Setup
# Load Libriaries
library(tidyverse)
library(knitr)
# Read data
super <- read.csv("2013Coupes.csv")
dat <- filter(super,Price < 100000)
Identify Variables
#### Assign the mean to a variable
m <- mean(dat$Price)
#### Create dataframe of values below the mean
ltm <- filter(dat,dat$Price < m)
#### Calculate the size and assign it to a variable
s <- length(dat$Price)
#### Calculate p and assign it to a variable
p <- length(ltm$Price)/s
#### Calculate q and assign it to a variable
q <- 1-p
#### Return results
df <- data.frame(s,p,q)
kable(df)
Problem 1: If you were to find another random sample of 10 cars
based on the same data, what is the probability that exactly 4 of them
will fall below the average? .
# Note: dbinom(x,size,prob) returns P(X=x)
## Calculate probability as decimal
p1 <- dbinom(4,s,p)
## Interpret results
cat("There is a",round(p1*100,digits = 2),"% probability that exactly 5 cars will fall below average.")
## There is a 20.51 % probability that exactly 5 cars will fall below average.
Problem 2: If you were to find another random sample of 10 cars
based on the same data, what is the probability that fewer than 5 of
them will fall below the average?
# Note: pbinom(x,size,prob) returns P(X <= x)
# Note: P(X < x) = P(X <= x -1)
## Calculate probability as decimal
p2 <- pbinom(5-1,s,p)
## Interpret results
cat("There is a",round(p2*100,digits = 2),"% probability that fewer than 5 of the cars will fall below average.")
## There is a 37.7 % probability that fewer than 5 of the cars will fall below average.
Problem 3: If you were to find another random sample of 10 cars
based on the same data, what is the probability that more than 6 of them
will fall below the average?
# Note: pbinom(x,size,prob) returns P(X <= x)
# Note: P(X > x) = 1- P(X <= x)
## Calculate probability as decimal
p3 <- 1 - pbinom(6,s,p)
## Interpret results
cat("There is a",round(p3*100,digits = 2),"% probability more than 6 of the cars will fall below average.")
## There is a 17.19 % probability more than 6 of the cars will fall below average.
Problem 4: If you were to find another random sample of 10 cars
based on the same data, what is the probability that at least 4 of them
will fall below the average?
# Note: pbinom(x,size,prob) returns P(X <= x)
# Note: P(X => x) = 1 - P(X <= x-1)
## Calculate probability as decimal
p4 <- 1 - pbinom(4-1,s,p)
cat("There is a",round(p4*100,digits = 2),"% probability that at least 4 of the cars will fall below average.")
## There is a 82.81 % probability that at least 4 of the cars will fall below average.
Reference
kable(dat)
| Coupe |
2013 |
Jaguar |
XK |
21807 |
16 |
24 |
385 |
8 |
| Coupe |
2013 |
Chevrolet |
Camero |
27795 |
15 |
24 |
426 |
8 |
| Coupe |
2013 |
Ford |
Mustang |
29145 |
15 |
26 |
420 |
8 |
| Coupe |
2013 |
Mercedes |
E550 |
14403 |
17 |
27 |
402 |
8 |
| Coupe |
2013 |
Audi |
S5 |
17209 |
18 |
28 |
333 |
6 |
| Coupe |
2013 |
BMW |
M3 |
25732 |
14 |
20 |
414 |
8 |
| Coupe |
2013 |
Mini |
Coupe 2D |
13674 |
26 |
35 |
208 |
4 |
| Coupe |
2013 |
Dodge |
Challenger |
13774 |
16 |
25 |
375 |
8 |
| Coupe |
2013 |
Cadillac |
CTS-V |
27742 |
12 |
18 |
556 |
8 |
| Coupe |
2013 |
Nissan |
370Z |
20177 |
19 |
26 |
332 |
6 |