our data set is: Restaurant Safety (NYC)
I need the introduction today by 11:59pm pst I will provide info about myself. you will not be completing everything this is a team assignment so I just need to do my part which is 4 pages and I will send you what everyone else is doing to contribute.
this is just the written not the spreadsheet
Instructions
In general, your team’s task is to analyze a dataset, and the ethical issues that might arise in the
dataset or the related business contexts.. Essentially, your team is analyzing key data issues.
Both team composition and selection of a dataset/question will be done before the middle of the
semester. Each person in each team must contribute both to the analytics and to the writing. The
written deliverable must be printed and delivered to the instructor at the beginning of class on the
due date. The written deliverable must also be submitted electronically in Canvas no later than 1
hour before the beginning of class on that day.
Deliverable
The due date is listed on the course outline. Before that due date, there should be enough time in
or out of class to go over any questions your team may have.
Length
The “Main Body” of the written deliverable must be no less than ten (10) pages and no more
than twenty (20) pages (not including the cover page, cover letter, executive summary,
references, or appendices). The written deliverable may include an Appendix or may not include
an Appendix depending on circumstances.
Page 2 of 10
Formatting
Use only double space. You can choose to indent paragraphs if you like. Use 1 inch margins
(top, bottom, left, and right).
Scoring
There will be 100 points allocated for breadth and depth of content. There will be 100 points
allocated for language use and grammar.
Context, Resources, and Audience
The following is excerpted and adapted from Professor Roger Peng’s writings at:
https://leanpub.com/dataanalysisessays
The three key aspects of data analysis are context, resources, and audience.
The context of a problem covers many factors, including the question that gave rise to the dataset
and the motivations of the people asking the questions. Understanding what kind of solution
needs to be created and what kind of answer might be useful is a key part of the context. Datasets
and statistical methods can be deemed useful or not based solely on the context of a problem.
Data analysts must make an effort to understand the context of a problem in order to develop a
complete understanding of the problem. Getting a better understanding of the context may
require communicating with subject matter experts or other people involved in posing the
question.
Every data analysis is conducted with a limited set of resources. The resources available
determine the completeness and complexity of the solution developed. The most critical resource
for a data analyst is time, but computing power, technology, and money also play a critical role
Understanding what resources were available when a data analysis was done allows us to
evaluate the quality of an analysis relative to what else could have been done.
Who is this data analysis for? Every data analysis has an audience, even if it is the data analyst
alone. Knowing who the audience is and what they need is important for determining whether an
analysis is successful or not. Further, if one considers data analysis has a rhetorical activity, then
it can be important to understand how an audience receives information and evidence. Many
factors can play a role here, including cultural differences, differences in background knowledge,
and technical proficiency. While it may not be possible for a data analyst to know all of these
things as an analysis is being conducted, the analyst must make a reasonable attempt to obtain
this information.
Content
In general, the structure of the content (“main body”) of the written deliverable is to follow the
general outline and sequence of the scoring rubric. Use your own words, and not textbook
Page 3 of 10
chapter titles. Apply the concepts from the textbook chapters and other materials from class that
help your team analyze the data and address the business question. In addition, of course, to
material from this course, this assignment builds upon ideas from several general education,
lower-division core, and upper division courses.
The following document contains additional details regarding this written analysis including the
correct sequence:
https://ocw.smithw.org/bus312/casewritingrequirements.pdf
Use a “References” (or “Works Cited”) page. Make sure your team also uses “In-Text” Citations
as well. The specifics of the citations are enumerated in the document above.
Introduction
Provide an introduction and overview of each member of the team. What skills, knowledge, and
abilities does each team member bring to the team? How do those skills, knowledge, and ability
contribute to a business decision or use data? Which skills, knowledge, or abilities are from
education and which are from experience?
Provide an introduction and overview of the case choice. Why was it selected? What were the
other topics considered? What was interesting about those other topics not selected?
Summarize two non-class articles broadly related to the topic. The articles must come from one
of the sources listed at the end of this document.
Provide an introduction and overview of the dataset. Summarize the data including its relevance
and source.
Descriptive-level Analytics
An analytical workflow begins elementary analysis that simply describes the data in various
ways—usually summary tables and graphs (charts). Descriptive Analytics doesn’t answer
questions; Descriptive Analytics often raises questions or revises initial questions.
Visualization
Your analysis must include at least four graphs. At least one of the graphs must be a histogram.
The graphs must be labeled correctly, including appropriate x- and y-axis labels, and titles.
Practice making sure the graphs are situated correctly in the written and can be seen well in the
presentation.
Exploratory Analysis
Page 4 of 10
Your analysis team must provide two different exploratory analyses. For example, one
exploratory analysis can be on one field (column) and another exploratory analysis can be on
another field. Or, each exploratory analysis can be on two different datasets. Follow the process
we used in class, and learned in your elementary business statistics class, to summarize the
central tendency (e.g., mean or median) and dispersion (e.g., range or standard deviation) of a
field (this is sometimes called “univariate” analysis). You must also provide at least one
frequency distribution (i.e., a table of counts or cross-tabulations). A frequency distribution
enables a summary view of the entire field as classified by certain categories.
Preliminary, Interesting Information
What preliminary information did the team discern from the visualization and exploratory
analysis? What questions does it raise? Which ones are the most important?
Diagnostic-level Analytics
An analytical workflow continues with digging deeper into one or more questions. In particular,
we need to use hypothesis testing to “rule out” randomness. That is, we want to have some
confidence that data we see is more than just being random.
Decision, Question, or Issue
What decision, question, or issue do you want to analyze? Of all of the possible questions that
your team might want to ask, why is this one the most important?
Justify your question. Your team must use at least one idea from the four upper-division core
courses (i.e., FIN 303, MGT 360, MKT 304, or SOM 306); or, at least one idea from five of the
six lower-division core courses (i.e., Principles of Financial Accounting, Principles of
Managerial Accounting, Principles of Micro-Economics, Principles of Macro-Economics,
Business Law—we’ll exclude Business Statistics). See Sources for LDC/UDC concepts
(below). In addition, your team members’ own textbooks and course materials, and the
textbooks on reserve in the Oviatt Library Reserve Bookroom may be helpful.
Explanatory Analysis
Perform and explain a complete Hypothesis Test (e.g., a two-sample t-test). Perform and explain
a complete Confidence Interval. In general, a hypothesis test and a confidence interval support
each other. This confirms, or explains, your data in the context of the question.
Compelling Finding
What compelling finding can you conclude from the results of the Hypothesis Test and
Confidence Interval?
Predictive-level Analytics
Page 5 of 10
An analytical workflow continues even further with digging deeper into one or more questions.
In particular, we would like to forecast some new information. This is done by using the existing
information. You will use a regression of some type.
Decision, Question, or Issue
What decision, question, or issue do you want to analyze? The question is going to be different
from the diagnostic analysis but it can come from the same or similar dataset. Of all of the
possible questions that your team might want to ask, why is this one the most important? Since
this is different part of the analysis, and a different question, it requires a different kind of
analysis.
Justify your question. Your team must use at least one idea from the four upper-division core
courses (i.e., FIN 303, MGT 360, MKT 304, or SOM 306); or, at least one idea from five of the
six lower-division core courses (i.e., Principles of Financial Accounting, Principles of
Managerial Accounting, Principles of Micro-Economics, Principles of Macro-Economics,
Business Law—we’ll exclude Business Statistics). See Sources for LDC/UDC concepts
(below). In addition, your team members’ own textbooks and course materials, and the
textbooks on reserve in the Oviatt Library Reserve Bookroom may be helpful.
Forecast Analysis
Perform a Correlation Analysis (this is sometimes called “bivariate” analysis). Additionally,
perform a Regression Analysis. You can use either simple (single x-value) linear regression or
multiple (more than one x-value) linear regression. Remember to clearly understand the slope
and intercept, and R-squared, well.
Compelling Finding
What compelling finding can you conclude from the results of the Correlation Analysis and the
Regression Analysis?
Ethical Analysis
Discuss at least one ethical issue that arises in your team’s analysis of your selected dataset.
ESG or U.N. Global Compact Classification
Ethical issues can be broad and expansive but to analyze them, much less make actionable
recommendations, need to be clear and explicit. Classify the ethical issue or issues. 1), Your
team can use one or more of the four U.N. Global Compact categories (Human Rights, Labor,
Environment, or Anti-Corruption) that we discussed briefly in class. Which category does your
issue or issues fall into? Be specific. Which principle in which category does your team feel
applies the most?
Page 6 of 10
https://www.unglobalcompact.org/what-is-gc/mission/principles
Or, 2), Your team can use one or more of the three Environmental, Social, or Governance (ESG)
categories that we discussed briefly in class. Which category does your issue or issues fall into?
Again, be specific. Which specific element in which category does your team feel applies the
most?
https://research.ftserussell.com/products/downloads/ESG-ratings-overview.pdf
Normative Ethics
CSR theory, in turn, is based up Normative Ethics. Normative means “should”. Your team must
use at least one ethical theory (Utilitarianism, Deontology, Nicomachean, Rights, or Justice, but
not CSR because that was in the prior section) from the “Ethical Decision-making” presentation
in the “Assumptions I’ll Make About You” section of the first day’s class.
https://ocw.smithw.org/mgt360/ethical-thinking-ws-short.pptx
Additionally, make any reasonable counter-argument that your team feels is appropriate. You do
this by using a different ethical theory. Again, draw upon the theories in our class “Ethical
Decision-Making” reading (above).
Conclusions
Provide any Recommendations you feel are appropriate. Also, no analysis is ever fully
complete. Describe possible limitations of your team as appropriate. Might the team have
suffered from one or more cognitive biases (a good list is available on Wikipedia). Could you
have benefitted from a specialist from a different discipline? Essentially, what might be
important but you know you are missing it?
Describe possible limitations of the data. What additional quantitative data might be useful for
future work? Does it is exist and you didn’t have time? Do you even know if the data exists at
all?
———————————————————————————————————————
Sources for Non-Class Article
The sources for the articles for this class will be drawn from the following set:
• Newspapers (Dailies)
o Los Angeles Times
o New York Times
o The (London) Times
o Wall Street Journal
Page 7 of 10
o Financial Times
• Magazines (Weeklies or Monthlies)
o The Economist
o Bloomberg BusinessWeek
o Forbes
o Fortune
o Barron’s
These sources embody a high degree of investigative journalism regarding business-related
activities. To make a strong analogy, you want sources that emphasize authority, educational
value, intent, originality, and quality. If you want to use something else, it must be approved by
me in advance (it’s possible, but have a back-up plan just in case).
Sources for LDC/UDC Concepts
FIN 303 – Financial Management
http://www.csun.edu/~jpd45767/303/fin303.html
MGT 360 – Management and Organizational Behavior
https://openstax.org/details/books/principles-management (MGT)
https://openstax.org/details/books/organizational-behavior (OB)
https://ocw.smithw.org/mgt360/textbook/carpenter.pdf (MGT/OB)
MKT 304 – Marketing Management
https://open.umn.edu/opentextbooks/textbooks/principles-of-marketing
SOM 306 – Operations Management
http://www.csun.edu/~vcmgt0j3/SOM306.html
In addition to your own textbooks and course materials, and the textbooks on reserve in the
Oviatt Library Reserve Bookroom, the following textbooks may also be useful.
ACCT 220 – Introduction to Financial Accounting
https://open.umn.edu/opentextbooks/textbooks/4
ACCT 230 – Introduction to Managerial Accounting
https://open.umn.edu/opentextbooks/textbooks/137
ECON 160 – Principles of Microeconomics
https://openstax.org/details/books/principles-microeconomics-2e
ECON 161 – Principles of Macroeconomics
https://openstax.org/details/books/principles-macroeconomics-2e
BLAW 280 – Business Law I
Page 8 of 10
https://saylordotorg.github.io/text_foundations-of-business-law-
and-the-legal-environment/
Remember that each BUS 497a student has passed the BUS 302L “Gateway Lab” as well.
While not textbooks, per se, the “top ten topics” and the concomitant review/study material for
each of the six lower-division core subjects above make strong supporting and reference
materials too.
https://www.csun.edu/nazariancollegeadvisement/review-materials
Possible Sources for Quantitative Reasoning
A good start for data is the Business Databases available via the Library:
https://libguides.csun.edu/bus/library-databases
The FRED database is good for macro-level data. It’s run by the Federal Reserve Bank in St.
Louis:
https://libguides.csun.edu/az.php?a=f
Data-Planet is well-organized (hierarchical) system of data that helps with various kinds of
business, political, and social queries, with results that can be filtered by year and region.:
https://libguides.csun.edu/az.php?a=d
Remember too that for general, broad information, the U.S. Census (data.census.gov) can be
quite helpful, especially for demographic data and trends (formerly known as the American Fact
Finder):
https://libguides.csun.edu/az.php?a=d
Mergent Online also provides extensive information on companies and their competitors. It
provides more firm information than what is required by the Securities and Exchange
Commission (SEC) and can then therefore do industry-level analyses:
https://libguides.csun.edu/az.php?a=m
IBISWorld provides some of the best publicly available data on industries and markets.
IBISWorld combines public- and private-data together for industry-by-industry analyses:
https://library.calstate.edu/northridge/databases/alphabetical?alpha=I
One CSUN-provided database for company stock prices is Y-Charts. Y-Charts is useful for
accessing stock prices, among other things:
Page 9 of 10
https://library.calstate.edu/northridge/databases/alphabetical?alpha=Y
Another CSUN-provided database is CalcBench. CalcBench is useful for accessing publicly-
held financial statements. The source of this database is the SEC EDGAR system, however the
web interface and usability is much improved over the standard EDGAR web interface:
https://library.calstate.edu/northridge/databases/alphabetical?alpha=C
The CSUN Library provides links to additional statistical data as well:
https://library.calstate.edu/northridge/databases/subject/statistical-data
Other sources of quality data that students have found useful in the past are:
https://WSJMarkets.com/
https://google.com/finance
https://yahoo.com/finance
https://www.statista.com/
https://www.axios.com
Tips for Quantitative Reasoning
Data Literacy, Analytics, and Analysis are a start but they, by themselves, are incomplete. Look
for trends and patterns. What are you comparing and contrasting? Just solely in the area of
organizational performance, there are at least five major kinds of performance evaluation:
Improvement
Comparing current performance with past performance.
Comparative
Comparing current performance to the performance of peers.
Goal
Comparing current performance to the performance stated in a clear/explicit goal.
Ideal
Comparing current performance to an ideal or perfect performance.
Stakeholder
Comparing current performance to the expectations of one or more stakeholders.
Page 10 of 10
You’ll most likely rely on financial statements but there are other kinds of data too (e.g.,
marketing, operations, management). Recall the “Balanced Scorecard” (examples on
Wikipedia). You must make a conscious decision to exclude one of these. Be prepared to justify
your answer.
Just understanding data is difficult. Data is raw, Information is meaningful data, Knowledge
combines explicit information with tacit information, and Wisdom is extraordinary insight or
foresight. In your quantitative reasoning, can you distinguish between these in a clear way; that
is, clear in the eyes of the decision-makers (audience)?
Which parts of your analysis are relatively objective (fact-based, education-based, primary-
sources, first-person)? Which parts are relatively subjective (intuition-based, experience-based,
secondary-sources, third-party)?
Are you explaining or predicting? Both are about understanding, however, explanations are of
the recent past, and predictions are about the near future. Both are important but require
different kinds of analytical techniques (the former, perhaps, hypothesis testing; the latter,
perhaps, linear regression).
Are you modeling or judging? You develop models when you have some data; you use
judgment when you don’t have much data.
How have you maximized rationality and/or minimized uncertainty in the eyes of decision-
makers? How have you leveraged serendipity and/or controlled complexity, again, in the eyes of
the decision-makers?
Have you discussed reward and risk in the same context? One without the other will lead to
weak results. Have you discussed measurement and management in the same context? One
without the other is ineffective.
