“The scientific study of politics requires empirical evaluation of theoretical models, but theories too often proliferate without adequate testing, and empirical work too frequently applies sketchy and oversimplified theory. In EITM, researchers use recent advances in game theory and mathematical modeling to develop theoretical models of politics. These models are then subjected to rigorous tests that meet the highest standards of empirical research, including statistical analysis, experiments, and case studies. In some instances, researchers create new estimators designed to closely test the assumptions and predictions of the theoretical models. By integrating models and data, EITM is creating a new standard for theoretically grounded empirical research that yields cumulative advances to our understanding of politics.
Recognizing that gaps between theory and empirical method seriously impair scientific progress, the Political Science Program of the National Science Foundation supports annual four-week summer institutes on Empirical Implications of Theoretical Models (EITM). Previous summer institutes have taken place at Harvard (2002), Michigan (2003 and 2006), Duke (2004), UC-Berkeley (2005) and UCLA (2006).
Funding to defray participants’ costs of travel, accommodation, and subsistence is available. EITM institutes are selective, with admission based significantly on the quality and potential of research presented. Institute training includes teaching and research components, providing students a highly individualized interaction with a far wider and deeper array of mentors than is available at any individual institution. Female and minority applications are strongly encouraged.”]]>
Dr John Kirwan, a rheumatologist from the University of Bristol in England, has studied researchers’ attitudes on sharing data from clinical trials. He found that three-quarters of researchers he surveyed, as well as a major industry group, opposed making original trial data available. It is worth restating this finding: most scientists doing research on how best to help those in pain, or at risk of death, want to keep their data a secret.
Dr. Kirwan went on to ask his subjects why. Their reasons were entirely trivial: one cited the difficult of putting together a data set (wouldn’t this have to be done anyway in order to publish a paper?); another was concerned that the data might be analyzed using invalid methods (surely a judgment for the scientific community as a whole). This is something of a clue that the real issue here has more to do with status and career than with any loftier considerations. Scientists don’t want to be scooped by their own data, or have someone else challenge their conclusions with a new analysis.”]]>
Between now and January 22, we ask that you make a small, but important
contribution to the quality of the 2008 ANES surveys by offering advice
that we and the proposals authors’ can use to increase the effectiveness
of our questionnaires. We are most interested in comments that can
increase the range of hypothesis tests in which particular questions can
At the end of this letter are the lists of the proposals we have
received. You can read the full proposals in the Online Commons at:
If you can comment on even one of these proposals, it will help future
users of the ANES a great deal.
Please note that at the conclusion of the one-week comment period,
proposal authors will then have an additional week to revise their
proposals in response to any comments that you offer. So this is a
moment where your advice can make a big difference. In addition, the
ANES PIs and Board of Overseers will make extensive use of your comments
when they select questions for inclusion on the survey.
All comments must be made through the Online Commons. If you would like
to make a comment and are not yet an OC member, signing up is easy. All
it takes is filling out a simple form at:
The new 2008 ANES Time Series Study has the potential to help scholars
examine electoral dynamics in an unprecedented way. Please take a moment
to help ANES make the most effective use of this great opportunity.
We hope you will take advantage of this opportunity to make a productive
contribution to the development of the ANES surveys.
We look forward to hearing from you!
Jon A. Krosnick and Arthur Lupia
2008 ANES TIME SERIES STUDY: NOT IN THE CORE PROPOSALS:
01. “Native Born or Naturalized Americans” by user “Jimbo”
02. “Monetary Recruitment and the Rise of Internet Fundraising” by users
“Wiley” and “pollock”
03. “Interviewer-coded items” by user “clawson”
04. “From Online Newspapers to YouTube: Examining Exposure to Internet
Sources”" by users “ttowner” and “ddulio”
05. “Religion and Electoral Behavior” by users “mockabee”, “kenwald” and
06. “Three ideas: titles, turnout modeling, cell phone users” by user
07. “General Incentives Models of Turnout: ANES & BES” by user
08. “Political Alienation” by users “javeline” and “bairdv”
09. “The Role of Collective Political Efficacy” by users “Markmann”,
“Constanzebeierlein”, “Preiser” and “Wermuth”
10. “Internet Blog Usage and Political Participation” by user “rlreed”
11. “Why Do Parties Distribute Particularistic Goods?” by users
“jordangansmorse”, “sebastian.mazzuca” and “nichters”
12. “Character Judgments and Voting Behavior” by user “dcm23″
13. “Threat Perceptions and Charisma” by users “merolla” and “ejzech”
14. “A Better Way to Measure Prospective Economic Evaluations” by users
“KMichelitch”, “marco_morales”, “andrewowen” and “jtucker”
15. “Measuring Knowledge and Attitudes about the Electoral College” by
users “ShaunBowler”, “ToddDonovan” and “karpjeffrey”
16. “Independents, Leaners and Partisanship” by users “ShaunBowler”,
“ToddDonovan”, “karpjeffrey” and “DavidLanoue”
17. “Including ‘Propensity to vote’ questions in the ANES time series”
by users “Franklin” and “SamAbrams”
18. “Wealth and Electoral Behavior” by user “tdeluca”
19. “Issue Scales in the 2008 Election Study” by users “stuart” and
20. “Understanding Trust in Government” by users “nes user” and
21. “Systematic Misrepresentation of Political Polarization” by users
“andrewgelman”, “david.chungpark” and “ejuliast”
22. “Gender and Race in American Elections” by users “kdolan” and “Kira
23. “Election Integrity” by user “HeleniT”
24. “Civic Skills and Contacting” by users “Verba”, “Schlozman” and
25. “Institutional Legitimacy in the United States” by users
“legitimacy”, “MargaretLevi” and “audreysacks”
26. “Effects of decision to vote on other household members” by user
27. “Measuring Commitment to Economic Equality” by user “suhay”
2008 ANES TIME SERIES STUDY: CHANGES IN THE CORE PROPOSALS:
01. “Cognitive and Affective Partisanship” by user “klofstad”
02. “Media Use Measures for the ANES 2008 Time Series Study” by users
“salthaus” and “tewksbur”
03. “Moral Foundations Questions” by users “aperrin” and “vaisey”
04. “Internet User Definitions and New Communications Channels” by user
05. “Measuring Issues with Open-Ended Questions” by user “RePass”
06. “Measuring Attitudes toward Candidates” by user “RePass”
07. “Gender and Race in American Elections” by users “kdolan” and “Kira
08. “Method of Registration and Its Impact on Turnout” by users
“ReneeParadis” and “kahlilw”
09. “Proposal to Modify ANES 2008 Items” by user “Prysby”
2008 ANES TIME SERIES STUDY: BONUS MINUTES PROPOSALS
01. “Religious Identity” by users “bphillips” and “Saxe”
02. “Race, Gender, and Policy” by users “nburns” and “DRK”
TERRORISM AND HOMELAND SECURITY PROPOSALS:
01. “Items used in TESS survey and/or Palestinian survey for
consideration for ANES” by users “Moskalenko” and “cmccaule”
02. “Collective Memory of 9/11 and Public Opinion of Counter-Terrorism:”
by user “cbail”
03. “Public attitudes about terrorism, natural disasters, risk
perception and preparedness” by user “Bill8008″
04. “Fear of crime and terrorism as it relates to political affiliation
and voter turnout” by users “fayewachs” and “stacymcgoldrick”
05. “Emotional Responses to Potential Threats” by user “hlench”
06. “Public attitudes towards technology and perception of terrorist
attacks” by users “hbalyssa” and “kbuerkle”
07. “Individual and Government/Emergency Preparedness” by user “Keith”
08. “Proposed National Survey Question” by user “rejali01″
09. “Political views and funding homeland security policy” by users
“carolm” and “Kerry Smith”
1) The 2008 ANES Time Series
You may submit a proposal for questions to be included in the 2008 ANES
Time Series face-to-face presidential election study. The time series
continues a string of interviews that began in 1948. We are accepting
two kinds of proposals: changes to the ANES “core” questions (the set of
questions that the ANES Time Series asks repeatedly over time) and
changes to the rest of the survey (including proposals to capture
opinions and attitudes that are especially relevant to the November 2008
presidential and congressional elections).
2) Terrorism and Homeland Security
We are also running a special competition in cooperation with the
Department of Homeland Security. For that competition, we are accepting
proposals pertinent to the intersection between elections and DHS
emphases on terrorism, natural disasters, risk perception, and
preparedness. Questions from successful proposals in this competition
can be included on the 2008-2009 ANES Panel Study and/or the 2008 ANES
Time Series study.
We accept proposals through the ANES Online Commons. Please go to its
website to get more information about these opportunities:
The ANES Online Commons will continue to accept these proposals until
3:00pm Eastern Time (noon Pacific Time) on January 15, 2008.
The Online Commons will remain open for two additional weeks thereafter
to allow commentary and revision of the proposals.
We look forward to hearing from you!
Jon Krosnick and Arthur Lupia
American National Election Studies (ANES)
A project on which I’m working recently received continuation funding to collect cohort data for another five year funding cycle. The project’s PI, Elise Riley, and its project director, Jennifer Cohen, are looking to hire a statistician at 50% effort. The job description appears below. Please feel free to forward this job announcement on to interested individuals or groups and please direct all inquiries about the position to Jennifer Cohen (her e-mail address appears in the job description).
With best wishes for a happy 2008,
We are seeking a statistician for 50% employment with our UCSF research study regarding the longitudinal effects of HIV, housing, drug use and social support on the victimization and risk behavior of unstably housed women. Strong organizational skills and an ability to communicate well will be necessary in this position. Three to five years of statistical experience are preferred and no supervisory responsibility is involved with this position.
In collaboration with the PI and the senior statistician, the incumbent will choose appropriate statistical techniques, which will guide study development as well as determine the interpretation of study results. Prior experience with complex data sets will prepare the incumbent to develop the analyses and protocols needed in this study. Job duties will include the following: documenting all procedures; assessing survey question validity and reliability; performing descriptive statistics; performing time to event and adjusted analyses such as logistic, linear and Poisson regression, Kaplan-Meier estimation, and Cox proportional hazards survival analysis; performing longitudinal analyses that adjust for correlated data such as random effects and GEE modeling techniques; conducting power analyses for all projects and grant proposals; writing the first draft of results sections for manuscripts and analytic methods sections for grant proposals.
The incumbent must be proficient with SAS or equivalent statistical software that has the capacity to analyze longitudinal data with time-varying repeated measures (e.g., R, S+ or STATA). In addition, the incumbent must be adept with database systems such as ACCESS. Experience with computer-based interview systems is preferred; if the incumbent has none, s/he must be willing to become acquainted with the Questionnaire Development System (QDS) package. Weekly check-in and/or meetings with the PI, monthly all-staff meetings, and periodic briefings will provide the incumbent multiple opportunities to assess progress, prioritize work, explore new ideas and discuss problems.
Interested applicants should contact Ms. Jennifer Cohen for more information (firstname.lastname@example.org) and apply through the UCSF Career website: http://www.ucsfhr.ucsf.edu/careers/ Please apply for the Statistician position, Requisition number: 24552BR.]]>
Title: Statistical Analysis of Online News
Speaker: Laurent El Ghaoui, Electrical Engineering and Computer Science Department,
4:15 - 5:15 pm, Packard 101
Thursday, Nov 29, 2007
(Refreshments after the talk)
Each day we are inundated with an avalanche of online news. Yet is is currently hard to obtain a global view of this information. What are the images that various news media project about specific topics, such as global warming, human rights or presidential candidates? How do these images evolve over time? How do they differ across different media sources, scientific or mainstream? What are the dynamics of news events across news networks?
Modern statistical learning and optimization methods are having a great impact in fields where large amounts of data have become recently available, such as biology or finance. With no doubt, such methods can help shed light on the issues above as well, to the benefit of the social scientist or the ordinary citizen. In turn, online news analysis pushes the boundaries of statistics and optimization towards databases, networks, visualization, and calls for a renewed interaction between computer engineering and social sciences.
I will describe a project which aims at providing user-friendly tools for analyzing large amounts of text data residing in online databases, with a focus on online news data and voting records. I will discuss in particular how online learning and sparsity-inducing methods arise as key ingredients, and I will delineate some related fundamental challenges.
Laurent El Ghaoui graduated from Ecole Polytechnique (
Presentation Slides (pdf)
Jonathan Wand is an Assistant Professor in the Department of Political Science at Stanford University and a Robert Wood Johnson Health Policy Scholar at the University of Michigan. His applied and computational statistical research interests include models of dynamic and strategic individual choice behavior, non-parametric and semi-parametric scaling methods, and shape constrained inference for testing formal models.Substantively, he works on elections, campaign finance, public opinion and health care policy. Jonathan is the recipient of both the Harold Gosnell Award from the APSA and the Robert H. Durr Award from the MPSA for his research on political methodology.
Abstract for the talk:
Attitudes and attributes of individuals are often measured by means of survey questions with ordered response categories, and these measures are commonly employed to make interpersonal comparisons. These types of comparisons, however, rely on the assumption that individuals agree on the meaning of the scale categories. The interpersonal incomparability of responses due to differences in standards is a central challenge in the study of surveys and public opinion. My talk will focus on the use of anchoring objects, such as anchoring vignettes, to improve our ability to draw reliable comparisons across individual’s. Relevant applications range from measuring patient pain to racial discrimination, and from customer satisfaction to the influence of political corruption.
I investigate how to compare survey responses across individuals by asking all individuals to evaluate a common set of anchoring vignettes, or other common survey items. I offer an axiomatic derivation of building scales that illuminates previously unrecognized assumptions implicit in an earlier non-parametric methods using anchoring vignettes, and also leads to a new non-parametric scaling method. I also propose a new semi-parametric method for accomodating measurement error that overcomes earlier uses of strong assumptions concerning within-group homogeneity of the use of scales and the underlying attributes that are compared across groups.]]>
Bio: Arie Kapteyn is a senior economist at the RAND Corporation and director of RAND Labor and Population. He is a fellow of the Econometric Society, past president of the European Society for Population
Economics, and corresponding member of the Netherlands Royal Academy of Arts and Sciences. Before joining RAND, Dr. Kapteyn held a chair in econometrics at Tilburg University, where he served the university in numerous capacities, including dean of the Faculty of Economics and Business Administration; founder and director of Center (a research institute and graduate school) and of CentERdata (a survey research institute); and director of CentER Applied Research (a contract research institute). He has held visiting positions at several universities, including Princeton University, California Institute of Technology, Australian National University, University of Canterbury, New Zealand, University of Bristol, and University of Southern California.
Dr. Kapteyn’s research expertise covers microeconomics, public finance, and econometrics. Much of his recent applied work is in the fi eld of aging, with papers on topics related to retirement, consumption and savings, pensions and Social Security, disability, and economic well-being of the elderly. At RAND, he leads several projects, including one to incorporate Internet interviewing into the HRS; a center on the analysis of health and economic determinants of retirement in the United States and Western Europe; and a center on the analysis of economic decisionmaking related to retirement and saving and investing for retirement. He is also a lead researcher in a consortium designing and implementing the Survey of Health, Ageing, and Retirement in Europe (SHARE), which will provide unique opportunities for international comparative research.
He received his Ph.D. in economics from Leiden University.
Abstract for the Talk: Individuals are influenced by the types of people with whom they associate and who form their social networks. These social interactions may affect individual and social norms. We develop a direct test of this using Dutch survey data on how respondents evaluate work disability of hypothetical people with some work related health problem (vignettes). We analyze how the thresholds respondents use to decide what constitutes a (mild or more serious) work disability depend on the number of people receiving disability insurance benefits (DI) in their reference group. To account for endogeneity of DI receipt in a respondent’s reference group, we jointly model the respondent’s own self-reported work disability, the evaluation thresholds, and DI receipt in the reference group. We find that reference group e¤ects are significant, and contribute substantially to an explanation of why self-reported work disability in the Netherlands is much higher than in, e.g., the US. This implies an important role for social interactions and norms on the perception of work limitations.]]>
Bio: Mark Appelbaum is a Professor of Psychology at UCSD and until July 1 of this year was Associate Vice Chancellor for Undergraduate Education at UCSD. Appelbaum specializes in Quantitative Psychology including applied statistics, experimental design, applied measurement and assessment. He has been Editor of the Psychological Bulletin and was Founding Editor of Psychological Methods. He was a member of the SAT Committee of the College Board. Prior to joining the faculty at UCSD he was a on the faculties of the University of North Carolina, Chapel Hill and Vanderbilt University.
Abstract for the Talk: It is not uncommon, especially in studies of special populations and pilot studies, for researchers to be faced with special analytic problems due to the small numbers of subjects they have amassed. Under these circumstances, when power is already problematic, it may be difficult to rely on the asymptotic assumptions of the most commonly used statistical techniques. In this talk we will consider the consequences of the violation of asymptotic assumptions and will explore statistical techniques such as randomization/permutation tests that may be employed in small sample situations.]]>
Location: Meyer Forum Room
Visual cortex has been an excellent model system for developing a quantitative understanding of brain function. We understand a great deal about the physical signals that initiate vision, and this knowledge has led to a relatively advanced understanding of the organization of major structures in visual cortex. This talk will explain several measurements and neuroimaging methods that are used to understand human visual cortex.
First, we have developed functional magnetic resonance imaging (fMRI) methods for measuring and quantifying the properties of maps in individual human and macaque brains.
Second, we have made functional measurements of cortical plasticity to examine the consequences of abnormal retinal development, retinal disorders, and acquired damage. These experiments were performed in both human and macaque.
Third, we are combining fMRI with diffusion tensor imaging (DTI), to understand visual development of the pathways needed for reading. Specifically, as children develop and learn to read certain visual recognition skills become highly automatized and the brain develops specialized visual circuitry to support skilled reading. We are measuring how certain parts of the essential visual circuits develop, and how the signals from these circuits are transmitted to other cortical systems.
Bio: Brian Wandell is the first Isaac and Madeline Stein Family Professor at Stanford University. He graduated from the University of Michigan in 1973 with a B.S. in mathematics and psychology. In 1977, he earned a Ph.D. in social science from the University of California at Irvine. After a year as a postdoctoral fellow at the University of Pennsylvania, he joined the faculty of Stanford University in 1979. Professor Wandell was promoted to associate professor with tenure in 1984 and became a full professor in 1988.
Brian Wandell’s research includes image system engineering and visual neuroscience. In cooperation with Professor Emeritus Joseph Goodman (a faculty member in Stanford’s School of Engineering), Professor Wandell founded the university’s Stanford Center for Image Systems Engineering Program. As part of this research, Wandell and his team study and build devices used for digital imaging, including image sensors, high dynamic range displays, and software simulations of the digital imaging pipeline.
RSVP for Lunch
To RSVP for Brian Wandell’s talk, please click here.]]>