Exercise Set 2: Fall 2024 - Stats

Instructor: Emir Hidovic (TA for Prof. Pauwels)

September 24, 2024

For every question, write out the necessary formula and show the calculations
required to arrive at your answer.
Please round decimal numbers to two decimal places.

Problem 1: Summary Statistics

You are thinking about moving to Sta-Ta-Land, but you are unsure if it might
be too cold. Thus, you acquire the following information about temperatures
(in degrees Celsius):

Month January March May July September November

Temperature (°C) 10 20 25 25 20 20

Use this information to answer the following questions:

(a) What is the mean and the standard deviation of the temperature?
(b) What is the median temperature in Sta-Ta-Land? What are the first and
third quartiles (Q1 and Q3)?

1
Problem 2: Representing Data
Consider the fictitious data set below this question. In this dataset, there are
22 observations with information on four variables (major, gender, height, and
weight).

(a) Interpret, in your own words, the histogram on the next page. That is,
what can you say abou the distribution of the variable ”height”?

Figure 1: Histogram of Heights

(b) What is the mean height in the sample? What is the variance of the
height in the sample? What is the standard deviation of the height in
the sample? What is the median height in the sample? What is the
interquartile range of the height in the sample? On which scales can these
variables be measured? Is Gender/Height categorical or quantitative?
How about Major/Weight, is it categorical or quantitative? (Consider the
dataset - Fictitious Class Dataset - for this question).

2
Fictitious Class Dataset
StudentID Major Gender Height (cm) Weight (kg)
001 Econ M 181 71.4
002 Econ F 163 61.1
003 Bio F 159 48.6
004 Econ M 174 66.5
005 CompSci F 166 63.4
006 SRPP M 176 77.2
007 Econ M 172 71.7
008 PoliSci M 179 91.6
009 SRPP F 164 53.9
010 SRPP M 168 62.3
011 Econ F 166 54.4
012 Econ F 171 67.1
013 Bio M 192 100.6
014 PoliSci M 182 86.8
015 PoliSci M 163 58.2
016 Econ M 174 64.9
017 Econ M 171 65.3
018 SRPP F 169 61.8
019 Econ F 151 47.4
020 PoliSci M 154 48.1
021 Bio F 186 78.6
022 SRPP M 185 81.2

3
Problem 3: Probability
You are studying the fashion choices of spectators at Wimbledon. You receive
the following information:

• 60% of spectators are women and 40% are men.

• 50% of spectators wear a hat.
• 10% of spectators wear gloves.
• 5% of spectators wear a hat and gloves.
• 70% of female spectators wear a hat.
• 20% of male spectators wear a hat.

Suppose you were to meet one spectator at random.

(a) Let H be the event that the spectator you meet is wearing a hat and G
be the event that the spectator is wearing gloves. Are H and G disjoint
events? What is the probability that the spectator you meet is wearing a
hat or gloves, i.e., what is P (H [ G)?
(b) The spectator you meet is wearing a hat. What is the probability that
the spectator is a woman?
(c) What is the probability that the spectator you meet is a woman who is
wearing a hat?
(d) Are the events ”wearing a hat” and ”woman” independent?

Problem 4: The Taxi Problem

A taxi was involved in a hit-and-run accident at night. There are two taxi
companies that operate in the city: the Green company (which has green cars)
and the Blue company (which has blue cars). You are given the following data:

• 85% of the taxis in the city are Green and 15% are Blue.
• An eye witness identified the taxi as Blue.
• The court has tested the reliability of the witness under the same circum-
stances that existed on the night of the accident. The court concluded that
the witness correctly identified each one of the two colors 80% of the time
and failed 20% of the time (i.e., if the taxi was Blue the witness correctly
identified the color as Blue 80% of the time and incorrectly identified the
color as Green 20% of the time, and likewise for the Green taxi).

What is the probability that the taxi involved in the accident was Blue?

4
Problem 5: Expectation and Variance
Firm JBM produces microchips and is planning a major investment. The gross
returns from the investment X are uncertain, but a probabilistic estimate gives
the following distribution (in millions of dollars):

Gross Returns 1 2 5 10
Probability 0.1 0.5 0.3 0.1

(a) Calculate the expected gross returns E(X) from the investment.
(b) Calculate the standard deviation X of the gross returns.

In order to make the investment, Firm JBM will need to get a loan. An
investment bank o↵ers the following terms: in order to provide the capital for
the investment, the firm will need to pay a fixed fee of $200,000 as well as 20%
of the gross returns.

(c) Let Z be the random variable that describes the net returns of the invest-
ment. How is Z related to X? What is the expected net return and the
standard deviation of the net returns?

Firm JBM is also planning a second investment. The second investment has
an expected net return of $3 million, with a standard deviation of $2 million.
Because the two investments are in di↵erent sectors, the returns are not
perfectly correlated. Let Y be the net return on the second investment, and
suppose that the correlation between Z and Y is 0.15.

(d) What is the total net return on the two investments?

(e) What is the standard deviation of the total net returns from the two
investments?

Problem 6: Probability Combined

Consider the following scenario. You work in an international company that
owns a plant in country E. Next year, the population in country E is voting
for a referendum to exit a regional trade agreement, and you are in charge of
evaluating the expected profit of the plant in country E. You run a probabilistic
model and find that the chance that country E leaves the trade agreement is
60%. You calculate the profits of the plant and find that, if country E leaves the
trade agreement, then the plant generates 20 million dollars in profits, and, if it
does not leave the trade agreement, then the plant generates 10 million dollars.

(a) Using the percentages given above, define the probabilities associated with
the outcomes of the referendum.

5
 (b) What is the expected profit and the standard deviation of the profit of
the plant that your company owns in country E?
(c) Your boss asks you to make the same calculations in Euros so that he
can compare the profit of the plant in country E with another plant in
Europe. You look at the exchange rate and the conversion rate is 1.15
Dollars to 1 Euro (equivalent to 0.87 Euros to 1 Dollar). Using linear
transformations, write down the equation for the new variable (profits in
Euros) and calculate the expected profit and the standard deviation of the
profit of the plant in Euros.

In the next year, there is also a presidential election in country E, and your
boss asks you to predict it. In this election, there are only two candidates, R
and L. R is in favor of leaving the trade agreement, and L is against it. You
run a new model and find that the probability that country E votes in favor of
leaving the trade agreement is still 60%. In addition, you find that, if the
referendum is approved, then the probability that R wins the election is 75%,
and, if the referendum is not approved, then the probability that R wins the
election is 25%.

(d) Using the percentages given above, define the conditional probabilities
associated with each potential outcome.
(e) Make a tree diagram to represent the potential outcomes of the referendum
and election results and their probabilities (or a Venn diagram if you
prefer). Please write down the necessary formulas and calculations.
(f) Calculate the probability that candidate R wins the election.
(g) Calculate the probability that country E leaves the trade agreement if
candidate R wins the election. Please write down the necessary formula.
(h) Calculate the expected profit in Dollars and the standard deviation of the
profits of the plant in E if candidate R wins the election.

Problem 7: Probability and Binomial - for Quiz 2

Imagine that the National Scientific Foundation of the United States of Eurasia
(NSF-ESA) announces that it will give generous funds for 3 projects or more as
long as they are approved by a scientific committee. A group of researchers from
NYU-ESA decides to make some collective e↵ort to get the funds from NSF-
ESA. From previous studies, this group of researchers knows that the probability
of a project being approved by the scientific committee of NSF-ESA is about
10%. The group is initially thinking about submitting 4 projects. Define the
number of approved projects as a random variable X and answer the following
questions. (For questions f to i, assume that an n of 20 is large enough for a
binomial to generate sample statistics that are normally distributed).

(a) What is the sample space for 4 projects?

6
 (b) Calculate the probability of each outcome in the sample space.
(c) What is the probability that the group will get at least 3 projects ap-
proved?
(d) What is the expected value of X?

(e) What is the variance of X?

(f) Assume that the group submits 20 projects, what is the expected value of
X?
(g) Assume that the group submits 20 projects, what is variance of X?

(h) How many projects does the group of researchers from NYU-ESA have to
submit to get a proportion of projects approved equal to or below 0.05
with a probability of less than 5%?

Problem 8: Binomial Distribution - for QUIZ 2

The manager of a restaurant knows from past experience that 10% of customers
complain about their meals. One day, an important food critic comes to evaluate
the restaurant. The food critic knows that customers can sometimes be overly
picky and is willing to forgive the manager if one customer complains. However,
the food critic will write a bad review if 2 customers complain, and a very bad
review if 3 or more customers complain.

Suppose that, on this day, there are 12 customers in the restaurant.

(a) What is the probability that the critic will write a bad review?

(b) What is the probability that the critic will write a very bad review?
(c) What is the expected number of complaints the manager will receive on
this day?

Problem 9: Poisson Distribution - for Quiz 2

The milkweed aphid is a common pest to many ornamental plants. Suppose
that the number of aphids on a shoot of a Mexican butterfly weed follows a
Poisson distribution with mean µ = 5.4 aphids.

(a) What is the probability of observing exactly 7 aphids on a shoot?

(b) What is the probability of observing 5 or fewer aphids on a shoot?

7
Problem 10: Bernoulli vs. Binomial Dist. for Quiz 2
Suppose a new drug has been developed to treat a certain disease, and clinical
trials are being conducted to assess its e↵ectiveness. The drug has a probability
p = 0.7 of successfully treating a patient. Assume that the treatment outcome
for each patient is independent of the others and follows a Bernoulli distribution.

(a) What is the probability that the drug successfully treats a patient?

(b) What is the probability that the drug fails to treat a patient?
(c) What are the expected value and variance of the treatment outcome for a
single patient?
(d) If 10 patients are treated with this drug, what is the probability that
exactly 7 patients are successfully treated?