Events

Professor Stanislav Anatolyev - New Economic School, Moscow

Sequential Testing with Uniformly Distributed Size

Abstract: Sequential procedures of testing for structural stability do not provide enough guidance on the shape of boundaries that are used to decide on acceptance or rejection, requiring only that the overall size of the test is asymptotically controlled. We introduce and motivate a reasonable criterion for a shape of boundaries which requires that the test size be uniformly distributed over the testing period. Under this criterion, we numerically construct boundaries for most popular sequential tests that are characterized by a test statistic behaving asymptotically either as a Wiener process or Brownian bridge. We handle this problem both in a context of retrospecting a historical sample and in a context of monitoring newly arriving data. We tabulate the boundaries by fitting them to certain flexible but parsimonious functional forms. Interesting patterns emerge in an illustrative application of sequential tests to the Phillips curve model.

Download paper (pdf, 816kb)

6 November

Professor David Vines - Oxford University

Keynes, Finance, and the Future of Macroeconomics

Abstract: The lecture will have four parts: (1) a description of the Krugman’s story in his ‘How Did Economists Get It So Wrong’ piece, and a demonstration that his story, although suggestive, is inadequate, (2) a description of the part that Keynesian insights and Keynesian methods need to play in our response to the crisis, (3) a description of what macroeconomists need to understand about the financial system, and (4) a demonstration that Keynesian methods will be important in helping us to build the required understanding of the financial system.

Professor Timo Teräsvirta - University of Aarhus

Conditional Correlations Models of Autoregressive Conditional Heteroskedasticity with Nonstationary GARCH Equations (joint work with Cristina Amado)

Abstract: We investigate the effects of careful modelling the long-run dynamics of the volatilities of stock market returns on the conditional correlation structure. To this end we allow the individual unconditional variances in Conditional Correlation GARCH models to change smoothly over time by incorporating a nonstationary component in the variance equations. The modelling technique to determine the parametric structure of this time-varying component is based on a sequence of specification Lagrange multiplier-type tests derived in Amado and Teräsvirta (2009). The variance equations combine the long-run and the short-run dynamic behaviour of the volatilities. The structure of the conditional correlation matrix is assumed to be either time independent or to vary over time. We apply our model to seven pairs of daily returns of stocks belonging to the S&P 500 stock index and traded at the New York Stock Exchange. The results suggest that accounting for deterministic changes in the unconditional variances considerably improves the fit of the multivariate Conditional Correlation GARCH models to the data. The effect of careful specification of the variance equations on the estimated correlations is variable: in some cases rather small, in others more discernible.

2 October

Dr Andrew Patton - University of Oxford

Data-based Ranking of Realised Volatility Estimators

Abstract: This paper presents new methods for formally comparing the accuracy of estimators of the quadratic variation of a price process. I provide conditions under which the relative average accuracy of competing estimators can be consistently estimated (as T → infinity) from available data, and show that existing tests from the forecast evaluation literature may be adapted to the problem of ranking these estimators. The proposed methods eliminate the need for specific assumptions about the properties of the microstructure noise, and the need to estimate quantities such as integrated quarticity or the noise variance, and facilitate comparisons of estimators that would be difficult using methods from the extant literature, such as those based on different sampling schemes (calendar-time vs. tick-time). In an application to high frequency IBM stock price data between 1996 and 2007, I find that tick-time sampling is generally preferable to calendar-time sampling, and that the optimal sampling frequency is between 15 seconds and 5 minutes, when using standard realised variance.

Professor Roger Craine - UC Berkeley

The Yield Curve Conundrum

Abstract: Between 2004-2006 the US Federal Reserve relentlessly increased the Federal Funds Target rate by ¼% at seventeen consecutive Federal Open Market Committee meetings. The Target
rose from 1% to 5 ¼%. Short maturity yields dutifully followed the target, but long maturity yields (10 years or more) actually fell until by June 2006 they were less than short maturity yields. Alan Greenspan,
Chairman of the Federal Reserve at the time, labeled the unusual behavior of the yield curve a conundrum. We find that unusually strong demand by foreigners for US bonds led to yields 1 ½% lower than they would have been otherwise. Monetary and macroeconomic surprises had almost no effect on long maturity yields. In the future if foreigners switch their holdings to non-dollar denominated assets
US yields will have to rise above what they would have been otherwise.

Professor Rudolf Winter-Ebmer - Linz University

Clash of Career and Family: Fertility Decisions after Job Displacement

Abstract: In this paper we investigate how fertility decisions respond to unexpected career interruptions which occur as a consequence of job displacement. Using an event study approach we compare the birth rates of displaced women with those of women unaffected by job loss after establishing the pre-displacement comparability of these groups. Our results reveal that job displacement reduces average fertility by 5 to 10% in both the short and medium term (3 and 6 years) and that these effects are largely explained by the response of white collar women. Using an instrumental variable approach we provide evidence that the reduction in fertility is not due to the income loss generated by unemployment but arises because displaced workers undergo a career interruption. These results are interpreted in the light of a model in which the rate of human capital accumulation slows down after the birth of a child and all specific human capital is destroyed upon job loss.

John Geweke - University of Iowa

Bayesian Modeling of Conditional Distributions.

Abstract: In econometric modeling the problem of inferring the distribution of a variable of interest conditional on a vector of covariates arises repeatedly. Examples include distributions of future asset returns conditional on available information and the assessment of changing inequality in earnings conditional on characteristics like age and education. Typically the conditional distribution cannot reasonably be confined to a known parametric family of models. Since the entire conditional distribution, and not just the conditional mean, is important the voluminous parametric and nonparametric regression literature does not address this problem. This paper introduces a new variant of mixture of experts models developed in the neural computation literature over the past decade, using probit gating functions. As the number of mixture components increases the Kullback-Leibler distance to any conditional distribution in the exponential family becomes arbitrarily small. The paper shows that these models are practical for data sets commonly used in applied econometrics, and they outperform widely used alternatives.

5 April

Robert Engle - New York University, Stern School of Business

New Approaches to Estimating Correlations

Robert Engle, the Michael Armellino Professor of Finance at New York University Stern School of Business, was awarded the 2003 Nobel Prize in Economics for his research on the concept of autoregressive conditional heteroskedasticity (ARCH). He developed this method for statistical modeling of time-varying volatility and demonstrated that these techniques accurately capture the properties of many time series. Professor Engle shared the prize with Clive W. J. Granger of the University of California at San Diego.

Professor Engle is an expert in time series analysis with a long-standing interest in the analysis of financial markets. His ARCH model and its generalizations have become indispensable tools not only for researchers, but also for analysts of financial markets, who use them in asset pricing and in evaluating portfolio risk. His research has also produced such innovative statistical methods as cointegration, common features, autoregressive conditional duration (ACD), CAViaR and now dynamic conditional correlation (DCC) models.

6 October

Avner Kalay - Tel Aviv University and University of Utah

Ex Dividend Arbitrage in Option Markets, Estimated Volume of Trade, and Market Efficiency.

Abstract: We examine the behavior of call options during the ex-dividend period of their underlying stocks. The evidence is inconsistent with the predictions of rational exercise policy; a significant fraction of the open interest remains unexercised. The potential profits to the option writers trigger a sophisticated trading scheme that enable short term traders to receive a significant fraction of the gains. The trading scheme inflates reported volume and distorts its traditional relations to liquidity. The dramatic increases in volume of trade on the last cum-dividend day are made possible by limitations on transaction costs passed by the various option exchanges. Yet, option pricing models based on the assumption of rational exercise policy involve only minor mistakes.

15 September

Bob Gregory - Australian National University

Welfare Reform and the Disappointing Employment Aspects of the Current Boom.

Abstract: How is employment evolving in the current economic boom? What is happening to welfare recipients? Does Australian need radical welfare reform similar to the US economy?

8 September

Susan E. Mayer - University of Chicago, Harris School of Public Policy Studies (Dean)

The Relationship between Income Inequality and Equality of Opportunity.

Ralf Becker - University of Manchester

Thoughts on Evaluating Variance Covariance Forecasts.