11.220 Quantitative Reasoning and Statistical Methods for Planning I

11.220 Quantitative Reasoning and Statistical Methods for Planning I

Department of Urban Studies and Planning, MIT, Spring 2017, Credits: 4-2-6

DRAFT version 2/2/2017 - SUBJECT TO CHANGE

Lectures: MW 11:00-12:30; 9-354

Instructor:Mariana , Office 9-426,

Office Hour: Monday 2:40 - 4:00, alternate Tuesdays 9:10 - 10:10

Assistant: Phil Sunde, 9-316,

Recitations: Students are required to join ONE weekly recitation.

●Wed 5:00-6:30 (9-450B) TA: ; Office: ___; Office Hour: TBA

●Thu 11:00-12:30(10-401) TA: Parrish Bergquist: ; Office: ___; Office Hour: TBA.

●Fri 10:30-12:00 (9-451) TA: Jeff Rosenblum: ; Office: 9-569; Office Hour: TBA

Please complete this survey to rank order your preferences for a time slot; we will do our best to accommodate your preference but cannot guarantee it.

Stellar website:

Do you have to take QR?

No! There are two alternatives for students with scheduling conflicts or previous coursework in statistics:

Taking a substitute class. Here is the currently approved list of substitute classes.
Passing the test-out exam (Monday Feb 6, 2016, 3PM - 5PM - OR - 5pm-7pm, 9-451). (No make-up exam, sorry.)

Statistics software: This course uses the statistical software program R. Prior experience with R is not necessary. We have developed R tutorials specific to each assignment, and TAs will help with that during recitation. Tutorial 1 will show you step by step how to install R and RStudio and begin using it. The benefit of R is that it is free and will allow you to use it in the future after DUSP. There are several brief guides and “cheat sheets” on Stellar that are helpful resources.

Textbooks (you can access the relevant excerpts on Stellar)

●Urdan, T. 2011. Statistics in Plain English

●Lynch, S. 2013. Using Statistics in Social Research: A Concise Approach

●Wheelan, S. 2013. Naked Statistics: Stripping the Dread from the Data

●Triola, M. 2006. Elementary Statistics 10th Edition

Student expectations

ODGE. The Office of the Dean for Graduate Education (ODGE.mit.edu) is an Institute-wide support and referral office for graduate students. The ODGE is very friendly and super helpful to all graduate students at MIT if you are having any issues, they can refer you to the right source. ODGE can provide more guidance, but in general, exceptions to the expectations provided in this syllabus are only accepted with approval through the Office of Student Disability Services (e.g., extended time for tests, use of computer in class) But check in with ODGE first.

Academic Integrity You are encouraged to learn from one another in this class. You are very welcome to collaborate while doing problem sets but the final product you turn in should be your own work. Please do not copy solutions from one another. The MIT Policy on Student Academic Dishonesty is outlined in MIT’s Policies and Procedures 10.2.

Learning Norms

●Reading before the class: to establish the norm of reading

●No laptops in class. Taking notes by hand, it turns out, is better anyways (read about that here).

●In-class idea notes

●Learning from each other

Grading

Items / %
Reading before the class, class participation, recitation participation, in-class idea notes (attendance check) / 20%
Six Problem Sets (8%, 8%, 8%, 8%, 8%, 15%) / 55%
Five In-Class Quizzes (5%, 5%, 5%, 5%, 5%) / 25%

In-class idea notes

At the end of the each class, we’ll reserve 5 minutes for you to write an in-class idea note. You may use it to ask the following questions:

●What does the lecture inspire you to think? Either as a practitioner, as a researcher, or as a citizen

●How does the lecture connect to any of your personal experience, public events, planning debates, other courses, or your future career?

●Do you learn any new data source that might of use for your future work?

●Any puzzles, confusions or misunderstandings of the statistical concepts discussed today

●Anything you’ve learned on research design? Any ideas for your future projects?

●It is NOT graded. Everyone gets the full score as long as you submit it. This idea notes are designed to help you reflect on what you’ve learned in the class. We will collect and use them to gauge the class pace, target our recitations and improve the next lectures.

Problem Sets

●Late policy: No late submissions are accepted. Problem set solutions will be posted at Stellar Site on the DUE date.

●Individual submissions are required. If you collaborate on problem sets with others, you must list their names. But the work must be yours.

●Submission: Please upload a digital copy to the Stellar Site, AND submit a hard copy to your TA at the beginning of lecture on the due date.

Quizzes. There will be five in-class quizzes, each will be 15 minutes long. The quizzes are open book (you may use any printed material/books; no computers, tablets, or smartphones allowed). You may use a calculator during the quiz; however, you may not use any statistical functions on the calculator.

Schedule Overview

Class #/Date / Topics / PS assigned / PS due / Quiz
Feb 8 / QR in a Nutshell
Feb 13 / Data basics, measurement, displaying descriptive data / PS1
Feb 15 / Central tendency and dispersion
Feb 21 / Populations, samples, censuses / PS1
Feb 22 / Probability and sampling
Feb 27 / The US Census / Quiz 1
Mar 1 / Sampling distributions / PS2
Mar 6 / Inferences from samples 1
Mar 8 / Inferences from samples 2 / PS2
Mar 13 / Testing differences in means / PS3 / Quiz 2
Mar 15 / Testing differences in proportions
Mar 20 / Review / PS3
Mar 22 / Studying inequality / Quiz 3
Mar 27-29 / RELAX!
Apr 3 / Describing and displaying relationships between variables
Apr 5 / Correlation and bivariate regression / PS4
Apr 10 / Multiple regression 1 / PS4
Apr 12 / Multiple regression 2 / PS5
Apr 19 / Multiple regression 3 / PS5
Apr 24 / Logistic regression / Quiz 4
Apr 26 / Review
May 1 / Study designs / PS 6
May 3 / Survey design
May 8 / Mixed methods research
May 10 / Multi-level models / Quiz 5
May 15 / Data reduction
May 17 / Challenges in quantitative research / PS6

Schedule Detail

Class #/Date / Topics / Reading
Feb 8 / QR in a Nutshell / Derman E. 2014
Krause K. 2017
Feb 13 / Data basics, measurement, displaying descriptive data / Urdan pp. ix-x; 4-10
Triola pp. 56-65
Feb 15 / Central tendency and dispersion / Lynch pp. 37-48
Urdan pp. 19-28
Triola pp. 76-80; 92- 100
Feb 21 / Populations, samples, censuses / Urdan pp.1-4
Lynch pp. 22-26
Triola pp. 26-31
Wrigley-Field E. 2017.
Feb 22 / Probability and sampling / Lynch pp. 58-71
Triola pp. 213-220
Feb 27 / The US Census / Bazuin JT, Fraser JC. How the ACS gets it wrong: The story of the American Community Survey and a small, inner city neighborhood. Applied Geography. 2013 Dec 31;45:292-302.
Recommended: Spielman SE, Folch D, Nagle N. Patterns and causes of uncertainty in the American Community Survey. Applied Geography. 2014 Jan 31;46:147-57.
Skim: U.S. Census Bureau. A Compass for Understanding and Using Ameri
can Community Survey Data: What State and Local Governments Need
to Know, 2009.

Mar 1 / Sampling distributions / Lynch pp. 71-77
Triola pp. 246- 250
Raza S. 2017
Mar 6 / Inferences from samples 1 / Lynch pp. 83 - 90
Statistics for The Behavioral and Social Sciences: A Brief Course, Aron, 5E pp. 135 - 145
Mar 8 / Inferences from samples 2 / Lynch pp. 90 - 95
Gigerenzer G. 2014
For additional reference: Urdan pp. 71 - 73
Mar 13 / Testing differences in means / Lynch pp. 95 - 98
Wheelanch 9
Christakis N. 2014
Mar 15 / Testing differences in proportions / Urdan pp. 161-165
Lynch pp. 107 - 114
Mar 20 / Review
Mar 22 / Studying inequality / Arcaya MC, Arcaya AL, Subramanian SV. Inequalities in health: definitions, concepts, and theories. Global health action. 2014 Dec;8:27106
Weinberg, Iceland, and Steinmetz. Measurement of Segregation by the U.S. Bureau of the Census In Racial and Ethnic Residential Segregation in the United States: 1980-2000.
Mar 27-29 / RELAX!
Apr 3 / Describing and displaying relationships between variables / Feel free to begin readings for April 5 (or enjoy your last day of spring break)
Apr 5 / Correlation and bivariate regression / Lynch pp 127-141 ch. 9
Triola pp. 517 - 524
Apr 10 / Multiple regression 1 / Urdanch. 13
Apr 12 / Multiple regression 2 / Lynch pp. 143-164
Seife C. 2014
Apr 19 / Multiple regression 3 / Wheelanch. 11 - 12
Apr 24 / Logistic regression / Triola pp. 571 - 572
Shi, Chu & Debats (2015). Explaining Progress in Climate Adaptation Planning Across 156 US Municipalities
Apr 26 / Review / Stone - Quantitative analysis as narrative
May 1 / Study designs / Nisbet R. 2014
Wheelanch. 13
Mastering Metrics Introduction
Been V, Ellen IG, Gedal M, Glaeser E, McCabe BJ. Preserving history or restricting development? The heterogeneous effects of historic districts on local housing markets in New York City. Journal of Urban Economics. 2016
Skim: Mastering Metrics ch. 4- 5
May 3 / Survey design / Triola pp. 16-17
May 8 / Mixed methods research / Mills, K. 2014
Small ML, Jacobs EM, Massengill RP. Why organizational ties matter for neighborhood effects: Resource access through childcare centers. Social Forces. 2008;87(1):387-414.
May 10 / Multi-level models / Caceres IA, Arcaya M, Declercq E, Belanoff CM, Janakiraman V, Cohen B, Ecker J, Smith LA, Subramanian SV. Hospital differences in cesarean deliveries in Massachusetts (US) 2004–2006: the case against case-mix artifact. PloS one. 2013 Mar 18;8(3):e57817.
May 15 / Data reduction / Arcaya M, Reardon T, Vogel J, Andrews BK, Li W, Land T. Peer Reviewed: Tailoring Community-Based Wellness Initiatives With Latent Class Analysis—Massachusetts Community Transformation Grant Projects. Preventing chronic disease. 2014;11.
May 17 / Challenges in quantitative research / Ioannidis JP. Why most published research findings are false. PLos med. 2005 Aug 30;2(8):e124.
Wheelanch. 7

DUSP QR Syllabus Spring 2017 | page 1