As mentioned in class today, if you had points deducted from Assignment #1 because you didn’t meet the basic scenario requirements, (you will know this from my additional note at the top of your evaluation sheet), you may earn half those points back by submitting, to my Owlbox (MIS0855.1ptopenatj1r90sy@u.box.com) the following by 7:59am Friday, September 30th, 2016:

1. Revised hypotheses clearly comparing Philadelphia to another US location (another city, state, region, or national comparison is fine, but it must be specifically stated in each hypothesis). You must also still meet requirements for testability and falsifiability.
2. Revised rationales for each new hypothesis, answering the question “Why might this condition I’m testing for be true?”
3. Two specific pieces of data you would look for to test each new hypothesis. You are not required to find a dataset containing the pieces of data you specify, but I want you to list what you would look for to support the tests.

So, for instance:

Original hypothesis: Philadelphia is a safer city. (Not testable. How do you test for “safe”, and where are you comparing it to?)

Revised hypothesis: Philadelphia had fewer incidences of robberies at gunpoint than New York City, per 1000 residents, in year 2015.

Rationale – needs to answer the question why NYC might have more robberies at gunpoint, or why Philadelphia might have fewer, thus could include rationales like: Philadelphia residents don’t stay out as late as NYC residents do, so aren’t on the streets to be robbed. OR, Philadelphia makes it harder to buy a gun than NYC. OR, Philadelphia has a better staffed police department and presence on the streets to deter robberies at gunpoint.

Two pieces of data to test the hypotheses could be:

1. Ratio of robberies at gunpoint to residents in NYC
2. Ratio of robberies at gunpoint to residents in Philadelphia

Or, you can cite the data you’d use to figure out the ratio (you’re not restricted to two pieces of data, can have more, just not less):

1. # of residents in NYC in 2015
2. # of robberies at gunpoint in NYC in 2015
3. # of residents in PHL in 2015
4. # of robberies at gunpoint in PHL in 2015

If you have further questions, do email me. If you have questions about any other part of your Assignment #1 evaluation, please email me those as well.

Professor Pote

Here is the study guide for the first midterm exam. Exam is October 7. Exam review is October 3.

Format for review is:

• Unstructured, for my part. I do not have an agenda for topics to cover. I will field questions as you ask them, but only if you ask them.
• I won’t answer questions like “what’s going to be on the exam”.
• Conceptually, the following are subject for valid questions:
  • Anything on the study guide
  • Anything from the readings
  • Anything from the slides and in-class activities
  • Anything from the Assignments
  • Anything from the quizzes and weekly questions
• When the questions stop or we reach 50 minutes, class will end.
• On the matter of questions:
  • There are no dumb questions.
  • Don’t self-censor. Ask your question, and leave it to me to determine if it’s one I’m inclined to answer, discuss, or if it’s too close to the “what’s on the exam” slant to respond to.
  • Remember if you have the question, likelihood is someone else does too, and they’ll probably thank you for asking it.
  • And lastly, do come to class with questions in hand.

Suggested study approach:

• Review the Study Guide first, then:
• Start with the slides
  • Look at the major concepts
  • Where a slide is associated with a reading, review the reading that covers the major concept
  • Understand how the reading is associated with the slide, and the reading’s key concepts
• Then look at the quizzes
  • Review the questions and answers to the quizzes
  • Understand where all the answers came from, review those readings
• Then review the In-Class Exercises
  • If we did it in an exercise, it’s probably important.
  • Focus on topics we emphasized in the Exercises.
• Then, review your Assignments.
• Lastly, re-read any readings you didn’t review in the prior study steps.

What will be on the exam, in order of likelihood, are:

• Things we talked about explicitly in class
• Slides, and readings directly associated with them
• Things I quizzed you on
• Things we worked on in class through the exercises
• Things you used while completing Assignments
• Other things from readings that may not have otherwise been emphasized in class discussion or readings

Here’s the site we discussed in today’s class, Spurious Correlations. Poke around and see what you can find. Great for conversation starters!

In class we talked about a few examples of open data. Here are some others you might want to check out throughout the course. Consider how having these data sets freely available to the public might transform various industries:

• Business: data.gov’s “Impact” section
• Science: The Genomes Unzipped project
• Government: New York City parking violations
• Journalism: Swarmize

Class,

For the “Building a Data Dictionary” exercise that I asked you on Friday to do over the weekend, here’s some additional detail we didn’t have time to cover in the classroom:

1) A data dictionary is another component of metadata.

2) It’s a metadata repository, that catalogs all the details pertaining to the metadata.

3) Cataloging your metadata in a data dictionary will make both your life, and that of anyone else using this spreadsheet, much easier!

4) So, your assignment is to practice interpreting the metadata for the spreadsheet, and create a data dictionary for the exercise spreadsheet.

5) Remember, metadata is data about data. So you are not cataloging any data about cars themselves, only the data related to the fields used to describe the cars.

If you have any questions as you work through the exercise, email me and I’ll point you in the right direction.

Professor Pote

Here’s the website we talked about in class today. Give it a try, see what you can learn about yourself from your own email metadata!

https://immersion.media.mit.edu/

Class, 

Through Monday, 9/5/16, I will have limited access to Internet and email. I 
will check for email at least 1x/day, and respond immediately to urgent requests. 

All other email will be responded to when classes resume on Tuesday, 

9/6/16.

Enjoy your holiday weekend, see you on Wednesday!

Professor Pote

We are all drowning in data, and so is your future employer. Data pours in from sources as diverse as social media, customer loyalty programs, weather stations, smartphones, and credit card purchases. How can you make sense of it all? Those that can turn raw data into insight will be tomorrow’s decision-makers; those that can solve problems and communicate using data will be tomorrow’s leaders. This course will teach you how to harness the power of data by mastering the ways it is stored, organized, and analyzed to enable better decisions. You will get hands-on experience by solving problems using a variety of powerful, computer-based data tools virtually every organization uses. You will also learn to make more impactful and persuasive presentations by learning the key principles of presenting data visually.