Streak is number of baskets before a miss.
In a streak of 1, there’s 1 hit and 1 miss.
In a streak of 0, there’s just a miss.
head(kobe)## vs game quarter time
## 1 ORL 1 1 9:47
## 2 ORL 1 1 9:07
## 3 ORL 1 1 8:11
## 4 ORL 1 1 7:41
## 5 ORL 1 1 7:03
## 6 ORL 1 1 6:01
## description basket
## 1 Kobe Bryant makes 4-foot two point shot H
## 2 Kobe Bryant misses jumper M
## 3 Kobe Bryant misses 7-foot jumper M
## 4 Kobe Bryant makes 16-foot jumper (Derek Fisher assists) H
## 5 Kobe Bryant makes driving layup H
## 6 Kobe Bryant misses jumper M
Distribution is right-skewed and bounded at zero on the left.
Typical streak is of length 0. Longest streak is of 4 baskets.
##
## H M
## 22 78
sample function so that it reflects a shooting percentage of 45%? Make this adjustment, then run a simulation to sample 133 shots. Assign the output of this simulation to a new object called sim_basket.sim_basket <- sample(outcomes, size = 133, replace = TRUE, prob = c(0.45, 0.55))calc_streak, compute the streak lengths of sim_basket.barplot(table(kobe_streak))sim_streak <- calc_streak(sim_basket)
barplot(table(sim_streak))Distribution of the simulated streak is right-skewed and bounded at 0 on the left.
Typical streak again is zero.
Longest streak is 5 baskets.
I’d expect the overall shape to remain the same, as it will always be left-bounded at 0, and probability of values to the right are increasingly unlikely
\[ P(\textrm{x hits, hit probability p}) = p^x \]
barplot(prop.table(table(kobe_streak)), main = "Kobe's streak")barplot(prop.table(table(sim_streak)), main = "Simulated streak")In this specific comparison, there is wider variation in the simulation (one streak of 5 hits). There happens to be a greater percentage of missed shots. In Kobe’s data, there’s a greater number of 0 or 1 hit “streaks” but I don’t know if 1 hit is really a “hot hand”. I think we’d only be comparing the percentage of > 1 streaks versus streaks that ended at 1. Here, there doesn’t seem to be a greater percentage of such shots. This is only one simulation, though, so we can’t draw conclusions from just this one comparison.
Additionally, I think this question of hot-hand would have to take into account the type of shots that were taken. Maybe if you’re making shots, you’re more likely to try more difficult shots. Even if your percentage of “hits” was the same, you still might legitimately be playing “better” after making prior shots.