Archive

Archive for the ‘Columbia University’ Category

After Midnight: A Regression Discontinuity Design in Length of Postpartum Hospital Stays

September 17, 2014 Comments off

After Midnight: A Regression Discontinuity Design in Length of Postpartum Hospital Stays (PDF)
Source: Columbia University (Almond), MIT (Doyle)

Estimates of moral hazard in health insurance markets can be confounded by adverse selection. This paper considers a plausibly exogenous source of variation in insurance coverage for childbirth in California. We find that additional health insurance coverage induces substantial extensions in length of hospital stay for mother and newborn. However, remaining in the hospital longer has no effect on readmissions or mortality, and the estimates are precise. Our results suggest that for uncomplicated births, minimum insurance mandates incur substantial costs without detectable health benefits.

About these ads

XRay: Enhancing the Web’s Transparency with Differential Correlation

August 21, 2014 Comments off

XRay: Enhancing the Web’s Transparency with Differential Correlation (PDF)
Source: Columbia University

Today’s Web services – such as Google, Amazon, and Facebook – leverage user data for varied purposes, including personalizing recommendations, targeting advertisements, and adjusting prices. At present, users have little insight into how their data is being used. Hence, they cannot make informed choices about the services they choose.

To increase transparency, we developed XRay, the first fine-grained, robust, and scalable personal data tracking system for the Web. XRay predicts which data in an arbitrary Web account (such as emails, searches, or viewed products) is being used to target which outputs (such as ads, recommended products, or prices). XRay’s core functions are service agnostic and easy to instantiate for new services, and they can track data within and across services. To make predictions independent of the audited service, XRay relies on the following insight: by comparing outputs from different accounts with similar, but not identical, subsets of data, one can pinpoint targeting through correlation. We show both theoretically, and through experiments on Gmail, Amazon, and YouTube, that XRay achieves high precision and recall by correlating data from a surprisingly small number of extra accounts.

See: New Tool Makes Online Personal Data More Transparent

The Great Society, Reagan’s revolution, and generations of presidential voting

July 9, 2014 Comments off

The Great Society, Reagan’s revolution, and generations of presidential voting (PDF)
Source: Columbia University (Ghitza and Gelman)

We build a generational model of presidential voting, in which long-term partisan presidential voting preferences are formed, in large part, through a weighted “running tally” of retrospective presidential evaluations, where weights are determined by the age in which the evaluation was made. Under the model, the Gallup Presidential Approval Rating time series is shown to be a good approximation to the political events that inform retrospective presidential evaluations. The political events of a voter’s teenage and early adult years, centered around the age of 18, are enormously important in the formation of these longterm partisan preferences. The model is shown to be powerful, explaining a substantial amount of the macro-level voting trends of the last half century, especially for white voters and non-Southern whites in particular. We use a narrative of presidential political events from the 1940s to the present day to describe the model, illustrating the formation of five main generations of presidential voters.

A Measurement Study of Google Play

June 26, 2014 Comments off

A Measurement Study of Google Play (PDF)
Source: Columbia University

Although millions of users download and use third-party Android applications from the Google Play store, little in- formation is known on an aggregated level about these applications. We have built PlayDrone, the first scalable Google Play store crawler, and used it to index and analyze over 1,100,000 applications in the Google Play store on a daily basis, the largest such index of Android applications. PlayDrone leverages various hacking techniques to circumvent Google’s roadblocks for indexing Google Play store con- tent, and makes proprietary application sources available, including source code for over 880,000 free applications. We demonstrate the usefulness of PlayDrone in decompiling and analyzing application content by exploring four previously unaddressed issues: the characterization of Google Play application content at large scale and its evolution over time, library usage in applications and its impact on application portability, duplicative application content in Google Play, and the ineffectiveness of OAuth and related service authentication mechanisms resulting in malicious users being able to easily gain unauthorized access to user data and resources on Amazon Web Services and Facebook.

See: Crucial security problem in Google Play: Thousands of secret keys found in android apps (Science Daily)

The Art and Science of Data-Driven Journalism

June 3, 2014 Comments off

The Art and Science of Data-Driven Journalism (PDF)
Source: Tow Center for Digital Journalism, Columbia University School of Journalism

Journalists have been using data in their stories for as long as the profession has existed . A revolution in computing in the 20th century created opportunities for data integration into investiga tions, as journalists began to bring tec hnology into their work. In the 21st century, a revolution in connectivity is leading the media toward new horizons. The Internet, cloud computing, agile development, mobile devices , and open source software have transformed the practice of journalism, lea ding to the emergence of a new term: data journalism.

Although journalists have been using data in their stories for as long as they have been engaged in reporting, data journalism is more than traditional journalism with more data. Decades after early p ioneers successfully applied computer – assisted reporting and social science to investigative journalism, journalists are creating news apps and interactive features that help people understand data, explore it , and act upon the insights derived from it. Ne w business models are emerging in which data is a raw material for profit, impact , and insight, co – created with an audience that was formerly reduced to passive consumption. Journalists around the world are grappling with the excitement and the challenge o f telling compelling stories by harnessing the vast quantity of data that our increasingly networked lives, devices, businesses , and governments produce every day.

While the potential of data journalism is immense, the pitfalls and challenges to its adop tion throughout the media are similarly significant, from digital literacy to competition for scarce resources in newsrooms. Global threats to press freedom, digital security, and limited access to data create difficult working conditions for journalists i n many countries. A combination of peer – to – peer learning, mentorship, online training, open data initiatives, and new programs at journalism schools rising to the challenge, however, offer reasons to be optimistic about more journalists learning to treat d ata as a source.

MOOCs: Expectations and Reality

May 19, 2014 Comments off

MOOCs: Expectations and Reality (PDF)
Source: Teachers College, Columbia University

Over the past few years, observers of higher education have speculated about dramatic changes that must occur to accommodate more learners at lower costs and to facilitate a shift away from the accumulation of knowledge to the acquisition of a variety of cognitive and non-cognitive skills. All scenarios feature a major role for technology and online learning. Massive open online courses (MOOCs) are the most recent candidates being pushed forward to fulfill these ambitious goals. To date, there has been little evidence collected that would allow an assessment of whether MOOCs do indeed provide a cost-effective mechanism for producing desirable educational outcomes at scale. It is not even clear that these are the goals of those institutions offering MOOCs. This report investigates the actual goals of institutions creating MOOCs or integrating them into their programs, and reviews the current evidence regarding whether and how these goals are being achieved, and at what cost.

Through interviews with 83 administrators, faculty members, researchers, and other actors from 62 different institutions (see Appendices I, III and VI for details) active in the MOOCspace or more generally in online learning, we observed that colleges and universities have adopted several different stances towards engaging with MOOCs and are using them as vehicles to pursue multiple goals. Some institutions are actively developing MOOCs and may be termed “producers,” some are using MOOCs developed by other institutions in their programs and could be termed “consumers,” and a few are doing both. Others are adopting a “wait-and-see” approach, or have considered MOOCs and have decided against any form of official engagement. There is no doubt, however, that the advent of MOOCs has precipitated many institutions to consider or revisit their strategy with respect to online learning, whether at large scale or small.

Amidst Bitter Cold and Rising Energy Costs, New Concerns About Energy Insecurity

February 16, 2014 Comments off

Amidst Bitter Cold and Rising Energy Costs, New Concerns About Energy Insecurity
Source: Columbia University (Mailman School of Public Health)

With many regions of the country facing an unrelenting cold snap, the problem of energy insecurity continues to go unreported despite its toll on the most vulnerable. In a new brief, researchers at the Mailman School of Public Health paint a picture of the families most impacted by this problem and suggest recommendations to alleviate its chokehold on millions of struggling Americans. The authors note that government programs to address energy insecurity are coming up short, despite rising energy costs.

Energy Insecurity (EI) is measured by the proportion of household energy expenditures relative to household income. Lower-income families are more likely to experience EI because they tend to live in housing that has not benefited from the structural improvements that wealthier Americans can afford.

Follow

Get every new post delivered to your Inbox.

Join 930 other followers