Probability Lab

Author

M. Lopez

Probability Lab: The Hot Hand

Loading Libraries

library(tidyverse)
── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.4     ✔ readr     2.1.5
✔ forcats   1.0.0     ✔ stringr   1.5.1
✔ ggplot2   3.4.4     ✔ tibble    3.2.1
✔ lubridate 1.9.3     ✔ tidyr     1.3.1
✔ purrr     1.0.2     
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(openintro)
Loading required package: airports
Loading required package: cherryblossom
Loading required package: usdata

Data Access

data(kobe_basket)
glimpse(kobe_basket)
Rows: 133
Columns: 6
$ vs          <fct> ORL, ORL, ORL, ORL, ORL, ORL, ORL, ORL, ORL, ORL, ORL, ORL…
$ game        <int> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1…
$ quarter     <fct> 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 3, 3…
$ time        <fct> 9:47, 9:07, 8:11, 7:41, 7:03, 6:01, 4:07, 0:52, 0:00, 6:35…
$ description <fct> Kobe Bryant makes 4-foot two point shot, Kobe Bryant misse…
$ shot        <chr> "H", "M", "M", "H", "H", "M", "M", "M", "M", "H", "H", "H"…
head(kobe_basket)
# A tibble: 6 × 6
  vs     game quarter time  description                                    shot 
  <fct> <int> <fct>   <fct> <fct>                                          <chr>
1 ORL       1 1       9:47  Kobe Bryant makes 4-foot two point shot        H    
2 ORL       1 1       9:07  Kobe Bryant misses jumper                      M    
3 ORL       1 1       8:11  Kobe Bryant misses 7-foot jumper               M    
4 ORL       1 1       7:41  Kobe Bryant makes 16-foot jumper (Derek Fishe… H    
5 ORL       1 1       7:03  Kobe Bryant makes driving layup                H    
6 ORL       1 1       6:01  Kobe Bryant misses jumper                      M    

Exercise 1: What does a streak length of 1 mean, i.e. how many hits and misses are in a streak of 1? What about a streak length of 0?

Answer: In a streak of length 1, one hit is made, immediately followed by a miss. This appears in the data as a sequence HM. In a streak of length 0, there are no sequential hits made, therefore the streak consists of one miss. This appears in the data as a sequence of just M. If at any point there is a miss, the streak length will automatically return to 0.

Calculating Streak Length

kobe_streak <- calc_streak(kobe_basket$shot)

ggplot(data = kobe_streak, aes(x = length)) +
  geom_bar()

summary(kobe_streak)
     length      
 Min.   :0.0000  
 1st Qu.:0.0000  
 Median :0.0000  
 Mean   :0.7632  
 3rd Qu.:1.0000  
 Max.   :4.0000  

Exercise 2: Describe the distribution of Kobe’s streak lengths from the 2009 NBA finals. What was his typical streak length? How long was his longest streak of baskets? Make sure to include the accompanying plot in your answer.

Answer: The distribution of Kobe’s streak lengths from the 2009 NBA finals is right-skewed. His typical streak length was 0. The longest streak of baskets he had was 4, as evidenced by the graph’s use of this number as the last interval on the x-axis and confirmed by the “Max” value of the data summary.

Simulating with Coin Flip

coin_outcomes <- c("heads", "tails")
set.seed(57391)

#Fair coin flip simulation
sim_fair_coin <- sample(coin_outcomes, size = 100, replace = TRUE)
sim_fair_coin
  [1] "heads" "tails" "heads" "tails" "tails" "heads" "heads" "heads" "tails"
 [10] "heads" "tails" "heads" "heads" "heads" "heads" "heads" "tails" "tails"
 [19] "tails" "heads" "tails" "tails" "tails" "tails" "tails" "heads" "tails"
 [28] "heads" "tails" "tails" "heads" "heads" "tails" "heads" "heads" "heads"
 [37] "heads" "tails" "tails" "heads" "heads" "heads" "tails" "heads" "tails"
 [46] "tails" "heads" "tails" "tails" "heads" "heads" "heads" "heads" "tails"
 [55] "heads" "heads" "tails" "tails" "tails" "tails" "tails" "tails" "heads"
 [64] "heads" "tails" "heads" "tails" "tails" "heads" "tails" "tails" "heads"
 [73] "heads" "heads" "heads" "heads" "tails" "tails" "tails" "tails" "tails"
 [82] "tails" "heads" "tails" "tails" "heads" "heads" "heads" "heads" "heads"
 [91] "tails" "tails" "tails" "heads" "tails" "heads" "tails" "heads" "heads"
[100] "heads"
table(sim_fair_coin)
sim_fair_coin
heads tails 
   51    49 
#Unfair coin flip simulation
sim_unfair_coin <- sample(coin_outcomes, size = 100, replace = TRUE, prob = c(0.2,0.8))
sim_unfair_coin
  [1] "tails" "heads" "tails" "heads" "tails" "tails" "tails" "tails" "tails"
 [10] "heads" "tails" "tails" "heads" "tails" "tails" "tails" "tails" "heads"
 [19] "tails" "tails" "heads" "tails" "tails" "tails" "tails" "tails" "tails"
 [28] "tails" "tails" "tails" "heads" "tails" "heads" "tails" "tails" "tails"
 [37] "tails" "tails" "tails" "heads" "tails" "tails" "tails" "tails" "tails"
 [46] "tails" "tails" "tails" "tails" "heads" "heads" "tails" "tails" "tails"
 [55] "tails" "tails" "tails" "tails" "heads" "tails" "tails" "tails" "tails"
 [64] "heads" "tails" "tails" "tails" "tails" "tails" "tails" "heads" "tails"
 [73] "tails" "tails" "tails" "tails" "heads" "tails" "tails" "tails" "tails"
 [82] "tails" "heads" "tails" "tails" "tails" "tails" "heads" "heads" "tails"
 [91] "tails" "heads" "tails" "heads" "tails" "tails" "tails" "tails" "tails"
[100] "heads"
table(sim_unfair_coin)
sim_unfair_coin
heads tails 
   21    79 

Exercise 3: In your simulation of flipping the unfair coin 100 times, how many flips came up heads? Include the code for sampling the unfair coin in your response. Since the markdown file will run the code, and generate a new sample each time you Knit it, you should also “set a seed” before you sample. Read more about setting a seed below.

Answer: In my simulation of flipping the unfair coin 100 times, the coin came up as heads 21 times.

Simulating the Independent Shooter

shot_outcome <- c("H", "M")
sim_basket <- sample(shot_outcome, size = 1, replace = TRUE)

Exercise 4: What change needs to be made to the 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.

Answer: In order to reflect a shooting percentage of 45%, the sample function needs to contain a “prob” section which sets the probability of “hit” to 0.45.

set.seed(36232)
shot_outcome <- c("H", "M")
sim_basket <- sample(shot_outcome, size = 133, replace = TRUE, prob = c(0.45, 0.55))

Comparing Data with Simulation

Exercise 5: Using calc_streak, compute the streak lengths of sim_basket, and save the results in a data frame called sim_streak.

Answer:

sim_streak <- calc_streak(sim_basket)


ggplot(data = sim_streak, aes(x = length)) +
  geom_bar()

summary(sim_streak)
     length      
 Min.   :0.0000  
 1st Qu.:0.0000  
 Median :0.0000  
 Mean   :0.7632  
 3rd Qu.:1.0000  
 Max.   :5.0000  

Exercise 6: Describe the distribution of streak lengths. What is the typical streak length for this simulated independent shooter with a 45% shooting percentage? How long is the player’s longest streak of baskets in 133 shots? Make sure to include a plot in your answer.

Answer: The distribution of streak lengths for the simulated independent shooter is right-skewed. The typical streak length for this simulation independent shooter is 0. The simulated shooter’s longest streak is 5, as indicated by the bar graph and summary.

Exercise 7: If you were to run the simulation of the independent shooter a second time, how would you expect its streak distribution to compare to the distribution from the question above? Exactly the same? Somewhat similar? Totally different? Explain your reasoning.

Answer: I would expect that a second simulation would appear very similar to the first, though there is a very small chance that it would vary dramatically. The reason being that the same parameters (probability values, number of outcomes) are being set forward to create a data set which will model the same behavior as its previous rendition.

Exercise 8: How does Kobe Bryant’s distribution of streak lengths compare to the distribution of streak lengths for the simulated shooter? Using this comparison, do you have evidence that the hot hand model fits Kobe’s shooting patterns? Explain.

Answer: Kobe Bryant’s distribution of streak lengths is very similar to the distribution of the streak lengths of the simulated shooter. Both distributions are right-skewed, have the same median, and have similar mean values. Given that the simulated data set was intended to model the expected outcomes of a shooter with hot hand, it would appear that Kobe Bryant’s data is similar enough to suggest he, too, exhibits the outcomes/behavior of those with hot hand.