Tim Bollerslev: Complex Puzzles, Simple Solutions

Tim Bollerslev: Complex Puzzles, Simple Solutions

14 July 2010 12:00AM

Normal 0 false false false EN-US X-NONE X-NONE /* Style Definitions */ table.MsoNormalTable {mso-style-name:"Table Normal"; mso-tstyle-rowband-size:0; mso-tstyle-colband-size:0; mso-style-noshow:yes; mso-style-priority:99; mso-style-qformat:yes; mso-style-parent:""; mso-padding-alt:0in 5.4pt 0in 5.4pt; mso-para-margin-top:0in; mso-para-margin-right:0in; mso-para-margin-bottom:10.0pt; mso-para-margin-left:0in; line-height:115%; mso-pagination:widow-orphan; font-size:11.0pt; font-family:"Calibri","sans-serif"; mso-ascii-font-family:Calibri; mso-ascii-theme-font:minor-latin; mso-fareast-font-family:"Times New Roman"; mso-fareast-theme-font:minor-fareast; mso-hansi-font-family:Calibri; mso-hansi-theme-font:minor-latin;} Tim Bollerslev likes to find practical solutions to practical problems.  He is well known for his GARCH modeling framework, which since the late 1980s has been the de rigueur analytical tool for calculating the uncertainty of financial asset returns.  By extrapolating from past price movements, the “standard” GARCH model is a particularly easy-to-understand technique that has found wide ranging applications in all areas of both academic and practical asset pricing finance.

Bollerslev arrived to graduate school at UC San Diego soon after Robert Engle published his ARCH model.  The way that the ARCH model dealt with time-varying uncertainty was brand new—and it won Engle the 2003 Nobel Prize in Economics.  The first empirical application of the ARCH model was focused on the Philips Curve and uncertainty of inflation rates in relation to unemployment. Bollerslev saw similar features in variances of financial data, albeit much more persistent, and as a grad student he created a generalized version of the ARCH model, called the GARCH model, to better handle the long “memory” seen in such data.  Practitioners in the financial industry, especially in the options market, already knew that if stock price volatility was high today it was probably going to be high tomorrow, but until the GARCH model they didn’t have a formal way of actually calculating it.  Since then, multiple new additions and modifications have been designed, but the basic premise behind all of these “new” models remains the same as in the basic GARCH model.

Bollerslev has also been highly influential in the rapidly growing area of high-frequency finance, and his work on so-called “realized volatility” measures has already found wide ranging practical applications. “Suppose that the opening and the closing price of an asset are the same,” says Bollerslev “This flat return day could very well mask a lot of intraday variation.” As such, the high-frequency data is incredibly useful and essentially acts like a microscope for better understanding the true price process.

In related research, Bollerslev has studied the linkage between financial markets and the real economy, in the form news announcement effects and the immediate reaction to the releases of key economic indicators. He also sees the current financial crisis as an opportunity to create better models and measures for the role that “fears” play in financial markets. To this end he is currently working on new ways in which to more accurately estimate the “tails” of high-frequency asset return distributions.

Although the theory underlying most of Bollerslev 's current research relies on fairly complex statistical ideas, he is committed to solving the high-frequency modeling, estimation, and forecasting questions with pragmatic and elegant solutions.