Updates from May, 2011 Toggle Comment Threads | Keyboard Shortcuts

  • anjalitb 2:15 pm on May 18, 2011 Permalink |  

    Time Series Cross Section : Anjali Bohlken 

    This week deals with Time Series Cross Section Data (also known as Longitudinal or Panel Data).

    Here are my lecture notes for Tuesday, May 31st.

    I will be relying on the following articles to provide the necessary background on the topic:

    • Beck, Nathaniel and Jonathan Katz. 1995. “What to do (and not to do) with Time-Series Cross-Section Data.” American Political Science Review.
    • Beck, Nathaniel. 2001. “TIME-SERIES–CROSS-SECTION DATA: What Have We Learned in the Past Few Years?”  Annual Review of Political Science Vol. 4: 271-293
    • Wilson, Sven and Daniel Butler. 2007. “A Lot More to Do: The Sensitivity of Time- Series Cross-Section Analyses to Simple Alternative Specifications.” Political Analysis. 15:101-123.
    • DeBoef, Suzanna and Luke Keele. 2008. “Taking Time Seriously” American Journal of Political Science Vol. 52, No. 1 (Jan., 2008), pp. 184-200
    • Green, Donald P. , Soo Yeon Kim and David H. Yoon. 2001. “Dirty Pool” International Organization Vol. 55, No. 2 (Spring, 2001), pp. 441-468.

    As of now, I do not plan to use a textbook since the above journal articles serve as useful primers. These in conjunction with some useful lecture notes available on the web should be sufficient.

    Neal Beck’s lecture notes on TSCS are excellent and can be found here under Week 13.

    Matt Golder’s notes on Stationary Time Series are also very useful.

    My lecture notes contain a list of references which are worth reading if you wish to explore a particular topic further.

    Problem Set:

    The problem set for this module is borrowed, with some alterations, with permission from Neal Beck.

    The problem set and associated datasets etc. are available here.

     

  • cutler 8:10 am on May 6, 2011 Permalink |  

    Discrete Choice – Multiple Categorical Outcomes – LDV 

    Introduction

    This module deals with statistical models to help us explain multiple, unordered, categorical outcomes.

    It should help you learn, relearn, and do a number of things:

    • Foundations of maximum likelihood estimation
    • Practicalities of maximum likelihood estimation and working with likelihoods (a bit)
    • Using Clarify and Margins to interpret non-linear models (logit, and beyond)
    • Understand, use, and interpret
      • Multinomial logit
      • Multinomial probit
      • Conditional logit
      • Selection models
    • More stata tricks

    Here are my teaching notes: 574 Cutler teaching notes Revised

    1. Maximum-Likelihood Estimation & Logit refresher

    First, you should make sure you’re on board with maximum likelihood estimation. Logit, for example. And interpreting effects of a logit in Stata with Clarify and/or the new “margins” command.

    One way to review MLE in general is to watch the screen and listen to me as I did the relevant class for this year’s POLI572. It’s slow moving, however, so it may not be the most efficient thing to do.

    http://www.screencast.com/t/kYG2I1ETE

    [You actually have to start in the middle because I cut it into two parts and then when I reassembled it I put the two parts backwards. So you have to wait for a bunch of it to download, start at 1:05:00 and follow it to the end, and then for the second half of the class, just start at the very beginning. The very beginning stuff is post-break, so it’s very silly for a few minutes — you can restart the second half at about 4:00.]

    Another way to refresh is for you to consult the materials listed and linked from the POLI572 blog: https://blogs.ubc.ca/poli5722011/ under “FOR MARCH 18”.

    The quickest and simplest is the Kellstedt and Whitten text: section 11.4 for a quick logit refresher.

    I strongly recommend the following new reading that will both reinforce what logit is doing and actually help you think about using interactions in logit/probit models is:

    William D. Berry, Jacqueline H. R. DeMeritt, Justin Esarey. 2009. Testing for Interaction in Binary Logit and Probit Models: Is a Product Term Essential? AJPS. 2009 DOI: 10.1111/j.1540-5907.2009.00429.

    2. Multiple Categorical Outcomes

    Then, SECOND, we can move on to starting to think about MULTIPLE unordered outcomes.

    The most obvious place this applies in our discipline is in vote choice in multiparty systems. I want to emphasize, however, that there are lots of, and probably more important, questions across subfields involving multiple unordered (discrete) outcomes.

    Nevertheless, because I know this stuff best in the context of voting research and because I have cool, brand new CES data, and because I have actually published using a conditional logit model, I’ll stick with this as an example.  We’ll try to explain vote choice in Quebec in this very recent election.  That’ll be the data you can play with. It will appear here with a do file on Monday.

    Oh, Tuesday officially. Here’s a zip file with data and do file: 574-class 1

    I’ve got three levels of ‘textbook’ for this module.

    From most detailed and hardest to follow to least:
    (So you may want to start with the bottom one if you want to ease into it; the top one if you’re confident you can follow the math. I would like you to have the Golder notes printed or otherwise handy for reference).

    1. Matt Golder’s teaching notes (http://homepages.nyu.edu/~mrg217/unordered_multiresponse.pdf)
      NOTE that Conditional logit (3) precedes Multinomial Logit (4) in Golder’s notes.
    2. Kousser Unordered Choice Models (pdf)
    3. and, for a more basic summary with some Stata-ish-ness: http://www.nd.edu/~rwilliam/stats2/l92.pdf

    Then (or, first):

    Tucker et al Transitional Winners and Losers AJPS 2002

    Transitional Winners and Losers: Attitudes toward EU Membership in Post-Communist Countries, Joshua A. Tucker, Alexander C. Pacek and Adam J. Berinsky.  American Journal of Political Science, Vol. 46, No. 3 (Jul., 2002), pp. 557-571 Article Stable URL: http://www.jstor.org/stable/3088399

    • This is a good application of Multinomial Logit.

    Alvarez Nagler Models Collide AJPS 1998

    When Politics and Models Collide: Estimating Models of Multiparty Elections
    R. Michael Alvarez and Jonathan Nagler, American Journal of Political Science, Vol. 42, No. 1 (Jan., 1998), pp. 55-96 Article Stable URL: http://www.jstor.org/stable/2991747

    • This shows that MNL is equivalent to binary logits, but slightly more efficient.

    Dow Endersby MNP vs. MNL JELS 2004

    Multinomial probit and multinomial logit: a comparison of choice models for voting research. Dow, Jay K. and James W. Endersby. Electoral Studies Volume 23, Issue 1, March 2004, Pages 107-122  doi:10.1016/S0261-3794(03)00040-4

    • This shows that MNP is kind-of a waste of time

    Golder’s Discrete Choice Notes II

    • This is a mini-textbook for Nested logit and Multinomial Probit

    3. Characteristics of CHOICES, not just of choosers: Conditional Logit

    See the Golder notes, above, for the math of the conditional logit model.

    See this Princeton page for the Stata operationalization of the model.

    Cutler Simplest Shortcut of All JOP 2001

    The Simplest Shortcut of All: Sociodemographic Characteristics and Electoral Choice. Fred Cutler. 2002. The Journal of Politics. Vol. 64, No. 2, pp. 466-490. Article Stable URL: http://www.jstor.org/stable/2691857

    4. Selection models

    We may make it to selection models. I’d like to.

    Start with Wooldridge section 17.5.

    Or, maybe there’s no point. Again, Matt Golder’s notes are excellent: http://homepages.nyu.edu/~mrg217/selection.pdf

    Then, for some examples, which you can read according to your interests

    Berinsky two faces of public opinion

    Blanton Sanctions AJPS

    Nooruddin sanctions[1]

    A Summary of Political Selection: The Effect of Strategic Choice on the Escalation of International Crises

    Alastair Smith, American Journal of Political Science. Vol. 42, No. 2 (Apr., 1998), pp. 698-701. Article Stable URL: http://www.jstor.org/stable/2991776

    Sorry, that one’s just a summary of a poster. This one is better:

    A Unified Statistical Model of Conflict Onset and Escalation

    William Reed
    American Journal of Political Science, Vol. 44, No. 1 (Jan., 2000), pp. 84-93
    Stable URL: http://www.jstor.org/stable/2669294

    James Raymond Vreeland (2008). Political Institutions and Human Rights: Why Dictatorships Enter into the United Nations Convention Against Torture. International Organization, 62, pp 65-101

     

  • cutler 8:09 am on May 6, 2011 Permalink |  

    Course Comments 

    I’d like everyone to comment on how the course goes. One or two comments over the whole period, or afterwards, will suffice. Wildly positive and constructively critical comments are welcome.  Also, suggestions for logisitical changes that will help us in the coming weeks or in subsequent years.

    Comment away…

     

c
Compose new post
j
Next post/Next comment
k
Previous post/Previous comment
r
Reply
e
Edit
o
Show/Hide comments
t
Go to top
l
Go to login
h
Show/Hide help
shift + esc
Cancel

Spam prevention powered by Akismet