Research

Working Papers

JDI

Workshops

QRDC

Research Areas

Conferences

Public Lectures

Prizes and Distinctions

Recent QED Working Papers

Previous Pause Next

#1430.

Ardyn Nordstrom, Christopher Cotton

Impact of a Severe Drought on Education: More Schooling but Less Learning

From October 2015 to April 2016, Southern Africa experienced one of the severest droughts in history. The drought's intensity varied significantly across locations. This provides a natural experiment to estimate the effect of large, negative agricultural shocks. We consider the impact of this shock on children’s educational outcomes using data from rural Zimbabwe. Those who experienced the drought may suffer from decreases in income and food access. This can affect household resource allocation and schooling decisions while exposing individuals to stress and uncertainty. We find the…

#1429.

Samuel Brien, Michael Jansson, Morten Ø. Nielsen

Nearly Efficient Likelihood Ratio Tests of a Unit Root in an Autoregressive Model of Arbitrary Order

We study large-sample properties of likelihood ratio tests of the unit root hypothesis in an autoregressive model of arbitrary, finite order. Earlier research on this testing problem has developed likelihood ratio tests in the autoregressive model of order one, but resorted to a plug-in approach when dealing with higher-order models. In contrast, we consider the full model and derive the relevant large-sample properties of likelihood ratio tests under a local-to-unity asymptotic framework. As in the simpler model, we show that the full likelihood ratio tests are nearly efficient, in the…

#1428.

James G. MacKinnon, Morten Ø. Nielsen, Matthew D. Webb

Testing for the appropriate level of clustering in linear regression models

Reliable inference with clustered data has received a great deal of attention in recent years. The overwhelming majority of this research assumes that the cluster structure is known. This assumption is very strong, because there are often several possible ways in which a dataset could be clustered. We propose two tests for the correct level of clustering. One test focuses on inference about a single coefficient, and the other on inference about two or more coefficients. We also prove the asymptotic validity of a wild bootstrap implementation. The proposed tests work for a null hypothesis…

#1427.

Brant Abbott, Robin Brace

Has Consumption Inequality Mirrored Wealth Inequality in the Survey of Consumer Finances?

A method to impute consumption expenditure inequality between wealth groups in the Survey of Consumer Finances is provided, allowing for measurement error that is correlated with income and wealth. Identification is derived from observing food at home and away, which are relative necessities and luxuries, respectively. The gap in expenditure between top and bottom wealth quintiles increased by 50% between 2004 and 2013, indicating that increases in wealth inequality have passed through to consumption.

#1426.

Christopher Cotton, Ardyn Nordstrom, jordan_naowski_wp, Eric Richert

Community Campaigns to Improve Attitudes towards Girls' Education Can Increase Math Scores and Enrollment

We show that information campaigns intended to improve the attitudes and beliefs about girls’ education throughout communities can increase girls’ mathematics performance and school enrolment. These campaigns also increase caregiver support for girls’ education. Our analysis uses data from a large, randomized UKAid Girls’ Education Challenge (GEC) project in rural Zimbabwe, where the staggered roll out of the project allows for us to isolate the impact of a community-wide information campaign to promote girls’ education by shifting the attitudes and beliefs of girls, parents, teachers and…

#1425.

Morten Ø. Nielsen, Antoine Noël

To infinity and beyond: Efficient computation of ARCH(\infty) models

This paper provides an exact algorithm for efficient computation of the time series of conditional variances, and hence the likelihood function, of models that have an ARCH($\infty$) representation. This class of models includes, e.g., the fractionally integrated generalized autoregressive conditional heteroskedasticity (FIGARCH) model. Our algorithm is a variation of the fast fractional difference algorithm of \cite{JensenNielsen2014}. It takes advantage of the fast Fourier transform (FFT) to achieve an order of magnitude improvement in computational speed. The efficiency of the algorithm…

#1424.

Charles Beach, Frank Milne

Ontario Post-Secondary Education Funding Policies: Perverse Incentives and Unintended Consequences

This paper offers some observations on the funding of post-secondary schools in Ontario and Canada more broadly. Specifically, it notes how limited public funding for domestic students has provided strong incentives for PSE schools to attract full fee-paying international students, whose numbers have risen dramatically in recent years in Canada. The result has been a rising financial exposure of such schools to sudden external funding shocks and an increasing risk to the overall quality and available curriculum of programs delivered to all students. The paper also comments on Ontario plans…

#1423.

collin_brown_workingpaper, Jonathan Chiu, Thorsten V. Koeppl

What Drives Bitcoin Fees? Using Segwit to Assess Bitcoin's Long-run Sustainability

We use block level data from the Bitcoin blockchain to estimate the impact of congestion and the USD price on average fee rates. The introduction and adoption of the Segwit protocol allows us to identify an aggregate demand curve for bitcoin transactions. We nd that Segwit has reduced fee revenue by about 80%. Fee revenue could be maximized at a blocksize of about 0.6 MB when Segwit adoption remains at 40%. At this blocksize, maximum fee revenue would be roughly 1/8 of the current block reward { or the equivalent of 1.6375 BTC as a reward in the long run given current prices and demand for…

#1422.

Jason Allen, Robert Clark, Brent R. Hickman, Eric Richert

Resolving Failed Banks: Uncertainty, Multiple Bidding & Auction Design

The FDIC resolves insolvent banks using an auction process in which bidding is multidimensional and the rule used to evaluate bids along the different dimensions is proprietary. Uncertainty about the scoring rule leads banks to simultaneously submit multiple differentiated bids. This resolution mechanism typically results in considerable losses for the FDIC—$90 billion during the crisis. Our objective is to see whether the mechanism could be improved. To do so, we propose a methodology for analyzing auction environments where bids are ranked according to multiple attributes chosen by…

Events

There are currently no upcoming research events.

Working Papers

JDI

Workshops

QRDC

Research Areas

Conferences

Public Lectures

Prizes and Distinctions

Graduate Research Awards

Research by four QED alumni and a PhD candidate earn graduate research awards.

COVID-19 and Econ Requirements

Grading of Winter 2020 courses