Suppose that 50% of this population prefers the color red. If 20 buyers are randomly selected, what is the probability that between 9 and 12 (both inclusive) buyers would prefer red?
#Sample size
n <- 20
#probability of buyers preference for a red car
x <- 9:12
# 50% prefer the color red
pi <- 0.5
#math equation
#P( x= 9:12 | n = 20 pi = 0.5)
#Binomial distribution
dbinom1 <- dbinom(x,n,pi)
result <- sum(dbinom1)
print(round(result, digits = 4))
## [1] 0.6167
pro1 <- result * 100
print("the probability of choosing a red car between 9 and 12 is 61%")
## [1] "the probability of choosing a red car between 9 and 12 is 61%"
?plot
## Help on topic 'plot' was found in the following packages:
##
## Package Library
## graphics /Library/Frameworks/R.framework/Versions/4.2-arm64/Resources/library
## base /Library/Frameworks/R.framework/Resources/library
##
##
## Using the first match ...
plot(x = 9:12,
y = dbinom(x = 9:12,
size = 20,
prob = .5
),
type = 'h',
main = 'Binomial Distribution (n=20, p=0.5)',
ylab = 'Probability',
xlab = '# Successes',
lwd = 3
)
Suppose 20% of the bulbs in the lot are defective. What is the probability that less than 6 but more than 3 bulbs from the sample are defective?
#binomial distribution
#sample size
n2 <- 13
#probability of defective bulbs
pi2 <- 0.2
#less than 5 but more than 3 bulbs
x2 <- 4:5
#math equation
# P( x = 4:5 | n = 13, pi = 0.2)
?dbinom
dbinom2 <- dbinom( x2, n2, pi2)
result2 <- sum(dbinom2)
print(round(result2, digits = 4))
## [1] 0.2226
plot(x = 0:13,
y = dbinom(x = 0:13,
size = 13,
prob = .2
),
type = 'h',
main = 'Binomial Distribution (n=13, p=0.2)',
ylab = 'Probability',
xlab = '# Successes',
lwd = 3
)
What is the probability that, for any day, the number of special orders sent out will be no more than 3?
#Poisson distribution
# Set the variables
x3 <- 3
mean3 <- 4.2
#math equation
# P( x < 3| lambda = 4.2)
?ppois
ppois3 <- ppois( q = 3, lambda = 4.2, lower.tail = TRUE)
result3 <- round(ppois3, digits = 4)
result3
## [1] 0.3954
# double checking results
sum(dpois(x=0:3, lambda = 4.2))
## [1] 0.3954034
#hyper geometric distribution
#Set up the Variables
N4 <- 17 #population size
n4 <- 3 # sample size
s4 <- 6 # number of success in population
f4 <- 11 # failure in population F = N - S
#Math equation
#P( x < 2 | s=6, f=11, n=3)
# on the dhyper fun x = success in sample, m = success in population
# n = failure in population, k = sample size
?dhyper
result4 <- sum(dhyper(x = 0:1, m = 6, n = 11, k = 3))
result4
## [1] 0.7279412
print(paste0("the result is ", round(x = result4, digits = 7)))
## [1] "the result is 0.7279412"
The town had 6 employees over 50 years of age and 19 under 50. If the dismissed employees were selected at random, what is the probability that more than 1 employee was over 50?
# Hypergeometric distribution
# identify the variables
# let x be the random variable of employees over fifty
N5 <- 25
S5 <- 6
n5 <- 6
F5 <- 19
# Math equation
#P(x > 1 | s = 6, f = 19, n = 6)
result5 <- sum(dhyper(x = 2:6, m = 6, n = 19, k = 6))
result5
## [1] 0.4528515
#identify the variables
var <- 90000
mean <- 800
sd <- sqrt(90000)
#math equation
#P(1040 < x < 1460 | mean = 800, standard deviation = 300 )
#best method dont use sum(dnorm) because it will give you a close aprox
?pnorm
result6 <- pnorm(q = 1460, mean = mean, sd = sd) - pnorm(q=1040, mean = mean, sd = sd)
result6
## [1] 0.197952
#identify the variables
mean7 <- 106
sd7 <- 4
#math equation
#P(103 < x < 111| mean = 106, sd = 4)
result7 <- pnorm(q = 111, mean = 106, sd = 4) - pnorm(q=103, mean = 106, sd = 4)
result7
## [1] 0.6677229
#Shorter way of getting the solution
?diff
diff( x = pnorm(c(103,111), mean = 106, sd = 4))
## [1] 0.6677229
#identify the variables
#quantile function
mean8 <- 3.34
sd8 <- 0.07
?qnorm
topqnorm <- qnorm(p = 0.97, mean = 3.34, sd = 0.07)
topqnorm
## [1] 3.471656
lowerqnorm <- qnorm(p = 0.03, mean = 3.34, sd = 0.07)
lowerqnorm
## [1] 3.208344
round(x = c((lowerqnorm), (topqnorm)), digits = 3)
## [1] 3.208 3.472
scheme.
A: Top 9% of scores
B: Scores below the top 9% and above the bottom 63%
C: Scores below the top 37% and above the bottom 17%
D: Scores below the top 83% and above the bottom 8%
F: Bottom 8% of scores
Scores on the test are normally distributed with a mean of 75.8 and a
standard
deviation of 8.1. Find the minimum score required for an A grade.
#identify the variables
mean9 <- 75.8
sd9 <- 8.1
#minimum score will be on the 91 percentile
result9 <- qnorm(p = 0.91, mean = 75.8, sd = 8.1)
result9
## [1] 86.66012
round(result9)
## [1] 87
Assume the probability that a given computer will not crash in a day
is 61%.
Approximate the probability using the normal distribution.
#identify the variables
n <- 155
pi <- 0.61
#we know the formulas to calculate the mean and the sd
mean10 <- pi * n
sd10 <- sqrt(pi * (1-pi) * n)
# Math equation
# P( x = 96 | pi = 0.61, n = 155)
result10 <- dnorm(x = 96, , mean = 0.61 * 155 , sd = sqrt(0.61 * 0.39 * 155))
result10
## [1] 0.06385071