Individual Final Project Assignment: Sections A, B, C, and D

General Instructions

This an individual assignment, not a group assignment. Please remember that I am chiefly
interested in documented evidence of engagement with the material presented; do not fear error.

Submit a single Microsoft Word file as the project. Accompany that with a single Excel file
containing back-office work. I will only look to the Excel file to double-check issues arising in
the Word document.

Write in the first person.

Share some of your (a) thought processes, (b) miscues, (c) workarounds, and (d) insights.

Demonstrate engagement with the concepts and approaches taken in the Lecture Notes.

Do not share your project work with anyone else; that is cheating.

Do not plagiarize; do not plagiarize me.

Number the questions in the same way as shown: A1, A2,...

Answer each question at its numbered position. I will not look elsewhere.

Number your pages.

Do not show the text of my questions. Instead, fold the question into the answer. For example,
instead of repeating my first question, you could say, "A.1. I am now going to develop a
research hypothesis. To get started, I am going to think about ways in which the effects of the
Irish Potato Famine might be reflected in..."

Put a title page on your project; on it give your name, course number and date.

For your filename, put your last name first.

You are permitted to consult with published sources from outside the course. If you elect to
consult such sources, list them in an appendix. If you quote or paraphrase, cite the source with a
footnote. If you quote, use quotation marks to avoid plagiarism.

Never share your material with another student. First, that is cheating. Second, because you can
not trust them; they may take your work, unchanged, and present it as their own.

1
Part A. One-sided, Two-Sample z-Test of Population Proportions (See LN9.)

In Part A, get your data from the U.S. Census using the methods discussed in LN9.
30 points

A1. [10] Develop your own research hypothesis to use in a one-sided two-sample z-test for
population proportions. One way to start is to imagine the potential social impacts of a
major historical event, such as the Civil War, Industrialization, or the Great Migration.
Then, think how such an impact might be reflected in a quantitative form in the Census.
Full Census data is available at 10 year intervals from 1790 to 1940. The full
records of the 1950 Census have just recently been released, and are not yet in a form usable
to us. What can be measured depends on what questions were asked in Census used at
that time. You can easily search for "index of census questions" to find a breakdown of
which questions were asked and when. I fear that sometimes two versions of a census was
used in the same year, as appears to be the case with 1820.
Finding a good topic requires working back-and-forth between history and data
availability. For example, consider the Pike's Peak Gold Rush, occurring 1858-1861 in parts
of what became Kansas and Nebraska. In principle, comparing data from the 1850 and 1860
Census could be used to study the impact of that event. However, Kansas and Nebraska
would not appear in either of the 1850 or 1860 Census because they had not yet achieved
statehood. Be flexible!

A2. [5] State your null and alternate hypothesis in symbols. Then explain in words what those
hypotheses say, being specific to your setting. Explain to a novice how your particular
population proportions would in principle be computed.

A3. [5] Gather your data from U.S. Census using original handwritten records. Those are
readily accessed using FamilySearch. For each of the two samples, I recommend working
from all persons shown on a single sheet of the census, which is usually between 30 and 40
people per sheet. If you are restricting yourself to a smaller groups, say, school-age
children, then your working sample sizes will of course be smaller.
Describe what you are doing as you present and process the data. Show the reader where
and how you got the data using cropped screenshots. Those images will not be self-
explanatory; they must be accompanied with text. Write as if you are interested in the
subject and the people, and are addressing someone else who is interested, too.

A4. [5] Walk the reader through the steps of the hypothesis test in the context of your data. As
you go, explain how the test progressively answers the question, “How far is far?”

A5. [5] Graph the test, labeling all relevant portions.

A6. [5] As we have stressed, taking a single page from the U.S. Census does not give a truly
random sample. What specific problems could arise your sample as a result? How would
using a random sample, of the same sample size, have helped overcome those problems?

2
Part B. One-sided, Two-Sample t-Test of Population Averages
(see LN8 and Section 4 of LN9)
30 pts

In Part B, get your data from ship manifests, from "Ellis Island" site or other immigration
records. The data site I recommend is presented in Section 4 of LN9. If you use a different site,
say so and explain how it is used. The Ellis Island website includes data from before and after
immigration was centered on Ellis Island itself was used - it's just a name.

B1. Develop a research hypothesis to use in a one-sided two-sample test of population averages
concerning age, height, or family size. To do so, consider how an event such as a World
War, famine, or the shifts in immigration policy could produce a change in who immigrates
and when. As always, write as if you are interested and even curious as to the nature of
things that you encounter, and are addressing someone else who is interested and curious,
too.

B2. Gather your two samples from immigration data. Use sample sizes between 5 and 70.
Show details of the sourcing and context. Show and use images of the manifests of the
ships. Explain what you are doing as you go. Annotate the images so the reader can follow
your explanation,

B3. State the null hypotheses in words that apply to the particular topic you are addressing.
Define the populations you are referencing, their approximate sizes, and how the population
averages would (in principle) be computed.

B4. Perform a one-sided, two-sample t-test. Explain what the software is doing on each line of
the table of output. In particular, name the sample statistics that are computed and explain
how those are connected with population parameters.

B5. State the conclusion of the test and the grounds. Explain the reasoning behind the
conclusion.

B6. All serious studies are preceded by a small trial run to look for problems, including lack of
clarity in definitions, problems in acquiring data, or a mismatch between the available
measurements and what was desired to be measured. Think of your study as a trial run for a
larger study, in which many ships will be selected at random. In terms of preparing for that
larger study, what problems did you encounter and what changes would you make?

3
Part C: Monopoly: Information about Monopoly is given in the LN5.D Homework.
25 points

C1. Explain how the probability distribution of the sum of two fair dice is computed. Write this
up as if you are explaining it to friend not in this class. Use the terms "sample point"
"sample space."

C2. Select a starting position on the Monopoly board other than Pacific Ave. Place at least one
house and one hotel within the range of your roll, where “a roll” is the sum of two dice. The
rent you must pay when landing on a property is shown on the Deed card. Assume you do
not own any of the properties in that neighborhood. For simplicity, count landing on Chance
or on Community Chest to result in a $0 outcome. Let the term payout denote the amount of
money you pay on the next roll. Construct the probability distribution of the payout,
explaining what you have doing to your patient friend.

C3. Explain how the expected value and variance of the payout is computed from the payout
probability distribution. Explain how the expected value of your payout is related to what
would occur in the long-run, under many replications.

C4. Suppose you could buy insurance from The Dog and Slipper Insurance Company to cover
you against the possible payout of the next roll. Explain how the expected value, above, is
related to the pricing of that insurance. (The name of this fictional insuror is based on the
playing pieces in the above photo.)

C5. Explain how and why it would benefit The Dog and Slipper Insurance Company to exchange
slices of similar insurance contracts with other insurors.

This business practice is called "reinsurance" and you are welcome to see what Wikipedia
and Investopedia have to say on the subject. Fortunately, you have access to parallel results
in your clearly defined work in constructing and analysing a portfolio gamble in roulette.
You are welcome to employ the numeric values you or I got in earlier material to orient your
explanation. But, please don't try to compute the probability distribution of an actual
portfolio of insurance contracts for Monopoly, as that would be too complicated. General
results - the concepts - must suffice!

4
Part D. Regression Study (See LN10-LN11)
15 points

Introduction
LN11 Regression Part Two contains an
introduction to CAPM, the Capital Assets Pricing Model.
The central interest of CAPM is the value of the sample
slope coefficient found from regressing the percentage
return on a stock against the percentage return on the
S&P500. In informal settings in finance, that sample
slope is called Beta.
I recently conducted an experiment to see if I
could match the value of Beta reported by Yahoo Finance
for Lions Gate Entertainment Corp (LGF-A). Yahoo
reported the Beta as 1.95, as seen in the screenshot to the
right.
I was able to do reasonably well because I finally took the time to search carefully and
read carefully about how Yahoo does the computation. Authoritative Yahoo sources state that
Beta is computed using monthly returns for a period of 5 years. This idea is supported, perhaps,
by the cryptic
5Y Monthly
modifier-notation used by Yahoo.
So, I downloaded five years of monthly data for both LGF and S&P500 (^GSPC),
computed the monthly returns for both, and regressed the LGF returns on the S&P500 returns.
Lo and behold, I got a sample slope of 1.903.
I was surprised and gratified to get a value so close to the one reported by Yahoo; I have
not worried at this point about the difference between 1.95 and 1.903.
One time, I was able to employ the 5Y (five year) button in Yahoo; other times I have
typed in the date under "Start Date." In the screenshot I highlight the key features of using that
button, and the selection of
monthly returns.
Recently, the
download button did not
come on, perhaps because
all the data fit on the screen.
So, I copied and pasted the
monthly returns into Excel:
that worked fine for me.

5
Assignment

D1. For your assigned stock - Seagate Technology PLC – STX and for the S&P, download
monthly prices for the past five years. Compute your monthly returns and those of the S&P.
Using the Data Analysis option in Excel, regress your monthly returns on those of the S&P.
Show a cropped screenshot that includes Yahoo's "Beta" for your stock and another for your
regression. How closely does your sample slope agree with the Yahoo Beta? Explain in
your own words what Beta is trying to measure.

D2. Plot your monthly stock returns against the S&P returns. Add the Excel's regression line,
then add the approximate 95% prediction intervals, stating how those were computed. Add
a vertical cut anywhere you choose and explain how the intersection of that line with the two
prediction interval lines is informative.

D3. In the context of your data, explain what is meant by the standard error of the slope - see
LN10 for details.