Set the working directory and RData file
setwd("~/Documents/Masters/DATA606/Week2/Lab/Lab2")
load("more/kobe.RData")
require(ggplot2)
## Loading required package: ggplot2
Answer:
A streak length of 1 is when kobe made only one basket before missing his next shot (i.e. one hit and one miss). A streak length of zero would consist of two misses in a row.
Answer:
kobe_streak <- calc_streak(kobe$basket)
summary(kobe_streak)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0000 0.0000 0.0000 0.7632 1.0000 4.0000
The distribution has a right skew with a median of 0, median of 0.7632, IQR of 1, and max of 4. The typical streak length was 0 (using median) and 0.7632 (using mean). The longest streak was 4.
outcomes <- c("H", "M")
sim_unfair_coin <- sample(outcomes, size = 100, replace = TRUE,
prob = c(0.2, 0.8))
number_of_heads <- table(sim_unfair_coin)[["H"]]
number_of_heads
## [1] 18
Answer:
outcomes <- c("H", "M")
sim_basket <- sample(outcomes, size = 133, replace = TRUE, prob = c(0.45,
0.55))
Answer:
I will re-run the sample command; however, this time I will use set.seed() to freeze the results so I can comment on them.
set.seed(100)
outcomes <- c("H", "M")
sim_basket <- sample(outcomes, size = 133, replace = TRUE, prob = c(0.45,
0.55))
sim_basket_streak <- calc_streak(sim_basket)
sim_basket_streak
## [1] 0 0 1 0 0 1 0 0 2 0 2 0 0 1 1 1 0 2 0 0 1 3 2 0 4 2 0 0 0 0 0 1 0 0 1
## [36] 0 3 0 0 0 0 1 0 7 0 3 2 0 2 0 0 1 0 0 0 1 0 0 0 4 0 2 0 1 2 1 0 0 1 0
## [71] 3 0 2
barplot(table(sim_basket_streak))
summary(sim_basket_streak)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0000 0.0000 0.0000 0.8356 1.0000 7.0000
The distribution has a right skew with a median of 0, median of 0.8356, IQR of 1, and max of 7. The typical streak length was 0 (using median) and 0.8356 (using mean). The longest streak was 7.
Answer:
My expectation would be that a second simulation would result in similar, but not exactly the same, distribution. We would expect simulation results to be more similar as the number of samples increases; however, since the probability of making each shot is independent of the others, it is unlikely we would get a result with exactly the same number of makes and misses.
I have run another simulation below which verifies that we would get a similar, but not exactly the same, result:
set.seed(200)
outcomes <- c("H", "M")
sim_basket <- sample(outcomes, size = 133, replace = TRUE, prob = c(0.45,
0.55))
sim_basket_streak <- calc_streak(sim_basket)
sim_basket_streak
## [1] 0 6 0 0 0 1 1 0 1 2 0 0 1 0 1 0 0 0 0 0 0 2 1 0 3 2 3 0 2 0 0 0 2 5 0
## [36] 0 1 0 0 0 0 0 1 1 3 0 1 1 1 0 0 0 1 0 0 0 3 1 0 1 0 0 1 0 1 2 0 0 2 3
## [71] 1 0 0 2
barplot(table(sim_basket_streak))
summary(sim_basket_streak)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0000 0.0000 0.0000 0.8108 1.0000 6.0000
Answer:
Let’s make a graph to compare our first simulation with Kobe’s baskets
set.seed(100)
outcomes <- c("H", "M")
sim_basket <- sample(outcomes, size = 133, replace = TRUE, prob = c(0.45,
0.55))
sim_basket_streak <- calc_streak(sim_basket)
sim_basket_table_f <- table(sim_basket_streak)/length(sim_basket_streak)
kobe_streak <- calc_streak(kobe$basket)
kobe_basket_table_f <- data.frame(table(kobe_streak)/length(kobe_streak),
"kobe")
names(kobe_basket_table_f) <- c("Streak", "Frequency", "Data")
table(sim_basket_streak)
## sim_basket_streak
## 0 1 2 3 4 7
## 42 14 10 4 2 1
sim_basket_table_f
## sim_basket_streak
## 0 1 2 3 4 7
## 0.57534247 0.19178082 0.13698630 0.05479452 0.02739726 0.01369863
table(kobe_streak)
## kobe_streak
## 0 1 2 3 4
## 39 24 6 6 1
table(kobe_streak)/length(kobe_streak)
## kobe_streak
## 0 1 2 3 4
## 0.51315789 0.31578947 0.07894737 0.07894737 0.01315789
combined_table <- data.frame(sim_basket_table_f, "Sim")
names(combined_table) <- c("Streak", "Frequency", "Data")
combined_table <- rbind(combined_table, kobe_basket_table_f)
ggplot(combined_table, aes(x = Streak, y = Frequency, fill = Data)) +
geom_bar(stat = "identity", position = "dodge")
I made a bar plot that summarizes the relative frequency of each type of streak. As you can, a streak of zero happened over 50% of the time for both cases, followed by decreasing frequencies for each streak type. As expected, Kobe’s distribtuion appears to be similar to the simulation performed. No, it does not appear the hot hand model, where a shooter’s percent chance of making a basket increases on successive shots, fits Kobe’s shooting pattern. His shots appear to be independent of each other.