Week 2 Homework - Summer 2020: Attempt History

8/3/2020 Week 2 Homework - Summer 2020: Simulation and Modeling for Engineering and Science - ISYE-6644-OAN/O01
Week 2 Homework - Summer 2020

Due May 29 at 11:59pm Points 33 Questions 33
Available May 22 at 8am - May 29 at 11:59pm 8 days Time Limit None
Instructions
Please answer all the questions below.
This quiz was locked May 29 at 11:59pm.
Attempt History
Attempt Time Score
LATEST Attempt 1 1,779 minutes 27 out of 33
Score for this quiz: 27 out of 33

Submitted May 29 at 4:59am
This attempt took 1,779 minutes.
Question 1 1 / 1 pts
(Lesson 2.1: Derivatives.) BONUS: If , find the

derivative .
a.
b.
Correct! c.
This follows by the chain rule,
https://gatech.instructure.com/courses/128642/quizzes/142125?module_item_id=833694 1/27
d.
(c). This follows by the chain rule,
(Lesson 2.1: Derivatives.) BONUS: If , find the

derivative .
a.
b.
c.
Correct!
d.
By the chain rule,
(d). By the chain rule,
(Lesson 2.2: Finding Zeroes.) BONUS: Suppose that

. Use any method you want to find a zero of
, i.e., such that .
a.
b.
c.
Correct! d.
This doesn't take too much work. Namely, set
This is the same as or
(d). This doesn't take too much work. Namely, set
This is the same as or
(Lesson 2.3: Integration.) BONUS: Find
a. 1/2
b. 7/2
c. 7/3
Correct!
d. 13/3
We have
(d). We have
a. 1
b.
Correct!
c. 23.6
We have
d. 46.2
(c). We have
a. 1
Correct!
b. 0
If we let and , then

and
, so that
seems to get us into a 0/0 issue. Thus, we'll need to employ

L'Hôspital's Rule:
c.
d. undetermined
(b). If we let and , then

and
, so that
seems to get us into a 0/0 issue. Thus, we'll need to employ

L'Hôspital's Rule:
(Lesson 2.4: Numerical Integration.) BONUS: Find the approximate value

of the integral using the lesson's form of the Riemann sum
with , and .
a. -2
b. 1/3
Correct!
c. 3/4
We have
Well, this is sort of close to the true integral of 2/3. Of course, we

could've done even better if had been bigger or if we had used the
midpoint of each interval instead of the right endpoint.
d. 3
(c). We have
Well, this is sort of close to the true integral of 2/3. Of course, we

could've done even better if had been bigger or if we had used
the midpoint of each interval instead of the right endpoint.
(Lesson 2.5: Probability Basics.) If and

and are independent, find the probability that exactly one of
and occurs.
a. 0.144
Correct! b. 0.288
You could also have used a binomial distribution argument to solve

this problem,
i.e.,
c. 0.576
d. 0.6
e. I'm from The University Of Georgia. Is the answer -3?
The answer is (b). To see why, note that
You could also have used a binomial distribution argument to solve

this problem,
i.e.,
(Lesson 2.5: Probability Basics.) Toss 3 dice. What's the probability that a
"4" will come up exactly twice?
Correct!
a. 5/72
Write out every possible outcome explicitly, or use the following

binomial argument: Let denote the number of times a "4" comes
up. Clearly,
b. 1/2
c. 13/16
d. 1/8
(a). Write out every possible outcome explicitly, or use the

following binomial argument: Let denote the number of times a
"4" comes up. Clearly,
(Lesson 2.6: Simulating Random Variables.) BONUS: Suppose and

are independent Uniform(0,1) random variables. (You can simulate these
using the RAND() function in Excel, for instance.) Consider the nasty-
looking random variable
where the cosine calculation is carried out in radians (not degrees). Go

ahead and calculate . . . don't be afraid. Now, repeat this task 1000
times (easy to do in Excel) and make a histogram of the 1000 's. What
distribution does this look like?
Correct!
a. Normal
This is the Box-Muller method to generate normal random variables.

We'll learn much more about this later on.
b. Unif(0,1)
c. Exponential
d. Weibull
(a). This is the Box-Muller method to generate normal random

variables. We'll learn much more about this later on. Here's some
example Matlab code that works well. . .
%Matlab code
clear all;close all;clc;
z_vec=zeros(1000,1);
for i = 1:1000
u = rand;
v = rand;
z_vec(i)= sqrt(-2*log(u))*cos(2*pi*v);
end
nbins = 30;
bins = linspace(-5,5,nbins);
histogram(z_vec,bins)
Of course, you can do this easily in R, Excel, Python etc.
(Lesson 2.7: Great Expectations.) Suppose that is a discrete random

variable having with probability 0.2, and with probability
0.8. Find .
a. -1
b. 3
c. 1
Correct!
d. 2.2
So the
answer is (d).
. So the
answer is (d).

0.8. Find .
a. -1
b. 1
Correct!
c. 2.56
In addition to the above work,
so that we have . So the

answer is (c).
d. 5.12
In addition to the above work,
so that we have . So the

answer is (c).

0.8. Find .
a. 3
b.
c. -2
Correct!
d. 44/15
Finally, by LOTUS,
so that . So the answer is (d).
Finally, by LOTUS,
so that . So the answer is (d).
(Lesson 2.7: Great Expectations.) Suppose X is a continuous random

variable with p.d.f. for . Find .
a. 2/3
b. 1
c. 3/2
Correct! d. 2
By LOTUS,
(d) By LOTUS,
(Lesson 2.8: Functions of a Random Variable.) Suppose is the result of

a 5-sided die toss having sides numbered . Find the
probability mass function of .
a.
b.
Correct! c.
This follows because
No other possible values for .
d.
(c). This follows because
No other possible values for .
(Lesson 2.8: Functions of a Random Variable.) Suppose is a

continuous random variable with p.d.f. for . Find
the p.d.f. . (This may be easier than you think.)
orrect Answer a. , for
b. , for
ou Answered c. , for
d. , for
(a). Note that the c.d.f. of is (you can do this in your

head). So by the Inverse Transform Theorem, we immediately
have that is Unif(0,1), with the p.d.f. .
(Lesson 2.9: Jointly Distributed RVs.) Suppose that for

. Find .
a. 1
b. 1/2
c. 1/4
Correct! d. 1/8
So the answer is (d).
(Lesson 2.9: Jointly Distributed RVs.) Suppose that for

. Find the marginal p.d.f. of .
Correct! a. , for
, for
. So the answer is (a).
b. , for
c. , for
d. , for
, for
. So the answer is (a).
(Lesson 2.9: Jointly Distributed RVs.) YES or NO? Suppose and

have joint p.d.f. for ,
, and whatever constant makes the nasty mess integrate to
1. Are and independent?
ou Answered a. Yes
orrect Answer b. No
NO! The lesson has a theorem that says that , are

independent if and only if you can write with
no funny limits for some functions and . Can't do such a
factorization, so and ain't indep.
(Lesson 2.10: Conditional Expectation.) BONUS: Suppose that
for . Hint (you may have seen this

someplace): the marginal p.d.f. of turns out to be
for . Find the conditional p.d.f. of

given that .
orrect Answer a.
ou Answered b.
c.
d.
So the answer is (a).
(Lesson 2.10: Conditional Expectation.) BONUS: Again suppose that
for . Hint (you may already have seen this

someplace): the the marginal p.d.f. of turns out to be
for . Find .
a.
Correct! b.
By the definition of conditional expectation, we have
So the answer is (b).
c.
d.
By the definition of conditional expectation, we have
So the answer is (b).
(Lesson 2.10: Conditional Expectation.) BONUS: Yet again suppose that

for . Hint (you may already have seen this
someplace): the the marginal p.d.f. of turns out to be
for . Find .
a. 1/2
ou Answered b. 2/3
orrect Answer c. 3/4
d. 1
By Law of the Unconscious Statistician and Question 21,
So the answer is (c).
Let's check this answer. First of all, the marginal p.d.f. of is:
Then
Finally, by double expectation, , so

the check works!
(Lesson 2.11: Covariance and Correlation.)

Suppose that the correlation between December snowfall and
temperature in Siberacuse, NY is . Further suppose that
100 in and (degrees F) . Find (in units of
degree inches, whatever those are).
Correct! a. -25
b. -5
c. 5
d. 25
The answer is (a). since
(Lesson 2.11: Covariance and Correlation.) If and both have mean

and variance 4, and , find .
Correct! a. 34
b. 36
c. 40
d. 41
So the answer is (a).
(Lesson 2.12: Probability Distributions.)
You may recall that the p.m.f. of the Geometric distribution is
If the number of orders at a production center this month is a Geom(0.7)

random variable, find the probability that we'll have at most 3 orders.
a. 0.027
b. 0.14
c. 0.86
Correct! d. 0.973
Denote . Then
Denote . Then
(Lesson 2.12: Probability Distributions.) Suppose the SAT math score of

a University of Georgia student can be approximated by a normal
distribution with mean 400 and variance 225. Find the probability that the
UGA Einstein will score at least a 415.
ou Answered a. 0.5
orrect Answer b. 0.1587
c. 0.975
d. 0.8413
This answer is (b). To see why, let denote his score and let
denote a standard normal random variable. Then
where you could've used the back of the book or the NORMSDIST
function in Excel to look up that last probability. (Actually, this is a
famous one, so you may have memorized it).
(Lesson 2.13: Limit Theorems.)

What is the most-important theorem in the universe?
a. Eastern Limit Theorem
Correct! b. Central Limit Theorem
c. Central Limit Serum
d. Central Simit Theorem (simit is a tasty Turkish bagel)
(b).
(Lesson 2.13: Limit Theorems.) If are i.i.d. from some

distribution with mean 1 and variance 400, find the approximate
probability that the sample mean is between 0 and 2.
a. 0.1587
b. 0.3174
Correct! c. 0.6826
First of all, note that and

Then by the CLT, we have
Nor (1,1). Thus,
d. 0.8413
First of all, note that and

Then by the CLT, we have Nor
(1,1). Thus,
(Lesson 2.14: Estimation.)

Suppose we collect the following observations: 7, , 1, 6. What is the
sample variance?
a. 13
b.
Correct!
c. 18
First of all, the same mean is . Then the

sample variance is
So that the answer is (c).
d. 28
First of all, the same mean is . Then the

sample variance is
So that the answer is (c).
(Lesson 2.14: Estimation.) BONUS: Consider two estimators, and ,

for an unknown parameter . Suppose that the ,
, , and . Which estimator
might you decide to use and why?
a. - it has lower expected value
b. - it has lower MSE
c. - it has lower variance
Correct! d. - it has lower MSE
Although low bias and variance are just great individually, we are
usually interested in the estimator with the lower MSE, which
balances bias and variance.
Of course, MSE = Bias + Variance. Thus, MSE and
MSE . So the answer is (d).
Note that (a) is incorrect because lower expected value doesn't
necessarily tell us about bias. (b) is just plain wrong, wrong, wrong.
(c) is close, but variance isn't as important as MSE.
Although low bias and variance are just great individually, we are
usually interested in the estimator with the lower MSE, which
balances bias and variance.
Of course, MSE = Bias + Variance. Thus, MSE and
MSE . So the answer is (d).
Note that (a) is incorrect because lower expected value doesn't
necessarily tell us about bias. (b) is just plain wrong, wrong, wrong.
(c) is close, but variance isn't as important as MSE.
(Lesson 2.15: Maximum Likelihood Estimation.) BONUS: Suppose that

are i.i.d. . Find , the MLE of . (Don't panic --
- it's not that difficult.)
Correct!
a.
The likelihood function is
To simplify things (as per the suggestion in the lesson), take logs:
where is a constant with respect to .
The recipe says that you now set the derivative , and solve for :
Solving, we get . (I won't do a second

derivative test because I'm lazy.) Thus, the correct answer is (a).
b.
c.
d.
The likelihood function is
To simplify things (as per the suggestion in the lesson), take logs:
where is a constant with respect to .
The recipe says that you now set the derivative , and solve for
:
Solving, we get . (I won't do a second

derivative test because I'm lazy.) Thus, the correct answer is (a).
(Lesson 2.15: Maximum Likelihood Estimation.) BONUS: Suppose that

we are looking at i.i.d. Exp( ) customer service times. We observe times
of 2, 4, and 9 minutes. What's the maximum likelihood estimator of ?
a. 5
ou Answered b. 1/5
c. 25
orrect Answer d. 1/25
From the lesson, we know that the MLE of is .
Therefore, the Invariance Property states that the MLE of

. This is choice (d).
(Lesson 2.16: Confidence Intervals.) BONUS: Suppose we collect the

following observations: (as in a previous question in this
homework). Let's assume that these guys are i.i.d. from a normal
distribution with variance . Give me a two-sided 95%
confidence interval for the mean .
a.
Correct! b.
The confidence interval will be of the form
where , the sample mean , the sample variance

, and , so that the -distribution quantile (which
you have to look up) is . All of this stuff yields
This is choice (b).
c.
d.
The confidence interval will be of the form
where , the sample mean , the sample variance

, and , so that the -distribution quantile (which
you have to look up) is . All of this stuff yields
This is choice (b).
Quiz Score: 27 out of 33

Week 2 Homework - Summer 2020: Attempt History

Uploaded by

Copyright:

Available Formats

You might also like

Week 2 Homework - Summer 2020: Attempt History

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Week 2 Homework - Summer 2020: Attempt History

Uploaded by

Copyright:

Available Formats

8/3/2020 Week 2 Homework - Summer 2020: Simulation and Modeling for Engineering and Science - ISYE-6644-OAN/O01

Week 2 Homework - Summer 2020

This quiz was locked May 29 at 11:59pm.

Score for this quiz: 27 out of 33

(Lesson 2.1: Derivatives.) BONUS: If , find the

This follows by the chain rule,

(c). This follows by the chain rule,

(Lesson 2.1: Derivatives.) BONUS: If , find the

By the chain rule,

(d). By the chain rule,

(Lesson 2.2: Finding Zeroes.) BONUS: Suppose that

This doesn't take too much work. Namely, set

This is the same as or

(d). This doesn't take too much work. Namely, set

This is the same as or

(Lesson 2.3: Integration.) BONUS: Find

(Lesson 2.3: Integration.) BONUS: Find

(Lesson 2.3: Integration.) BONUS: Find

If we let and , then

seems to get us into a 0/0 issue. Thus, we'll need to employ

(b). If we let and , then

seems to get us into a 0/0 issue. Thus, we'll need to employ

(Lesson 2.4: Numerical Integration.) BONUS: Find the approximate value

Well, this is sort of close to the true integral of 2/3. Of course, we

Well, this is sort of close to the true integral of 2/3. Of course, we

(Lesson 2.5: Probability Basics.) If and

You could also have used a binomial distribution argument to solve

e. I'm from The University Of Georgia. Is the answer -3?

The answer is (b). To see why, note that

You could also have used a binomial distribution argument to solve

Write out every possible outcome explicitly, or use the following

(a). Write out every possible outcome explicitly, or use the

(Lesson 2.6: Simulating Random Variables.) BONUS: Suppose and

where the cosine calculation is carried out in radians (not degrees). Go

This is the Box-Muller method to generate normal random variables.

(a). This is the Box-Muller method to generate normal random

Of course, you can do this easily in R, Excel, Python etc.

(Lesson 2.7: Great Expectations.) Suppose that is a discrete random

(Lesson 2.7: Great Expectations.) Suppose that is a discrete random

In addition to the above work,

so that we have . So the

In addition to the above work,

so that we have . So the

(Lesson 2.7: Great Expectations.) Suppose that is a discrete random

so that . So the answer is (d).

so that . So the answer is (d).

(Lesson 2.7: Great Expectations.) Suppose X is a continuous random

(Lesson 2.8: Functions of a Random Variable.) Suppose is the result of

This follows because

No other possible values for .

(c). This follows because

No other possible values for .

(Lesson 2.8: Functions of a Random Variable.) Suppose is a

orrect Answer a. , for

(a). Note that the c.d.f. of is (you can do this in your

(Lesson 2.9: Jointly Distributed RVs.) Suppose that for

So the answer is (d).