Prove the following; for every n ≥ 1 and ε > 0. If ε > θ , P ( θ − ε ≤ Y ( n ) ≤ θ + ε ) = 1. If ε < θ , P ( θ − ε ≤ Y ( n ) ≤ θ + ε ) = 1 − [ θ − ε θ ] n .

Question

Want to see more full solutions like this?

Answer 1

Question

Chapter 9.3, Problem 26E

a.

To determine

Prove the following; for every n≥1 and ε>0.

If ε>θ, P(θ−ε≤Y(n)≤θ+ε)=1.

If ε<θ, P(θ−ε≤Y(n)≤θ+ε)=1−[θ−εθ]n.

a.

Expert Solution

Answer to Problem 26E

It is proved that for every n≥1 and ε>0.

If ε>θ, P(θ−ε≤Y(n)≤θ+ε)=1.
If ε<θ, P(θ−ε≤Y(n)≤θ+ε)=1−[θ−εθ]n.

Explanation of Solution

It is given that Y1,Y2,...,Yn denote a random sample from the uniform distribution on the interval (0,θ).

Consider Y(n)=max(Y1,Y2,...,Yn) the cumulative distribution function of Y(n) is given below:

F(n)(y)={0 ; y<θ(yθ)n ; 0≤y≤θ1 ; y>θ

Now, consider n≥1 and ε>0.

P(|Y(n)−θ| ≤ε)=P(θ−ε≤Y(n)≤θ+ε)=F(n)(θ+ε)−F(n)(θ−ε)

If ε>θ then, F(n)(θ+ε)=1 and F(n)(θ−ε)=0. Therefore,

P(|Y(n)−θ| ≤ε)=1−0=1

If ε<θ then, F(n)(θ+ε)=1 and F(n)(θ−ε)=(θ−εθ)n. Therefore,

P(|Y(n)−θ| ≤ε)=1−(θ−εθ)n.

Thus, for every n≥1 and ε>0.

If ε>θ, P(θ−ε≤Y(n)≤θ+ε)=1.
If ε<θ, P(θ−ε≤Y(n)≤θ+ε)=1−[θ−εθ]n.

b.

To determine

Prove that Y(n) is a consistent estimator of θ by showing that for every ε>0, limn→∞P(|Y(n)−θ| ≤ε)=1.

b.

Expert Solution

Answer to Problem 26E

It is proved that Y(n) is a consistent estimator of θ.

Explanation of Solution

From Part (a), if ε>θ, then

P(|Y(n)−θ| ≤ε)=1limn→∞P(|Y(n)−θ| ≤ε)=limn→∞(1)=1

From Part (a), if ε<θ, then

P(|Y(n)−θ| ≤ε)=1−[θ−εθ]nlimn→∞P(|Y(n)−θ| ≤ε)=limn→∞(1−[θ−εθ]n)=1−limn→∞([θ−εθ]n)

Since ε>θ, therefore, 0<θ−εθ<1.

Hence, limn→∞([θ−εθ]n)=0.

Therefore,

limn→∞P(|Y(n)−θ| ≤ε)=1−0=1.

Hence, for every ε>0, limn→∞P(|Y(n)−θ| ≤ε)=1.

Thus, Y(n) is a consistent estimator of θ.

Want to see more full solutions like this?

Subscribe now to access step-by-step solutions to millions of textbook problems written by subject matter experts!

Students have asked these similar questions

Cycles to failure Position in ascending order 0.5 f(x)) (x;) Problem 44 Marsha, a renowned cake scientist, is trying to determine how long different cakes can survive intense fork attacks before collapsing into crumbs. To simulate real-world cake consumption, she designs a test where cakes are subjected to repeated fork stabs and bites, mimicking the brutal reality of birthday parties. After rigorous testing, Marsha records 10 observations of how many stabs each cake endured before structural failure. Construct P-P plots for (a.) a normal distribution, (b.) a lognormal distribution, and (c.) a Weibull distribution (using the information included in the table below). Which distribution seems to be the best model for the cycles to failure for this material? Explain your answer in detail. Observation Empirical cumulative Probability distribution Cumulative distribution Inverse of cumulative distribution F-1 (-0.5) F(x)) (S) n 4 3 1 0.05 9 5 2 0.15 7 7 3 0.25 1 10 4 0.35 3 12 5 0.45 Normal…

Problem 3 In their lab, engineer Daniel and Paulina are desperately trying to perfect time travel. But the problem is that their machine still struggles with power inconsistencies-sometimes generating too little energy, other times too much, causing unstable time jumps. To prevent catastrophic misjumps into the Jurassic era or the far future, they must calibrate the machine's power output. After extensive testing, they found that the time machine's power output follows a normal distribution, with an average energy level of 8.7 gigawatts and a standard deviation of 1.2 gigawatts. The Time Travel Safety Board has set strict guidelines: For a successful time jump, the machine's power must be between 8.5 and 9.5 gigawatts. What is the probability that a randomly selected time jump meets this precision requirement? Daniel suggests that adjusting the mean power output could improve time-travel accuracy. Can adjusting the mean reduce the number of dangerous misjumps? If yes, what should the…

Problem 5 ( Marybeth is also interested in the experiment from Problem 2 (associated with the enhancements for Captain America's shield), so she decides to start a detailed literature review on the subject. Among others, she found a paper where they used a 2"(4-1) fractional factorial design in the factors: (A) shield material, (B) throwing mechanism, (C) edge modification, and (D) handle adjustment. The experimental design used in the paper is shown in the table below. a. Run A B с D 1 (1) -1 -1 -1 1 2 a 1 -1 -1 1 3 bd -1 1 -1 1 4 abd 1 1 -1 1 5 cd -1 -1 1 -1 6 acd 1 -1 1 -1 7 bc -1 1 1 -1 abc 1 1 1 -1 paper? s) What was the generator used in the 2"(4-1) fractional factorial design described in the b. Based on the resolution of this design, what do you think about the generator used in the paper? Do you think it was a good choice, or would you have selected a different one? Explain your answer in detail.

Answer 2

Question

Chapter 9.3, Problem 26E

a.

To determine

Prove the following; for every n≥1 and ε>0.

If ε>θ, P(θ−ε≤Y(n)≤θ+ε)=1.

If ε<θ, P(θ−ε≤Y(n)≤θ+ε)=1−[θ−εθ]n.

a.

Expert Solution

Answer to Problem 26E

It is proved that for every n≥1 and ε>0.

If ε>θ, P(θ−ε≤Y(n)≤θ+ε)=1.
If ε<θ, P(θ−ε≤Y(n)≤θ+ε)=1−[θ−εθ]n.

Explanation of Solution

It is given that Y1,Y2,...,Yn denote a random sample from the uniform distribution on the interval (0,θ).

Consider Y(n)=max(Y1,Y2,...,Yn) the cumulative distribution function of Y(n) is given below:

F(n)(y)={0 ; y<θ(yθ)n ; 0≤y≤θ1 ; y>θ

Now, consider n≥1 and ε>0.

P(|Y(n)−θ| ≤ε)=P(θ−ε≤Y(n)≤θ+ε)=F(n)(θ+ε)−F(n)(θ−ε)

If ε>θ then, F(n)(θ+ε)=1 and F(n)(θ−ε)=0. Therefore,

P(|Y(n)−θ| ≤ε)=1−0=1

If ε<θ then, F(n)(θ+ε)=1 and F(n)(θ−ε)=(θ−εθ)n. Therefore,

P(|Y(n)−θ| ≤ε)=1−(θ−εθ)n.

Thus, for every n≥1 and ε>0.

If ε>θ, P(θ−ε≤Y(n)≤θ+ε)=1.
If ε<θ, P(θ−ε≤Y(n)≤θ+ε)=1−[θ−εθ]n.

b.

To determine

Prove that Y(n) is a consistent estimator of θ by showing that for every ε>0, limn→∞P(|Y(n)−θ| ≤ε)=1.

b.

Expert Solution

Answer to Problem 26E

It is proved that Y(n) is a consistent estimator of θ.

Explanation of Solution

From Part (a), if ε>θ, then

P(|Y(n)−θ| ≤ε)=1limn→∞P(|Y(n)−θ| ≤ε)=limn→∞(1)=1

From Part (a), if ε<θ, then

P(|Y(n)−θ| ≤ε)=1−[θ−εθ]nlimn→∞P(|Y(n)−θ| ≤ε)=limn→∞(1−[θ−εθ]n)=1−limn→∞([θ−εθ]n)

Since ε>θ, therefore, 0<θ−εθ<1.

Hence, limn→∞([θ−εθ]n)=0.

Therefore,

limn→∞P(|Y(n)−θ| ≤ε)=1−0=1.

Hence, for every ε>0, limn→∞P(|Y(n)−θ| ≤ε)=1.

Thus, Y(n) is a consistent estimator of θ.

Want to see more full solutions like this?

Subscribe now to access step-by-step solutions to millions of textbook problems written by subject matter experts!

Answer 3

Question

Chapter 9.3, Problem 26E

a.

To determine

Prove the following; for every n≥1 and ε>0.

If ε>θ, P(θ−ε≤Y(n)≤θ+ε)=1.

If ε<θ, P(θ−ε≤Y(n)≤θ+ε)=1−[θ−εθ]n.

a.

Expert Solution

Answer to Problem 26E

It is proved that for every n≥1 and ε>0.

If ε>θ, P(θ−ε≤Y(n)≤θ+ε)=1.
If ε<θ, P(θ−ε≤Y(n)≤θ+ε)=1−[θ−εθ]n.

Explanation of Solution

It is given that Y1,Y2,...,Yn denote a random sample from the uniform distribution on the interval (0,θ).

Consider Y(n)=max(Y1,Y2,...,Yn) the cumulative distribution function of Y(n) is given below:

F(n)(y)={0 ; y<θ(yθ)n ; 0≤y≤θ1 ; y>θ

Now, consider n≥1 and ε>0.

P(|Y(n)−θ| ≤ε)=P(θ−ε≤Y(n)≤θ+ε)=F(n)(θ+ε)−F(n)(θ−ε)

If ε>θ then, F(n)(θ+ε)=1 and F(n)(θ−ε)=0. Therefore,

P(|Y(n)−θ| ≤ε)=1−0=1

If ε<θ then, F(n)(θ+ε)=1 and F(n)(θ−ε)=(θ−εθ)n. Therefore,

P(|Y(n)−θ| ≤ε)=1−(θ−εθ)n.

Thus, for every n≥1 and ε>0.

If ε>θ, P(θ−ε≤Y(n)≤θ+ε)=1.
If ε<θ, P(θ−ε≤Y(n)≤θ+ε)=1−[θ−εθ]n.

b.

To determine

Prove that Y(n) is a consistent estimator of θ by showing that for every ε>0, limn→∞P(|Y(n)−θ| ≤ε)=1.

b.

Expert Solution

Answer to Problem 26E

It is proved that Y(n) is a consistent estimator of θ.

Explanation of Solution

From Part (a), if ε>θ, then

P(|Y(n)−θ| ≤ε)=1limn→∞P(|Y(n)−θ| ≤ε)=limn→∞(1)=1

From Part (a), if ε<θ, then

P(|Y(n)−θ| ≤ε)=1−[θ−εθ]nlimn→∞P(|Y(n)−θ| ≤ε)=limn→∞(1−[θ−εθ]n)=1−limn→∞([θ−εθ]n)

Since ε>θ, therefore, 0<θ−εθ<1.

Hence, limn→∞([θ−εθ]n)=0.

Therefore,

limn→∞P(|Y(n)−θ| ≤ε)=1−0=1.

Hence, for every ε>0, limn→∞P(|Y(n)−θ| ≤ε)=1.

Thus, Y(n) is a consistent estimator of θ.

Want to see more full solutions like this?

Subscribe now to access step-by-step solutions to millions of textbook problems written by subject matter experts!

Answer 4

Question

Chapter 9.3, Problem 26E

a.

To determine

Prove the following; for every n≥1 and ε>0.

If ε>θ, P(θ−ε≤Y(n)≤θ+ε)=1.

If ε<θ, P(θ−ε≤Y(n)≤θ+ε)=1−[θ−εθ]n.

a.

Expert Solution

Answer to Problem 26E

It is proved that for every n≥1 and ε>0.

If ε>θ, P(θ−ε≤Y(n)≤θ+ε)=1.
If ε<θ, P(θ−ε≤Y(n)≤θ+ε)=1−[θ−εθ]n.

Explanation of Solution

It is given that Y1,Y2,...,Yn denote a random sample from the uniform distribution on the interval (0,θ).

Consider Y(n)=max(Y1,Y2,...,Yn) the cumulative distribution function of Y(n) is given below:

F(n)(y)={0 ; y<θ(yθ)n ; 0≤y≤θ1 ; y>θ

Now, consider n≥1 and ε>0.

P(|Y(n)−θ| ≤ε)=P(θ−ε≤Y(n)≤θ+ε)=F(n)(θ+ε)−F(n)(θ−ε)

If ε>θ then, F(n)(θ+ε)=1 and F(n)(θ−ε)=0. Therefore,

P(|Y(n)−θ| ≤ε)=1−0=1

If ε<θ then, F(n)(θ+ε)=1 and F(n)(θ−ε)=(θ−εθ)n. Therefore,

P(|Y(n)−θ| ≤ε)=1−(θ−εθ)n.

Thus, for every n≥1 and ε>0.

If ε>θ, P(θ−ε≤Y(n)≤θ+ε)=1.
If ε<θ, P(θ−ε≤Y(n)≤θ+ε)=1−[θ−εθ]n.

b.

To determine

Prove that Y(n) is a consistent estimator of θ by showing that for every ε>0, limn→∞P(|Y(n)−θ| ≤ε)=1.

b.

Expert Solution

Answer to Problem 26E

It is proved that Y(n) is a consistent estimator of θ.

Explanation of Solution

From Part (a), if ε>θ, then

P(|Y(n)−θ| ≤ε)=1limn→∞P(|Y(n)−θ| ≤ε)=limn→∞(1)=1

From Part (a), if ε<θ, then

P(|Y(n)−θ| ≤ε)=1−[θ−εθ]nlimn→∞P(|Y(n)−θ| ≤ε)=limn→∞(1−[θ−εθ]n)=1−limn→∞([θ−εθ]n)

Since ε>θ, therefore, 0<θ−εθ<1.

Hence, limn→∞([θ−εθ]n)=0.

Therefore,

limn→∞P(|Y(n)−θ| ≤ε)=1−0=1.

Hence, for every ε>0, limn→∞P(|Y(n)−θ| ≤ε)=1.

Thus, Y(n) is a consistent estimator of θ.

Want to see more full solutions like this?

Subscribe now to access step-by-step solutions to millions of textbook problems written by subject matter experts!

Answer 5

Chapter 9.3, Problem 26E

a.

To determine

Prove the following; for every n≥1 and ε>0.

If ε>θ, P(θ−ε≤Y(n)≤θ+ε)=1.

If ε<θ, P(θ−ε≤Y(n)≤θ+ε)=1−[θ−εθ]n.

a.

Expert Solution

Answer to Problem 26E

It is proved that for every n≥1 and ε>0.

If ε>θ, P(θ−ε≤Y(n)≤θ+ε)=1.
If ε<θ, P(θ−ε≤Y(n)≤θ+ε)=1−[θ−εθ]n.

Explanation of Solution

It is given that Y1,Y2,...,Yn denote a random sample from the uniform distribution on the interval (0,θ).

Consider Y(n)=max(Y1,Y2,...,Yn) the cumulative distribution function of Y(n) is given below:

F(n)(y)={0 ; y<θ(yθ)n ; 0≤y≤θ1 ; y>θ

Now, consider n≥1 and ε>0.

P(|Y(n)−θ| ≤ε)=P(θ−ε≤Y(n)≤θ+ε)=F(n)(θ+ε)−F(n)(θ−ε)

If ε>θ then, F(n)(θ+ε)=1 and F(n)(θ−ε)=0. Therefore,

P(|Y(n)−θ| ≤ε)=1−0=1

If ε<θ then, F(n)(θ+ε)=1 and F(n)(θ−ε)=(θ−εθ)n. Therefore,

P(|Y(n)−θ| ≤ε)=1−(θ−εθ)n.

Thus, for every n≥1 and ε>0.

If ε>θ, P(θ−ε≤Y(n)≤θ+ε)=1.
If ε<θ, P(θ−ε≤Y(n)≤θ+ε)=1−[θ−εθ]n.

b.

To determine

Prove that Y(n) is a consistent estimator of θ by showing that for every ε>0, limn→∞P(|Y(n)−θ| ≤ε)=1.

b.

Expert Solution

Answer to Problem 26E

It is proved that Y(n) is a consistent estimator of θ.

Explanation of Solution

From Part (a), if ε>θ, then

P(|Y(n)−θ| ≤ε)=1limn→∞P(|Y(n)−θ| ≤ε)=limn→∞(1)=1

From Part (a), if ε<θ, then

P(|Y(n)−θ| ≤ε)=1−[θ−εθ]nlimn→∞P(|Y(n)−θ| ≤ε)=limn→∞(1−[θ−εθ]n)=1−limn→∞([θ−εθ]n)

Since ε>θ, therefore, 0<θ−εθ<1.

Hence, limn→∞([θ−εθ]n)=0.

Therefore,

limn→∞P(|Y(n)−θ| ≤ε)=1−0=1.

Hence, for every ε>0, limn→∞P(|Y(n)−θ| ≤ε)=1.

Thus, Y(n) is a consistent estimator of θ.

Answer 6

Chapter 9.3, Problem 26E

a.

To determine

Prove the following; for every n≥1 and ε>0.

If ε>θ, P(θ−ε≤Y(n)≤θ+ε)=1.

If ε<θ, P(θ−ε≤Y(n)≤θ+ε)=1−[θ−εθ]n.

a.

Expert Solution

Answer to Problem 26E

It is proved that for every n≥1 and ε>0.

If ε>θ, P(θ−ε≤Y(n)≤θ+ε)=1.
If ε<θ, P(θ−ε≤Y(n)≤θ+ε)=1−[θ−εθ]n.

Explanation of Solution

It is given that Y1,Y2,...,Yn denote a random sample from the uniform distribution on the interval (0,θ).

Consider Y(n)=max(Y1,Y2,...,Yn) the cumulative distribution function of Y(n) is given below:

F(n)(y)={0 ; y<θ(yθ)n ; 0≤y≤θ1 ; y>θ

Now, consider n≥1 and ε>0.

P(|Y(n)−θ| ≤ε)=P(θ−ε≤Y(n)≤θ+ε)=F(n)(θ+ε)−F(n)(θ−ε)

If ε>θ then, F(n)(θ+ε)=1 and F(n)(θ−ε)=0. Therefore,

P(|Y(n)−θ| ≤ε)=1−0=1

If ε<θ then, F(n)(θ+ε)=1 and F(n)(θ−ε)=(θ−εθ)n. Therefore,

P(|Y(n)−θ| ≤ε)=1−(θ−εθ)n.

Thus, for every n≥1 and ε>0.

If ε>θ, P(θ−ε≤Y(n)≤θ+ε)=1.
If ε<θ, P(θ−ε≤Y(n)≤θ+ε)=1−[θ−εθ]n.

Answer 7

Chapter 9.3, Problem 26E

a.

To determine

Prove the following; for every n≥1 and ε>0.

If ε>θ, P(θ−ε≤Y(n)≤θ+ε)=1.

If ε<θ, P(θ−ε≤Y(n)≤θ+ε)=1−[θ−εθ]n.

Answer 8

a.

Expert Solution

Answer to Problem 26E

It is proved that for every n≥1 and ε>0.

If ε>θ, P(θ−ε≤Y(n)≤θ+ε)=1.
If ε<θ, P(θ−ε≤Y(n)≤θ+ε)=1−[θ−εθ]n.

Answer 9

a.

Expert Solution

Answer 10

a.

Expert Solution

Answer 11

Expert Solution

Answer 12

Explanation of Solution

It is given that Y1,Y2,...,Yn denote a random sample from the uniform distribution on the interval (0,θ).

Consider Y(n)=max(Y1,Y2,...,Yn) the cumulative distribution function of Y(n) is given below:

F(n)(y)={0 ; y<θ(yθ)n ; 0≤y≤θ1 ; y>θ

Now, consider n≥1 and ε>0.

P(|Y(n)−θ| ≤ε)=P(θ−ε≤Y(n)≤θ+ε)=F(n)(θ+ε)−F(n)(θ−ε)

If ε>θ then, F(n)(θ+ε)=1 and F(n)(θ−ε)=0. Therefore,

P(|Y(n)−θ| ≤ε)=1−0=1

If ε<θ then, F(n)(θ+ε)=1 and F(n)(θ−ε)=(θ−εθ)n. Therefore,

P(|Y(n)−θ| ≤ε)=1−(θ−εθ)n.

Thus, for every n≥1 and ε>0.

If ε>θ, P(θ−ε≤Y(n)≤θ+ε)=1.
If ε<θ, P(θ−ε≤Y(n)≤θ+ε)=1−[θ−εθ]n.

Answer 13

b.

To determine

Prove that Y(n) is a consistent estimator of θ by showing that for every ε>0, limn→∞P(|Y(n)−θ| ≤ε)=1.

b.

Expert Solution

Answer to Problem 26E

It is proved that Y(n) is a consistent estimator of θ.

Explanation of Solution

From Part (a), if ε>θ, then

P(|Y(n)−θ| ≤ε)=1limn→∞P(|Y(n)−θ| ≤ε)=limn→∞(1)=1

From Part (a), if ε<θ, then

P(|Y(n)−θ| ≤ε)=1−[θ−εθ]nlimn→∞P(|Y(n)−θ| ≤ε)=limn→∞(1−[θ−εθ]n)=1−limn→∞([θ−εθ]n)

Since ε>θ, therefore, 0<θ−εθ<1.

Hence, limn→∞([θ−εθ]n)=0.

Therefore,

limn→∞P(|Y(n)−θ| ≤ε)=1−0=1.

Hence, for every ε>0, limn→∞P(|Y(n)−θ| ≤ε)=1.

Thus, Y(n) is a consistent estimator of θ.

Answer 14

b.

To determine

Prove that Y(n) is a consistent estimator of θ by showing that for every ε>0, limn→∞P(|Y(n)−θ| ≤ε)=1.

Answer 15

b.

Expert Solution

Answer to Problem 26E

It is proved that Y(n) is a consistent estimator of θ.

Answer 16

b.

Expert Solution

Answer 17

b.

Expert Solution

Answer 18

Expert Solution

Answer 19

Explanation of Solution

From Part (a), if ε>θ, then

P(|Y(n)−θ| ≤ε)=1limn→∞P(|Y(n)−θ| ≤ε)=limn→∞(1)=1

From Part (a), if ε<θ, then

P(|Y(n)−θ| ≤ε)=1−[θ−εθ]nlimn→∞P(|Y(n)−θ| ≤ε)=limn→∞(1−[θ−εθ]n)=1−limn→∞([θ−εθ]n)

Since ε>θ, therefore, 0<θ−εθ<1.

Hence, limn→∞([θ−εθ]n)=0.

Therefore,

limn→∞P(|Y(n)−θ| ≤ε)=1−0=1.

Hence, for every ε>0, limn→∞P(|Y(n)−θ| ≤ε)=1.

Thus, Y(n) is a consistent estimator of θ.

Answer 20

Ch. 9.2 - Prob. 1E Ch. 9.2 - Let Y1, Y2,, Yn denote a random sample from a...Ch. 9.2 - Let Y1, Y2, , Yn denote a random sample from the...Ch. 9.2 - Let Y1, Y2, , Yn denote a random sample of size n...Ch. 9.2 - Suppose that Y1, Y2, , Yn is a random sample from...Ch. 9.2 - Prob. 6E Ch. 9.2 - Prob. 7E Ch. 9.2 - Let Y1, Y2, , Yn denote a random sample from a...Ch. 9.3 - Applet Exercise How was Figure 9.1 obtained?...Ch. 9.3 - Applet Exercise Refer to Exercise 9.9. Scroll down...

Prove the following; for every n ≥ 1 and ε &gt; 0. If ε &gt; θ , P ( θ − ε ≤ Y ( n ) ≤ θ + ε ) = 1. If ε &lt; θ , P ( θ − ε ≤ Y ( n ) ≤ θ + ε ) = 1 − [ θ − ε θ ] n .

Prove the following; for every n≥1 and ε>0. If ε>θ, P(θ−ε≤Y(n)≤θ+ε)=1. If ε<θ, P(θ−ε≤Y(n)≤θ+ε)=1−[θ−εθ]n.

Answer to Problem 26E

Explanation of Solution

Prove that Y(n) is a consistent estimator of θ by showing that for every ε>0, limn→∞P(|Y(n)−θ| ≤ε)=1.

Answer to Problem 26E

Explanation of Solution

Want to see more full solutions like this?

Chapter 9 Solutions

Prove the following; for every n ≥ 1 and ε > 0. If ε > θ , P ( θ − ε ≤ Y ( n ) ≤ θ + ε ) = 1. If ε < θ , P ( θ − ε ≤ Y ( n ) ≤ θ + ε ) = 1 − [ θ − ε θ ] n .

Prove the following; for every n≥1 and ε>0.

If ε>θ, P(θ−ε≤Y(n)≤θ+ε)=1.

If ε<θ, P(θ−ε≤Y(n)≤θ+ε)=1−[θ−εθ]n.