From exercise 10, the minimum value has mean = \(\mu\)/\(n\)
Here, \(\mu\) \(=\) \(1000\) \(and\) \(n\) \(=\) \(100\)
Therefore, the expected time for the first of the given bulbs to burn out is \(1000\)/\(100\) \(=\) \(10\) \(hours\)
set.seed(158)
# Number of lightbulbs
n <- 100
# Failure rate
lambda <- 1/1000
# Simulating the lifetime of the lightbulbs
lifetime <- rexp(n, lambda)
# Expected time to burn out the first lightbulb
first_lightbulb_burnout_time <- min(lifetime)
first_lightbulb_burnout_time
## [1] 8.093611
Density function of Z = X1 - X2 can be found by using the convolution formula:
fZ(z) = \(\int\) fX1(t) fX2(z-t) dt, where fX1 and fX2 are the density functions of X1 and X2 respectively
As X1 and X2 are both exponentially distributed with parameter \(\lambda\), their density functions are:
fX1(x) = \(\lambda\)e^(-\(\lambda\)x), for x >= 0
fX2(x) = \(\lambda\)e^(-\(\lambda\)x), for x >= 0
Substituting these expressions into the convolution formula:
fZ(z) = \(\int\) \(\lambda\)e^(-\(\lambda\)t) \(\lambda\)e^(-\(\lambda\)(z-t)) dt
By simplifying:
fZ(z) = \(\lambda\)^2 \(\int\) e^(-\(\lambda\)t) e^(-\(\lambda\)z+\(\lambda\)t) dt
fZ(z) = \(\lambda\)^2 \(\int\) e^(-\(\lambda\)z) dt
fZ(z) = \(\lambda\)^2 e^(-\(\lambda\)z) \(\int\)dt
fZ(z) = \(\lambda\)^2 e^(-\(\lambda\)z) t / |t| from -\(\infty\) to +\(\infty\)
we have to consider here two cases: one where t is positive and another one where t is negative.By simplifying the above expression further we get:
fZ(z)= (\(\lambda\)^2/2) e^(-\(\lambda\)|z|)
Therefore, the density function of Z is:
fZ(z) = (1/2)\(\lambda\)e^(-\(\lambda\)|z|)
µ<-10
σ <-sqrt(100/3)
kσ<-2
k<-2/σ
upper_a<-1/k^2
round(upper_a,2)
## [1] 8.33
kσ<- 5
k<-5/σ
upper_b<-1/k^2
round(upper_b,2)
## [1] 1.33
kσ<-9
k<-9/σ
upper_c<-1/k^2
round(upper_c,2)
## [1] 0.41
kσ<-20
k<-20/σ
upper_d<-1/k^2
round(upper_d,2)
## [1] 0.08