance of the process (tβ1/2St), (St) being the score difference at time t.
time in the game t 12 min. 24 min. 36 min. 48 min.
Var(tβ1/2St
)5.010 4.196 4.21 3.519
(4.692,5.362) (3.930,4.491) (3.944,4.507) (3.296,3.766)
12
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
A Brownian process to model the score difference (ST) ?
β
β
β
β
ββ β
β
ββ
ββ
β β
ββ
β
β
ββ
ββ
ββ
β β β β ββ β β
ββ β
ββ
ββ
β ββ
ββ β
β
β
β
0 10 20 30 40
3.5
4.0
4.5
5.0
5.5
Var(St
t)
Time (t) in the game (in min.)
13
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
The score difference as a controlled process
Let (St) denote the score difference, A wins if ST > 0 and B wins if ST < 0.
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
β
0 10 20 30 40
β20
β10
010
20
Time (min.)
Team A wins
Team B wins
β
The score difference can be driven by a diffusion dSt = Β΅dt+ ΟdWt
00
14
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
The score difference as a controlled process
The score difference can be driven by a diffusion dSt = [Β΅A β Β΅B ]dt+ ΟdWt
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
β
0 10 20 30 40
β20
β10
010
20
Time (min.)
Team A wins
Team B wins
β
Here, Β΅A < Β΅B
15
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
The score difference as a controlled process
The score difference can be driven by a diffusion dSt = [Β΅A β Β΅B ]dt+ ΟdWt
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
β
0 10 20 30 40
β20
β10
010
20
Time (min.)
Team A wins
Team B wins
β
β
difference
16
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
The score difference as a controlled process
The score difference can be driven by a diffusion dSt = [Β΅A β Β΅B ]dt+ ΟdWt
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
β
0 10 20 30 40
β20
β10
010
20
Time (min.)
Team A wins
Team B wins
β
β
β
at time Ο = 24min., team B can change its effort level, dSt = [Β΅A β 0]dt+ ΟdWt
17
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
The score difference as a controlled process
The score difference can be driven by a diffusion dSt = [Β΅A β 0]dt+ ΟdWt
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
β
0 10 20 30 40
β20
β10
010
20
Time (min.)
Team A wins
Team B wins
β
β
β
β
at time Ο = 36min., team B can change its effort level, dSt = [Β΅A β Β΅B ]dt+ ΟdWt
difference
18
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
The score difference as a controlled process
The score difference is now driven by a diffusion dSt = [Β΅A β Β΅B ]dt+ ΟdWt
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
β
0 10 20 30 40
β20
β10
010
20
Time (min.)
Team A wins
Team B wins
β
β
β
β
19
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Introducing the effort as a control process
There are two players (teams), 1 and 2, playing a game over a period [0, T ]. Let
(St) denote the score difference (in favor of team 1 w.r.t. team 2)
β’ team 1 : max(u1)βU1
{E
([1(ST > 0)] +
β« T
Ο
eβΞ΄1tL1(Ξ±1 β u1,t)
)dt
}
β’ team 2 : max(u2)βU2
{E
([1(ST < 0)] +
β« T
Ο
eβΞ΄2tL2(Ξ±2 β u2,t)
)dt
}where (St) is a stochastic process driven by
dSt = [u1(St)β u2(St)]dt+ ΟdWt on [0, T ].
20
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Introducing the effort as a control process
There are two players (teams), 1 and 2, playing a game over a period [0, T ]. Let
(St) denote the score difference (in favor of team 1 w.r.t. team 2)
β’ team 1 : max(u1)βU1
{E
([1(ST > 0)] +
β« T
Ο
eβΞ΄1tL1(Ξ±1 β u1,t)
)dt
}
β’ team 2 : max(u2)βU2
{E
([1(ST < 0)] +
β« T
Ο
eβΞ΄2tL2(Ξ±2 β u2,t)
)dt
}where (St) is a stochastic process driven by
dSt = [u1(St)β u2(St)]dt+ ΟdWt on [0, T ].
21
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
An optimal control stochastic game
There are two players (teams), 1 and 2, playing a game over a period [0, T ]. Let
(St) denote the score difference (in favor of team 1 w.r.t. team 2)
β’ team 1 : u?1,Ο β argmax(u1)βU1
{E
([1(ST > 0)] +
β« T
Ο
eβΞ΄1tL1(Ξ±1 β u?1,t(St))
)dt
}
β’ team 2 : u?2,Ο β argmax(u2)βU2
{E
([1(ST < 0)] +
β« T
Ο
eβΞ΄2tL2(Ξ±2 β u?2,t(St))
)dt
}where (St) is a stochastic process driven by
dSt = [u?1,t(St)β u?2,t(St)]dt+ ΟdWt on [0, T ].
=β non-cooperative stochastic (dynamic) game with 2 players and non-null sum
22
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
An optimal control problem
Consider now not a game, but a standard optimal control problem, where an
agent faces the optimization program
max(ut)tβ[Ο,T ]
{E
(1(ST > 0) +
β« T
Ο
eβΞ΄tL(Ξ±β ut)dt
)},
with dSt =
udt+ ΟdWt if ut = u (= u > 0)
udt+ ΟdWt if ut = u (= 0)
where L is an increasing convex utility function, with Ξ± > 0, and Ξ΄ > 0.
Consider a two-value effort model,
β’ if ut = 0, there is fixed utility L(Ξ±)
β’ if ut = u > 0, there an decrease of utility L(Ξ±β u) < L(Ξ±), but also an
increase of P(ST > 0) since the stochastic diffusion now has a positive drift.
23
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
When should a team stop playing (with high effort) ?
The team starts playing with a high effort (u), and then, stop effort at some time
Ο : utility gains exceed changes in the probability to win, i.e.β« T
Ο
eβΞ΄tL(Ξ±β u)dt+ P(ST > 0|SΟ , positive drift on [Ο, T ])
>
β« T
Ο
eβΞ΄tL(Ξ±)dt+ P(ST > 0|SΟ , no drift on [Ο, T ])
Recall that, if Z = ST β SΟ
P(ST > 0|SΟ = d, no drift on [Ο, T ]) = P(Z > βd|Z βΌ N (0, ΟβT β Ο))
P(ST > 0|SΟ = d, drift on [Ο, T ]) = P(Z > βd|Z βΌ N (u[T β Ο ], ΟβT β Ο))
where Β΅ =1
2u.
24
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Thus, the difference between those two probabilities is
Ξ¦
(d
Οβ
[T β Ο ]
)β Ξ¦
(d+ [T β Ο ]u
Οβ
[T β Ο ]
)
Thus, the optimal time Ο? is solution of
[L(Ξ±β u)β L(Ξ±)][eβΞ΄Ο β eβΞ΄T ]
Ξ΄οΈΈ οΈ·οΈ· οΈΈβTβΟ
= Ξ¦
(d
Οβ
[T β Ο ]
)β Ξ¦
(d+ [T β Ο ]u
Οβ
[T β Ο ]
).
i.e.
Ο? = h(d, Ξ», u, L, Ο).
Thus, the optimal time to stop playing with hight effort (as a function of the
remaining time T β Ο and the score difference d) is the following region,
25
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Region where teams stop making (high) efforts
0 10 20 30 40
β15
β10
β5
05
1015
Obviously, it is too simple.... we need to consider a non-cooperative game.
26
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Optimal strategy on a discretized version of the game
Assume that controls u1 and u2 are discrete, taking values in a set U . Since we
consider a non-null sum game, Nash equilibrium have to be searched in extremal
points of polytopes of payoff matrices (see ).
Looking for Nash equilibriums might not be a great strategy
Here, (u?1, u?2) is solution of maxmin problems
u?1 β argmaxu1βU
{minu2βU
J1(u1, u2)
}and u?2 β argmax
u2βU
{minu1βU
J2(u1, u2)
}where J functions are payoffs.
27
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Discretized version of the stochastic game
0 10 20 30 40
β10
β5
05
10
Let (St)tβ[0,T ] denote the score difference over the game,
dS?t = (u?1(S?t )β u?2(S?t ))dt+ dWt
28
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Discretized version of the stochastic game
0 10 20 30 40
β10
β5
05
10
β
At time Ο β [0, T ), given SΟ = x, player 1 seeks an optimal strategy,
u?1,Ο (x) β argmaxu1βU
{minu2βU
E
(Ξ±11(S?T > 0) +
β« T
Ο
L1(u?1,s(S?s ))ds
)}
29
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Discretized version of the stochastic game
0 10 20 30 40
β10
β5
05
10
β
At time Ο β [0, T ), given SΟ = x, player 1 seeks an optimal strategy,
u?1,Ο (x) β argmaxu1βU
{minu2βU
E
(Ξ±11(S?T > 0) +
β« Ο+h
Ο
L1(u1)ds+
β« T
Ο+h
L1(u?1,s(S?s ))ds
)}
30
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Discretized version of the stochastic game
0 10 20 30 40
β10
β5
05
10
β
Consider a discretization of [0, T ] so that optimal controls can be updated at
times tk where 0 = t0 β€ t1 β€ t2 β€ Β· Β· Β· β€ tnβ2 β€ tnβ1 β€ tn = T .
We solve the problem backward, starting at time tnβ1.
31
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Discretized version of the stochastic game
0 10 20 30 40
β10
β5
05
10
β
β
β
β
Given controls (u1, u2) , Stn = Stnβ1+ [u1β u2](tnβ tnβ1) + Ξ΅n, where Stnβ1
= x.
u?1,nβ1(x) β argmaxu1βU
{minu2βU
J1(u1, u2)
}where J1(u1, u2) is the sum of two terms,
P(Stn > 0|Stnβ1 = x) =βsβS+
P(Stn = s|Stnβ1= x) and L1(u1).
32
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Discretized version of the stochastic game
0 10 20 30 40
β10
β5
05
10
β
ββ
β
β
β
β
β
Stn = Stnβ2+ [u1 β u2](tnβ1 β tnβ2) + Ξ΅nβ1οΈΈ οΈ·οΈ· οΈΈ
Stnβ1
+[u?1,nβ1βu?2,nβ1(Stnβ1)](tnβtnβ1)+Ξ΅n,
where Stnβ2= x. Here u?1,nβ2(x) β argmax
u1βU
{minu2βU
J1(u1, u2)
}, where J1(u1, u2)...
33
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Discretized version of the stochastic game
0 10 20 30 40
β10
β5
05
10
β
ββ
β
β
β
β
β
... is the sum of two terms, based on
P(Stn = y|Stnβ2= x) =
βsβS
P(Stn = y|Stnβ1= s)οΈΈ οΈ·οΈ· οΈΈ
function of (u?1,nβ1(s),u?2,nβ1(s))
Β·P(Stnβ1= s|Stnβ2
= x)οΈΈ οΈ·οΈ· οΈΈfunction of (u1,u2)
34
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Discretized version of the stochastic game
0 10 20 30 40
β10
β5
05
10
β
ββ
β
β
β
β
β
... one term is P(Stn > 0|Stnβ2= x) (as before), the sum of L1(u1) and
E(L1(u?1,nβ1)) =βsβS
L1(u?1,nβ1(s)) Β· P (Stnβ1= s|Stnβ2
= x)
35
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Discretized version of the stochastic game
0 10 20 30 40
β10
β5
05
10
β
β β
β
β
β
β
β
β
Stn = Stnβ3+ [u1 β u2]dt+ Ξ΅nβ2οΈΈ οΈ·οΈ· οΈΈ
Stnβ2
+[u?1,nβ2 β u?2,nβ2(Stnβ2)]dt+ Ξ΅nβ1
οΈΈ οΈ·οΈ· οΈΈStnβ1
+[u?1,nβ1 β u?2,nβ1(Stnβ1)]dt+ Ξ΅n with Stnβ3 = x.
36
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Discretized version of the stochastic game
0 10 20 30 40
β10
β5
05
10
β
β β
β
β
β
β
β
β
P(Stn = y|Stnβ3= x) =
βs1,s2βS
P(Stn = y|Stnβ1= s2)οΈΈ οΈ·οΈ· οΈΈ
function of (u?1,nβ1(s2),u?2,nβ1(s2))
Β· P(Stnβ1= s2|Stnβ2
= s1)οΈΈ οΈ·οΈ· οΈΈfunction of (u?1,nβ2(s1),u
?2,nβ2(s1))
Β·P(Stnβ2= s2|Stnβ3
= s1)οΈΈ οΈ·οΈ· οΈΈfunction of (u1,u2)
37
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Discretized version of the stochastic game
0 10 20 30 40
β10
β5
05
10
β
β β
β
β
β
β
β
β
Based on those probabilities, we have P(Stn > 0|Stnβ3= x) and the second term
is the sum of L1(u1) and E(L1(u?1,nβ2) + L1(u?1,nβ1)) i.e.βsβS
L1(u?1,nβ2(s)) Β· P (Stnβ2= s|Stnβ3
= x) +βsβS
L1(u?1,nβ1(s)) Β· P (Stnβ1= s|Stnβ3
= x)
38
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Numerical computation of the discretized gameteam 1 on the left vs team 2 on the right : οΏ½ low effort οΏ½ high effort
(simple numerical application, with #U = 60 and n = 12)
(β« T
Ο
eβΞ΄(sβΟ)ds
)}
ββ
β
0.0 0.2 0.4 0.6 0.8 1.0
β20
β10
010
20
ββ
0.0 0.2 0.4 0.6 0.8 1.0
β20
β10
010
20
39
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Numerical computation of the discretized gameteam 1 on the left vs team 2 on the right : οΏ½ low effort οΏ½ high effort Ξ±1 β
u?1,Ο (x) β argmaxu1βU
{minu2βU
E
(Ξ±11(S?T > 0) +
β« T
Ο
eβΞ΄1(sβΟ)(b1 β u?1,s(S?s ))Ξ³1ds
)}
ββ
β
0.0 0.2 0.4 0.6 0.8 1.0
β20
β10
010
20
ββ
0.0 0.2 0.4 0.6 0.8 1.0
β20
β10
010
20
40
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Numerical computation of the discretized gameteam 1 on the left vs team 2 on the right : οΏ½ low effort οΏ½ high effort b1 β
u?1,Ο (x) β argmaxu1βU
{minu2βU
E
(Ξ±11(S?T > 0) +
β« T
Ο
eβΞ΄1(sβΟ)(b1 β u?1,s(S?s ))Ξ³1ds
)}
ββ
β
0.0 0.2 0.4 0.6 0.8 1.0
β20
β10
010
20
ββ
0.0 0.2 0.4 0.6 0.8 1.0
β20
β10
010
20
41
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Numerical computation of the discretized gameteam 1 on the left vs team 2 on the right : οΏ½ low effort οΏ½ high effort Ξ³1 β
u?1,Ο (x) β argmaxu1βU
{minu2βU
E
(Ξ±11(S?T > 0) +
β« T
Ο
eβΞ΄1(sβΟ)(b1 β u?1,s(S?s ))Ξ³1ds
)}
ββ
β
0.0 0.2 0.4 0.6 0.8 1.0
β20
β10
010
20
ββ
0.0 0.2 0.4 0.6 0.8 1.0
β20
β10
010
20
42
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Numerical computation of the discretized gameteam 1 on the left vs team 2 on the right : οΏ½ low effort οΏ½ high effort Ξ΄1 β
u?1,Ο (x) β argmaxu1βU
{minu2βU
E
(Ξ±11(S?T > 0) +
β« T
Ο
eβΞ΄1(sβΟ)(b1 β u?1,s(S?s ))Ξ³1ds
)}
ββ
β
0.0 0.2 0.4 0.6 0.8 1.0
β20
β10
010
20
ββ
0.0 0.2 0.4 0.6 0.8 1.0
β20
β10
010
20
43
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Description of the datasetGameID LineNumber TimeRemaining Entry
20081028CLEBOS 1 00:48:00 Start of 1st Quarter
20081028CLEBOS 2 00:48:00 Jump Ball Perkins vs Ilgauskas
20081028CLEBOS 3 00:47:40 [BOS] Rondo Foul:Shooting (1 PF)
20081028CLEBOS 4 00:47:40 [CLE 1-0] West Free Throw 1 of 2 (1 PTS)
20081028CLEBOS 5 00:47:40 [CLE 2-0] West Free Throw 2 of 2 (2 PTS)
20081028CLEBOS 6 00:47:30 [BOS] Garnett Jump Shot: Missed
20081028CLEBOS 7 00:47:28 [CLE] James Rebound (Off:0 Def:1)
20081028CLEBOS 8 00:47:22 [CLE 4-0] James Pullup Jump shot: Made (2 PTS)
20081028CLEBOS 9 00:47:06 [BOS 2-4] Pierce Slam Dunk Shot: Made (2 PTS) Assist: Rondo (1 AST)
20081028CLEBOS 10 00:46:57 [CLE] James 3pt Shot: Missed
20081028CLEBOS 11 00:46:56 [BOS] R. Allen Rebound (Off:0 Def:1)
20081028CLEBOS 12 00:46:47 [BOS 4-4] Garnett Slam Dunk Shot: Made (2 PTS) Assist: Rondo (2 AST)
20081028CLEBOS 13 00:46:24 [CLE 6-4] Ilgauskas Driving Layup Shot: Made (2 PTS) Assist: James (1 AST)
20081028CLEBOS 14 00:46:13 [BOS] Garnett Jump Shot: Missed
20081028CLEBOS 15 00:46:11 [BOS] Perkins Rebound (Off:1 Def:0)
20081028CLEBOS 16 00:46:08 [BOS] Pierce 3pt Shot: Missed
20081028CLEBOS 17 00:46:06 [CLE] Ilgauskas Rebound (Off:0 Def:1)
20081028CLEBOS 18 00:45:52 [CLE] M. Williams Layup Shot: Missed
20081028CLEBOS 19 00:45:51 [BOS] Garnett Rebound (Off:0 Def:1)
20081028CLEBOS 20 00:45:46 [BOS] R. Allen Layup Shot: Missed Block: James (1 BLK)
20081028CLEBOS 21 00:45:44 [CLE] West Rebound (Off:0 Def:1)
44
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Description of the datasetGameID LineNumber TimeRemaining Entry
20081028CLEBOS 1 00:48:00 Start of 1st Quarter
20081028CLEBOS 2 00:48:00 Jump Ball Perkins vs Ilgauskas
20081028CLEBOS 3 00:47:40 [BOS] Rondo Foul:Shooting (1 PF)
20081028CLEBOS 4 00:47:40 [CLE 1-0] West Free Throw 1 of 2 (1 PTS)
20081028CLEBOS 5 00:47:40 [CLE 2-0] West Free Throw 2 of 2 (2 PTS)
20081028CLEBOS 6 00:47:30 [BOS] Garnett Jump Shot: Missed
20081028CLEBOS 7 00:47:28 [CLE] James Rebound (Off:0 Def:1)
20081028CLEBOS 8 00:47:22 [CLE 4-0] James Pullup Jump shot: Made (2 PTS)
20081028CLEBOS 9 00:47:06 [BOS 2-4] Pierce Slam Dunk Shot: Made (2 PTS) Assist: Rondo (1 AST)
20081028CLEBOS 10 00:46:57 [CLE] James 3pt Shot: Missed
20081028CLEBOS 11 00:46:56 [BOS] R. Allen Rebound (Off:0 Def:1)
20081028CLEBOS 12 00:46:47 [BOS 4-4] Garnett Slam Dunk Shot: Made (2 PTS) Assist: Rondo (2 AST)
20081028CLEBOS 13 00:46:24 [CLE 6-4] Ilgauskas Driving Layup Shot: Made (2 PTS) Assist: James (1 AST)
20081028CLEBOS 14 00:46:13 [BOS] Garnett Jump Shot: Missed
20081028CLEBOS 15 00:46:11 [BOS] Perkins Rebound (Off:1 Def:0)
20081028CLEBOS 16 00:46:08 [BOS] Pierce 3pt Shot: Missed
20081028CLEBOS 17 00:46:06 [CLE] Ilgauskas Rebound (Off:0 Def:1)
20081028CLEBOS 18 00:45:52 [CLE] M. Williams Layup Shot: Missed
20081028CLEBOS 19 00:45:51 [BOS] Garnett Rebound (Off:0 Def:1)
20081028CLEBOS 20 00:45:46 [BOS] R. Allen Layup Shot: Missed Block: James (1 BLK)
20081028CLEBOS 21 00:45:44 [CLE] West Rebound (Off:0 Def:1)
45
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Homogeneity of the scoring process
0 10 20 30 40
0.45
0.50
0.55
0.60
Time in the game
Num
ber
of p
oint
s sc
ored
(/1
5 se
c.)
Winning team (end of the game)Losing team
46
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
The scoring process : ex post analysis of the score
0 10 20 30 40
0.45
0.50
0.55
0.60
Time in the game
Num
ber
of p
oint
s sc
ored
(/1
5 se
c.)
Winning team (end of the first quarter)Losing team
47
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
The scoring process : ex post analysis of the score
0 10 20 30 40
0.45
0.50
0.55
0.60
Time in the game
Num
ber
of p
oint
s sc
ored
(/1
5 se
c.)
Winning team (end of the second quarter)Losing team
48
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
The scoring process : ex post analysis of the score
0 10 20 30 40
0.45
0.50
0.55
0.60
Time in the game
Num
ber
of p
oint
s sc
ored
(/1
5 se
c.)
Winning team (end of the third quarter)Losing team
49
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
The scoring process : home versus visitor
0 10 20 30 40
0.45
0.50
0.55
0.60
Time in the game
Num
ber
of p
oint
s sc
ored
(/1
5 se
c.)
Home teamVisitor team
50
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
The scoring process : team strategies ?
0 10 20 30 40
0.45
0.50
0.55
0.60
Time in the game
Num
ber
of p
oint
s sc
ored
(/1
5 se
c.)
Team : Clevaland CavaliersAll teams
0 10 20 30 40
0.45
0.50
0.55
0.60
Time in the game
Num
ber
of p
oint
s sc
ored
(/1
5 se
c.)
Team : Oklahoma City ThunderAll teams
0 10 20 30 40
0.45
0.50
0.55
0.60
Time in the game
Num
ber
of p
oint
s sc
ored
(/1
5 se
c.)
Team : Los Angeles LakersAll teams
0 10 20 30 40
0.45
0.50
0.55
0.60
Time in the game
Num
ber
of p
oint
s sc
ored
(/1
5 se
c.)
Team : Sacramento KingsAll teams
51
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Effect of explanatory variables ?
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
Number of victories β 2007/2008
Num
ber
of v
icto
ries
β 2
008/
2009
ATL
BOS
CLE
DAL
DEN
DET
HOU
LAL
NOH
ORL
PHI
PHO
SAS
TOR
UTA
WAS
CHA
CHI
GSW
IND
LAC
MEN
MIA
MIL
MIN
NJNNYK
POR
SAC
20 30 40 50 60
2030
4050
60
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
Rank of the team β 2007/2008
Ran
k of
the
team
β 2
008/
2009
ATL
BOS
CLE
DAL
DEN
DET
HOU
LAL
NOH
ORL
PHI
PHO
SAS
TOR
UTA
WAS
CHA
CHI
GSW
IND
LACMEN
MIA
MIL
MIN
NJN
NYK
POR
SAC
30 25 20 15 10 5 030
2520
1510
50
cf. Galtonβs regression to the mean.
52
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Winning as a function of time and score difference
Following the idea of Berger and Pope (2009),
logit[p(s, t)] = logp
1β p= Ξ²0 + Ξ²1s+ Ξ²2(T β t)+xTΞ³
(simple linear model)
points difference
time in the gam
e (minutes)
Y1
Winning probability (difference>0)
β15 β10 β5 0 5 10 15
010
2030
40
Winning probability (difference>0)
points difference
time
in th
e ga
me
(min
utes
)
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
0.5
53
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Winning as a function of time and score difference
a natural extention
logit[p(s, t)] = logp
1β p= Ξ²0 + Ο1[s] + Ο2[T β t]+xTΞ³
(simple additive model)
points difference
time in the gam
e (minutes)
Y2
Winning probability (difference>0)
β15 β10 β5 0 5 10 15
010
2030
40
Winning probability (difference>0)
points difference
time
in th
e ga
me
(min
utes
)
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
0.5
54
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Winning as a function of time and score difference
or more generally
logit[p(s, t)] = logp
1β p= Ξ²0 + Ο1[s, T β t]+xTΞ³
(functional nonlinear model)
points difference
time in the gam
e (minutes)
Y3
Winning probability (difference>0)
β15 β10 β5 0 5 10 15
010
2030
40
Winning probability (difference>0)
points difference
time
in th
e ga
me
(min
utes
)
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8 0.9
0.5
55
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Winning as a function of time and score difference
ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
βββββββββββββββββββββββββββββ
ββββββββββββββββββββββ
ββββββββββββββββββ
ββββββββββββββββ
ββββββββββββββ
ββββββββββββββ
ββββββββββββ
ββββββββββββ
ββββββββββββ
ββββββββββββββ
ββββββββββββββββ
ββββββββββββββββ
ββββββββββββββ
ββββββββββββ
ββββββββββββ
βββββββββββββ
ββββββββββββββ
ββββββββββββββ
ββββββββββββββββ
βββββββββββββββββββ
βββββββββββββββββββββββ
ββββββββββββββββββββββββββββββββ
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β20 β10 0 10 20
0.0
0.2
0.4
0.6
0.8
1.0
Score Difference (after 24 mins.)
Win
ning
Pro
babi
lity
ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
ββββββββββββββββββββββββ
βββββββββββββββββ
ββββββββββββββ
ββββββββββββ
ββββββββββββ
βββββββββββββ
βββββββββββββββ
ββββββββββββββββ
βββββββββββββββ
ββββββββββββ
βββββββββββββββββββββ
βββββββββββββ
ββββββββββββββββ
ββββββββββββββββ
ββββββββββββββ
ββββββββββββ
ββββββββββββ
βββββββββββββ
βββββββββββββββ
βββββββββββββββββββ
ββββββββββββββββββββββββββββ
ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β20 β10 0 10 20
0.0
0.2
0.4
0.6
0.8
1.0
Score Difference (after 28 mins.)
Win
ning
Pro
babi
lity
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
ββββββββββββββββββββββββββββ
ββββββββββββββββββββ
βββββββββββββββββ
ββββββββββββββ
ββββββββββββ
ββββββββββββ
βββββββββββββββββββββββββββββββ
ββββββββββββ
ββββββββββββ
ββββββββββββ
ββββββββββββ
βββββββββββββββββββββββββββββββ
ββββββββββββ
βββββββββββββ
βββββββββββββββ
ββββββββββββββββββ
βββββββββββββββββββββββ
βββββββββββββββββββββββββββββββββββ
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β20 β10 0 10 20
0.0
0.2
0.4
0.6
0.8
1.0
Score Difference (after 32 mins.)
Win
ning
Pro
babi
lity
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
βββββββββββββββββββββββββββββββββββββ
βββββββββββββββββββ
βββββββββββββ
ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
ββββββββββββ
ββββββββββββ
ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
βββββββββββββββ
βββββββββββββββββββββββ
βββββββββββββββββββββββββββββββββββββββββββββ
ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β20 β10 0 10 20
0.0
0.2
0.4
0.6
0.8
1.0
Score Difference (after 36 mins.)
Win
ning
Pro
babi
lity
ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
ββββββββββββββββββββββββββ
βββββββββββββββ
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
βββββββββββββββ
ββββββββββββββββββββββββ
ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β20 β10 0 10 20
0.0
0.2
0.4
0.6
0.8
1.0
Score Difference (after 40 mins.)
Win
ning
Pro
babi
lity
ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
ββββββββββββββββββββββ
ββββββββββββββ
ββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
βββββββββββββββ
βββββββββββββββββββββββββ
βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ
β20 β10 0 10 20
0.0
0.2
0.4
0.6
0.8
1.0
Score Difference (after 42 mins.)
Win
ning
Pro
babi
lity
β20 β10 0 10 20
0.0
0.2
0.4
0.6
0.8
1.0
Score Difference (after 24 mins.)
Win
ning
Pro
babi
lity
Home teamsAll teamsVisitor teams
β20 β10 0 10 20
0.0
0.2
0.4
0.6
0.8
1.0
Score Difference (after 28 mins.)
Win
ning
Pro
babi
lity
Home teamsAll teamsVisitor teams
β20 β10 0 10 20
0.0
0.2
0.4
0.6
0.8
1.0
Score Difference (after 32 mins.)
Win
ning
Pro
babi
lity
Home teamsAll teamsVisitor teams
β20 β10 0 10 20
0.0
0.2
0.4
0.6
0.8
1.0
Score Difference (after 36 mins.)
Win
ning
Pro
babi
lity
Home teamsAll teamsVisitor teams
β20 β10 0 10 20
0.0
0.2
0.4
0.6
0.8
1.0
Score Difference (after 40 mins.)
Win
ning
Pro
babi
lity
Home teamsAll teamsVisitor teams
β20 β10 0 10 20
0.0
0.2
0.4
0.6
0.8
1.0
Score Difference (after 42 mins.)
Win
ning
Pro
babi
lity
Home teamsAll teamsVisitor teams
56
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Smooth estimation, versus raw data
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
β20 β10 0 10 20
010
2030
40
Points difference
Tim
e
β20 β10 0 10 200
1020
3040
Points difference
Tim
e
57
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Smooth estimation, versus raw data
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
ββ
β20 β10 0 10 20
010
2030
40
Points difference
Tim
e
0.1
0
.2 0
.3
0.4
0.5
0.6 0.7 0.8 0.9
0.5
β20 β10 0 10 200
1020
3040
Points difference
Tim
e
0.1
0
.2
0.3
0
.4
0.5
0.6 0.7 0.8
0.9
0.5
58
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Do teams update their effort ?
β15 β10 β5 0 5 10 15
1520
2530
3540
45
score difference
time
0.1
0.2
0
.3
0.4
0.5
0.6
0.7
0.8
0.9
0.1
0.2
0
.3 0
.4
0.6 0.7 0.8
0.9
59
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
When do teams stop their effort ?
when teams are about to win (90% chance)
β15 β10 β5 0 5 10 15
1520
2530
3540
45
score difference
time
0.1
0.2
0
.3
0.4
0.5
0.6
0.7
0.8
0.9 0.9
Tim
e
1520
2530
3540
45
Winning probability=0.9
60
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
When do teams stop their effort ?
(with a more accurate estimation of the change in the slope)
β15 β10 β5 0 5 10 15
1520
2530
3540
45
score difference
time
0.1
0.2
0
.3
0.4
0.5
0.6
0.7
0.8
0.9 0.9
Tim
e
1520
2530
3540
45
Winning probability=0.9
61
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
When do teams stop their effort ?
when teams are about to win (80% chance)
β15 β10 β5 0 5 10 15
1520
2530
3540
45
score difference
time
0.1
0.2
0
.3
0.4
0.5
0.6
0.7
0.8
0.9
0.8
Tim
e
1520
2530
3540
45
Winning probability=0.8
62
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
When do teams stop their effort ?
when teams are about to win (70% chance)
β15 β10 β5 0 5 10 15
1520
2530
3540
45
score difference
time
0.1
0.2
0
.3
0.4
0.5
0.6
0.7
0.8
0.9 0.7
Tim
e
1520
2530
3540
45
Winning probability=0.7
63
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
When do teams stop their effort ?
when teams are about to loose (20% chance to win)
β15 β10 β5 0 5 10 15
1520
2530
3540
45
score difference
time
0.1
0.2
0
.3
0.4
0.5
0.6
0.7
0.8
0.9
0.2
Tim
e
1520
2530
3540
45
Winning probability=0.2
64
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
When do teams stop their effort ?
when teams are about to loose (10% chance to win)
β15 β10 β5 0 5 10 15
1520
2530
3540
45
score difference
time
0.1
0.2
0
.3
0.4
0.5
0.6
0.7
0.8
0.9
0.1
Tim
e
1520
2530
3540
45
Winning probability=0.1
65
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
NBA players are professionals....
Here are winning probability, college (left) versus NBA (right),
β10 β5 0 5 10
2025
3035
40
Points difference
Tim
e
0.1
0.2
0.3
0.4
0.6
0.7
0.8
0.9
β10 β5 0 5 10
2530
3540
45
Points difference
Tim
e
0.1
0.2
0.3
0.4
0.5 0.6
0.7
0.8 0.9
0.5
66
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
NBA players are professionals....
... when they play at home, college (left) versus NBA (right),
β10 β5 0 5 10
2025
3035
40
Points difference
Tim
e
0.1
0.2
0.3
0.4
0
.5
0.6
0.7
0.8
0.9
0.5
β10 β5 0 5 10
2530
3540
45
Points difference
Tim
e
0.1
0.2
0.3
0.4
0.5
0.6
0.7 0.8
0.9
0.5
67
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
On covariates, and proxy for the effort
β β
β
β
β
β β
β
β
β
β
β
β
β
β
β
β
β
ββ
β
ββ
β
β β
β
β βββ
β
β
β
β β
ββ
β
β
β
β β
β
β
β
β
ββ
ββ
β
ββ
ββ β β
β
βββ
β
β β β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
ββ
β
β
β
β
β
ββ β
β
β
β
β
ββ
β
β
β β
β
β
β
β
β
β
β ββ
β β
β
β
β ββ
β
β
ββ
β
β
β
β
β
ββ
β
β
β
β
β
β
β
β
β
β
β
β
β
ββ
β
ββ
β
β
β
β
β β
β
β
β βββ
ββ
β
βββ β
β
β
β
β
β
β
β
β
β
β
β
β ββ
β
β
ββ
β
β
β β
β
β
ββ
β
β
β
β
β β
β
β
β
β
β
βββ
β
β ββ
β
β
β
β
β
β
β β
ββ
β
β
β
β β
β
β
ββ
β
β β
β
β
β
β
ββ
β
β
β
β β
β
β
β
β
β
β
βββ
ββ β
β
β
β
β
β
β
β
β
ββ β
β
β
β
β
β β
ββ
ββ
β β
ββ
β
β
β
β
β
β
β
β
β
ββ ββββ
β
β β
β
β
β
β
β
β β
β
β
β
β
ββ
β
β
β
β β β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
ββ β
β β
ββ β
β
β
β
ββ
β
β
β
β
β
ββ
ββ β
β
ββ β
β β
β
β
β
β
ββ
β β
β
β ββ
ββ
β
β β
β
β β
β β
β
β
ββ β
ββ
β
β
β
β β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
ββ
ββ
β β
β
β
β
β
β
β
β
β
β
β
β
β
ββ
β
β
β
β
β
β
β
ββ
β ββ
β
β β
β
β
β
β
β
β
β
βββ β
β
β
ββ
β
ββ
β
β
ββ
β β
β ββ
β
β
β
β
β β
β
β
ββ
ββ
β
β
β
β
β
β
β
β
β
β
β
β
β
ββ
β
β
β
β
β
β
βββ
β
β
β β
ββ
ββ
β
β
β β
β
β
β β
β β
β
β
β
β
β
β
β
β
β
ββ β
β
β
β β
β
β
β
ββ
ββ
β
β
β
β
β
β
β
β β
β
ββ
β β
β
ββ ββ
β β
β
β
β
β
β
β
β
β
ββ ββ
β
β β
β β
β
β ββ
β
β
ββ ββ β
β
β
β ββ
β
β β
ββ
β
ββ
β
β
β
ββ
β
β
β β
β
β
β
β
β βββ β
β
β
β
β
β
β
β
β
β
β β
β
ββ
β
β β β
β
β
β
ββ
β
β
β
β
β
β β
β
β
β
ββ
β
ββ
β
β
ββ
β
β
ββ
β
β
β
β
β ββ
β
ββ β
β
β
β
β
β
β
ββ
ββ
β
β
β
β
β
β
β β
ββ
β
β
β
β
β
β
β β
β
β
β
β
β
β
β
β
β
β β
β
β
β
β
β
β
β
ββ
β
β
ββ ββ β
β β β
β
βββ β
β
β
β β
β
β β
β
β
β
β
β β
β
β
β β
β
β
ββ
β
ββ
β
β β
β β
β β
β
ββ
β
β
β
β
β
β
β
β
β
β
β β
β β
β
β
β
ββ
β
β β
ββ
ββ
β
β
β
β
β
β
β
β
β
ββ
β ββ
β
β
β
β
β
β
β β ββ β
β
β
β
β
β
β β β
β
β
β
β
β
β
ββ
β β
ββ
β
ββ
ββ
β
β
β
β
β
β
ββ
β β
β
β
β
β
β
βββ
β
β β
β
β
β
β
β
β
β
β β
β
β
β β
β
β
β
β β
β
β
β
β
β
ββ
ββ
β
β
β
β
β
β
β
β
β
β
β β
β
β
β
β
β β
ββ
β
β
β
β
β
β
β
β
β
β
β
β β
β
β
β
β ββ β
β
β
ββ
β
β
β
β
β
β
β β
β β
β
β
ββ
β
β
β
β
β
β βββ
ββ β
β ββ
β
β
β
ββ
β
β
ββ
β
β
β β
ββ
β
β
βββ β
β
β ββ
ββ
β
β
β
β
ββ
β
β
ββ
ββ
β
ββ
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
ββ β
β β
β
β
β β
β
ββ β
β
β
β
β
β
β ββ
β
β
β
β
β
β
β
β
β
β
β
β
ββ
β
β
β
β
β β
β
β
β
β
β
β
β β
β
β
ββ
β
β
β
β
β
β β
ββ
β
β β β
β
β
β
ββ β
ββ
β β
β
β
β
β
β
β β β
β
β β
β
β
β
β
ββ
β
β
β
β
β
β
β
β
β
β
β β
β
β β
β
β
ββ
β
β
ββ ββ β
β β
β
β
β
β β
ββ
β
ββ
β ββ
β
β
β
β
β
β
β
β
ββ
β
β
β
βββ β
β
ββ
β
β
β
β
ββ
β
β
β
β
β
β
β
β
β β
β
β
β
β
β
β
βββ
β
β
β
β
β
β β
β
ββ
ββ ββ
ββ
β
β
β
β
β
β
β
β
β
β
β
β
β
ββ
β
β
β
β
β
β
ββ β
β β
ββ
β
β
β
ββ
ββ
ββ
β
ββ
β
β
β
β
β
β
ββ
β
ββ
β
β
ββ
ββ
β
β
β
β β
β
β β ββ
β
β β
β
β β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β β β
β
β ββ β
β
ββ βββ β
β β
β ββ
β
β
β
β
β
β
β
ββ
β
β
β
ββ
β β
ββ
β β
β
β
β
β β
β
β
β
β
β
ββ β
β
β
β
β
ββ β β
β β
ββ
β
β
β
β
β β
β
ββ
β
β
βββ
β
β
β
β
β
β β
β
β
ββ
β
β
β
β
β
β
β
β
β
β
β
ββ
β
β β
β
β
β
β
β
ββ
β
β
β
β
ββ
β
β
ββ β
β
ββ β
β
β
β
ββ
β
β β
β
β
β
β
β
β
β
β
β
ββ
β
β β
β
β
ββ
β
β
β
β
β
β β
β
β β
β
β
β
β
β
β
β
β
ββ
ββ ββ β
β
β
β β
β
β ββ
β
β
β
β
β β
β β
β
β β
β
β ββ
β β
β
β β
β
ββ β
β
β
β
β
β
ββ
β β
β β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β β
β
β ββ
β
β
β
β
β
ββ β
β
β
β
β
β β
β
β
β
ββ
ββ
β
ββ
β
β
β
β
β ββ
β
β
β
β ββ β
βββ
β
β
β
β
β
β
β
β
ββ
ββ
β
β
β
ββ
β
β
β
β β
β ββ
β
β
β
β
β
β
β β
β
β β
ββ
β
β β
β
β
β
ββ
β β
β β
β
β
β
β ββ
β
β
β
β β
β
β
β
β
β
β
β
β
β β
β
β
β
ββ
β β
β
β
ββ
β
β
β
β
β
β
β
β
β
ββ
β
β
β
β
β
β
β
β β
β
β β
β
β
ββ
β
β
β
β ββ
β
ββ β
β
β
β
β
β
β β
ββ β β
β
β
β
β
β
β
β
ββ
β β
ββ
β
β
β
β
ββ
ββ
β
β β
β
β
ββ
ββ
β
β β
β
β
β
β
β β
β
ββ
β
β
β
ββ β
β
ββ β
ββ
β
β β
ββ
β
β
β
β
β
β
β
β
β
β
ββ
β
β
β
β
β β
β
β
β
β
ββ
ββ
β
β
β
β
β
β
β
β
β
ββ β
β
β
β
β
ββ
ββ
β
β
ββ ββ β
β
β β
β
β
β β
β β
β
β
β β
β ββ
β
β
β β
β β β
β
β
β
β β
β
β
β
ββ β
β
β
β β
ββ ββ ββ
β
β
β
ββ
ββ
β
β
β β
β
β
β
β
β
β
β ββ β
β
β
β
β ββ β
β
β
ββ ββ
β β
β
β
β
β
β
β
β
β15 β10 β5 0 5 10 15
2.0
2.2
2.4
2.6
2.8
3.0
Score Difference (beginning 3rd period)
Num
ber
of fa
ults
(fir
st 2
min
utes
)
β ββ βββ β βββββ ββ βββ β β β ββ ββ β ββ ββ ββ ββ βββ βββ βββ ββ βββ ββ ββ ββ β β βββ ββ ββ βββ β ββ β ββββ ββ ββ β β βββ ββ ββ β βββ ββ β ββ ββ β ββ ββ ββ βββ β β ββ ββ ββ βββ β βββ ββ ββββ ββ β ββ β ββ β ββ β βββ βββ βββ ββ β βββ β βββ ββ βββ βββ β ββ β ββ ββ βββ ββ β βββ β ββ ββ β β βββ ββ ββ β β ββ βββ ββββ ββ β βββ βββ β ββ β ββ ββ β ββ β ββ βββ ββ βββ ββ ββ ββ β βββ β ββ ββ βββ ββ β ββ ββ ββ βββ ββββ ββ ββ β βββ β βββ ββ βββ ββ ββ ββββ βββ ββ ββ β ββ ββ ββββ ββ βββ ββ β β β ββ ββ βββ ββ β βββ ββ βββ β ββ ββ ββ ββ ββ βββ ββ ββββ β ββββ βββ ββ β β βββββ β ββ ββ βββ βββββ β β βββ βββ β ββ β β ββ βββ ββ β ββ βββ β ββ β βββ ββ β ββ β β ββββ βββ ββ βββ ββ βββ βββ βββ β ββ ββ ββ β ββ ββ β β ββ βββ ββ βββ β β βββ βββ ββ β ββ ββββ βββ β ββ β ββ β ββ βββ ββ ββ β βββββ ββ ββ βββ β ββ β ββ ββ ββ ββ β ββ β βββββββ ββ β ββ β ββ ββ ββ β β ββ β ββ ββ β βββ ββ ββ ββ β ββ ββ β ββ ββ ββ βββ βββ ββ ββ ββ ββββ
β15 β10 β5 0 5 10 15
0.50
0.55
0.60
0.65
0.70
0.75
0.80
0.85
Score Difference (beginning 3rd period)
Num
ber
3pts
sho
ts(f
irst 2
min
utes
)
β
ββ
βββ
β
β
β
ββ
β
β
β
β
ββ
β β
β
β β
β
β
β
βββ β
β
β β
ββ
ββ β
β
β
β
β
β
β
β
β
ββ
β
β
β
ββ
β
β
β β
ββ
β
ββ β
β
β
β
β
β
β
β β
β
βββ
β
β
β
ββ
β
β
β
ββ
β
β
β
β ββ
β
β
β
β
ββ ββ
β
β
β
β ββ
β
β
β
β
β
β
β
β
β
β
β
β
β β
β
β
ββ ββ ββ β
β
ββ
β
β
β
β
ββ
β
β
β
β ββ
ββ
β
β
β
β
ββ
β
β
β
β
β
β β
β ββ β
β
β
β β
β
β
β
β
ββ β
β
β
ββ
ββ
β
β
β
β β
β
ββ β β
β
β
β β
ββ β
β
β
ββ β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
ββ
β
β
ββ
β
ββ β
β
β
β
β
β β
ββ
β
ββ
β
β β
β β
β β
β
ββ
ββ
β
β β
β
ββ
β
β
β
β β β
β β
β
ββ
β β
β
β
β β
β
ββ
β
β
β
β
β
β β
β
ββ
β
β
β
β
β
β
β
βββ
β
ββ
β
β
β
βββ β β
β
β
β
β
β
ββ
β
β
β
β
β
β
ββ β
β
β
β β
β
β ββ
β
β
β ββ
β
β
ββ
β
β
β
β
β β
β
β
β
β
β
β
β β
β
β
β
β β
β β
β
β β
β
β β
β
ββ
β
β
β
β
ββ
β
β
β
β
β
ββ
ββ β β
β
β
β
β β
β
β
β
β
ββ
ββ
ββ
β
β
β
βββ
β
β
β
β
β
β
ββ
β
β
β
ββ
β
β
β ββ
β
ββ
β
β
β
β
β
β
β
β
ββ β
β
β
β
β
β
β
β
β
ββ
β
β
β
β β
β
β ββ
β
β
β ββ
β β
β
β
β
β
ββ β
β
β β β β
β
β
β
β ββ
β
β β
β
β
β β
ββ β β
β
β β
β
β
β β
β
β
β
β β
β
β
β β
β
β
β
ββ
β
ββ
β
β
ββ
β
β
β
ββ
β
β
β
β β
β
β
β
β
ββ
β
β
β
β
β β ββ
ββ β
β
β
β
ββ
β
β β
β
β
β
β
βββ
β
β
β
β β
β
β
β
β
β
β
β
β
β β β
ββ β
β β
β
β
β
ββ
β
β β
β
β
β
β
β ββ
β
β
β
β ββ
β
β
β
β
β
β β
β
ββ
βββ β
β
β
β
β
β
β
β
β β
β
β
β β
β
ββ
β
β
ββ
β
β β
β
β
ββ β
ββ
β
β β
ββ
β
ββ β
ββ
β
ββ
β
β
β β
β
β
β β β
β
β β β
β
β
β
β
β
ββ
β β
β
β
ββ
β
β
ββ
β
β
β
ββ
β
β
ββ
β
β ββ ββ
ββ
β
β
β β
β
β β β β
β β
β
β
β
βββ
β ββ β β
β
ββ ββ β
β β
β
β
ββ
β
ββ
β
β
β
β
β
ββ
β
β
β
ββ
β
β
β
β
β
β
β
β
β β
ββ
β
β
β
β
β β
β
ββ
β
ββ ββ
β
β
βββ
ββ
β
ββ
ββ
β
ββ
β
β
β
β
β β
β β
β
β β
β
β
β
β
β β
β
β
β
β
β
β
β
β
β β
β
ββ
β
β
β
β β
β β
ββ β
ββ
β
βββ
β
β ββ
β
β
β
β
β
β
β
β
β
β
β
β β
β
ββ
ββ
ββ ββ
β β
β
ββ
β
β
β
β
β
β
ββ ββ
β
β
β β
β
β
β
β
β
β
β
β
β
β
β
β
β β β
β
β
β
β β
β
β
β
β
β β
β ββ
β
β
ββ
β
β
β
β βββ
β
β
β ββ
β
β
β
β
β
β
β
ββ ββ
ββ β
β
β
β
β
β
β
ββ β
β
β
β
β
β
ββ
ββ
β β
β
β
β
ββ
β β
β
β
β
β β
βββ
β
β
β
ββ
β β
β
β
β β
β
ββ
β β
β
β
β
β
β
β
βββ
ββ β
β β
ββ ββ
ββ
β
ββ
β
β
ββ
β
β
β ββ
β
β
β ββ
β
β β β
β
β
ββ
β
β β
β
ββ
β
β
β
β
β
ββ
β
β
β β
β
β
β
β
β β
β ββ β
ββ β
β
β
β
β
β
β
β
β
β ββ
β
β
β β
β
β
β
β
β
β ββ
β
ββ β
β β
β β
β
β
β
β
β
β
β β
β
β β
β β
β β
β
β
β
β
β
β
β
β
β
ββ
β
β ββ
β
β β
β
ββ
β
β
β
β
β
β
β
β
β
β β
ββ
β
β
β
β
ββ
β
ββ β
β β
β β
β
β
ββ
βββ ββ
β β
β
β
β
β
β
β
β
β
β
β
β
β β
β
β
β
β
β
β
β
β
ββ
β
β
β β
β
β
ββ
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β β β
β
β β
β
β ββ
β
β β β
β
β
ββ
β
β ββ ββ β
β
β
β
β
β
β ββ
β β
β
β
β β
β
β
β
β
β
β
ββ
β
β
β
β
β
ββ
β
β
β
β
β
ββ
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β
β β
β
ββ β
β β
β
β
β β β
β β
β
β
ββ
β
β
β
β
β β
β
β β
β β
β
β
ββ β ββ
β
β
β
β β
β
β
β
β
β
β
β
ββ
ββ
β
β
β
β
β
β
β
β
β
β
β
β
ββ
β
β
ββ
β
β
ββ β
β ββ
ββ
β
ββ ββ
β ββ
β
β
β
ββ
β β ββ β
β β
β
β
β
β
β
β
β
β
β
β β
β
ββ
β
β
β β
β
β
β ββ ββ
β
β
β
β
β
β β
ββ
β
ββ
β
β
β β
β
β
β
β β
β β
β
ββ β
β
ββ
β
β β
β
β
β
ββ β
β
β
β
β
β
β
ββ
β
β
β
β
β
β β
β
β
β
β
β
β
β
β β
β
ββ
ββ
β
β
β
β
ββ β
β
β
β
β
β β
β
β
β β
ββ ββ
β
β
β
βββ
β
β
ββ β
β
β
β
β
β
β
β
β
β β
β
β
β
ββ
β
β
β β
β
β
β
β
ββ
β
β
β
β
β
ββ
β
β
β
β
β
β
ββ
β
β
β
β
β
β β β
ββ
β β
β ββ
β
β
ββ
ββ
β
β ββ β
β
β
β
ββ
β
ββ
βββ β
β
β
β
β
β
β
β
β β ββ
β
β ββ
β
β β
β
ββ
β
β
ββ ββ
βββ β
β
ββ
β
β
β
β15 β10 β5 0 5 10 15
2.0
2.2
2.4
2.6
2.8
3.0
Score Difference (beginning 4th quarter)
Num
ber
of fa
ults
(fir
st 2
min
utes
)
β βββ β ββ ββ ββ β βββ β ββ ββ ββββ ββ βββ ββ β βββ ββ βββ β ββ β ββ β ββ ββββ β βββββ β ββ ββ βββ ββ ββ β ββ βββ ββ β ββ βββ βββ βββ ββ ββ ββ ββ ββ βββ ββ ββ ββ ββ ββ βββ ββββ β ββ β ββββ β β ββ ββ ββ ββ ββ ββ ββ ββ βββββββ ββ ββ ββ ββ ββ ββ β β βββ ββ β βββ ββ ββ ββ βββ β ββββ β β ββ β βββ βββ β ββ ββ β βββ ββ β ββ ββ ββ β ββ ββ βββ βββ β ββββ ββ ββ ββ ββ βββ β β ββ β ββββ ββ βββ ββ β β ββ ββ β ββ β βββ βββ β β ββββ β ββ ββ β ββ β ββ β βββ β β βββ ββ βββ βββ ββ ββ ββ β ββ β βββ ββ ββ ββ βββ ββ β ββ ββ β ββββ β ββ β ββ ββ β ββ ββ ββ βββ β ββ β β βββ ββ βββ ββββ ββ ββ ββ β ββββ β ββββ β βββ β βββ βββ β β βββββ β ββ ββ ββ ββββ β
β15 β10 β5 0 5 10 15
0.50
0.55
0.60
0.65
0.70
0.75
0.80
0.85
Score Difference (beginning 4th period)
Num
ber
3pts
sho
ts(f
irst 2
min
utes
)
68
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
ReferencesArkes, J. (2011). Do gamblers correctly price momentum in NBA betting markets. Journal of Prediction Markets 5 (1),
31β50
Arkes, J. & Martinez, J. (2011). Evidence for a Momentum Effect in the NBA. Journal of Quantitative Analysis in Sports 7
(3).
Aoyagi, M. (2010). Information feedback in a dynamic tournament. Games and Economic Behavior, 70 242β260
Basar, T. & Olsder, G-.J. (1987). Dynamic Noncooperative Game Theory. Society for Industrial & Applied
Mathematics.
Berger, J. & Pope, D. (2011) Can Losing Lead to Winning ? Management Science 57(5), 817β827,
Bressan, A. (2011). Noncooperative Differential Games : A Tutorial. Penn State University Lectures Notes.
Coffey, B. & Maloney, M.T. (2010). The thrill of victory : Measuring the incentive to win Journal of Labor Economics 28
(1) , 87β112.
Courty, P. & Marschke, G.R. (2004). An empirical investigation of gaming responses to explicit performance
incentives. Journal of Labor Economics 22 :1, 23β56.
Dionne, G. , Pinquet, J. Maurice, M. & Vanasse, C. (2011) Incentive Mechanisms for Safe Driving : A Comparative
Analysis with Dynamic Data. Review of Economic Studies 93 (1), 218β227.
Delfgaauw, J., Dur, R., Non, A. & Verbeke, W. (2014) Dynamic incentive effects of relative performance pay : A field
experiment. Labour Economics, 28,1β13.
Ederer, F. (2010). Feedback and motivation in dynamic tournaments Journal of Economics and Management Strategy, 19
(3), 733β769.
Eriksson, T., Poulsen, A. & Villeval, M.C. (2009). Feedback and Incentives : Experimental Evidence. Labour Economics,
16, 679β688.
Everson, P. & Goldsmith-Pinkh, P.S. (2008). Composite Poisson Models for Goal Scoring. Journal of Quantitative Analysis
in Sports 4 (2).
Falk, A. & Ichino, A. (2006). Clean Evidence on Peer Effects. Journal of Labor Economics, 24 (1), 39β58.
69
Arthur CHARPENTIER, Nathalie Colombier & Romuald Elie - Modeling Dynamic Incentives: an Application to Basketball Games
Gabel, A. & Redner, S. (2012). Random Walk Picture of Basketball Scoring. Journal of Quantitative Analysis in Sports 8
(1), 1β18.
Gandar, J.M., Zuber, R.A. & Lamb, R.P. (2001). The Home Field Advantage Revisited : A Search for the Bias in
Other Sports Betting Markets. Journal of Economics and Business, 53 :4, 439β453.
Gershkov, A. & Perry, M. (2009). Tournaments with midterm reviews. Games and Economic Behavior, 66, 162β190.
Kahn, L.M. (2000) The Sports Business as a Labor Market Laboratory. Journal of Economic Perspectives, 14 :3, 75β94.
Kubatko, J., Oliver, D. Pelton, K. & Rosenbaum, D.T. (2007). A Starting Point for Analyzing Basketball Statistics.
Journal of Quantitative Analysis in Sports 3 1β24 .
Lazear, E. P., & Rosen, S. (1981). Rank-order tournaments as optimum labor contracts. Journal of Political Economy 89
(5) 841β864.
Lazear, E. P. (1989). Pay Equality and Industrial Politics. Journal of Political Economy 97 (3), 561β580.
Lazear, E.P. & S. Rosen. (1981). Rank-order tournaments as optimum labor contracts. Journal of Political Economy 89(5)
841β864
Lazear, E.P. & Gibbs, M. (2009) Personnel Economics in Practice. Wiley.
Mas, A., & Moretti, E. (2009). Peers at Work. American Economic Review, 99 (1), 112β145.
Massey, C. &Thaler, R.H. (2013). The Loserβs Curse : Overconfidence vs. Market Efficiency in the National Football
League Draft. Management Science, 59 :7, 1479β1495
Meritt, S. & Clauset, A. (2014).Scoring dynamics across professional team sports : tempo, balance and predictability.
EPJ Data Science, 3 :4, 1479β1495
Prendergast, C. (1999). The Provision of Incentives in Firms. Journal of Economic Literature 37, 7β63.
Skinner, B. (2010). The Price of Anarchy in Basketball.Journal of Quantitative Analysis in Sports 6.
Soebbing, B. & Humphreys, B. (2010) Do gamblers think that teams tank ? Evidence from the NBA. Contemporary
Economic Policy, 31 301β313.
Vergin, R. (2000) Winning streaks in sports and the misperception of momentum Journal of Sports Behavior, 23, .
Westfall, P.H. (1990). Graphical Presentation of a Basketball Game The American Statistician, 44 :4, 305β307.
70