6533b86dfe1ef96bd12c9715

RESEARCH PRODUCT

Simulating term structure of interest rates with arbitrary marginals

Andrea ConsiglioSergio Salvino Guirreri

subject

Logarithmmedia_common.quotation_subjectYield (finance)Management Science and Operations ResearchTerm (time)Interest rateScenario simulationyield curveSettore SECS-S/06 -Metodi Mat. dell'Economia e d. Scienze Attuariali e Finanz.fat tailsLog-normal distributionKurtosisEconometricsvector autoregressive modelYield curveStatistics Probability and UncertaintyBusiness and International ManagementDecision modelmedia_commonMathematics

description

Decision models under uncertainty rely their analysis on scenarios of the economic factors. A key economic factor is the term structure of interest rates (yields). Simulation models of the yield curve usually assume that the conjugate distribution of the interest rates is lognormal. Dynamic models, like vector auto-regression, implicitly postulate that the logarithm of the interest rates is normally distributed. Statistical analyses have, however, shown that stationary transformations (yield changes) of the interest rates are substantially leptokurtic, thus posing serious doubts on the reliability of the available models. We propose in this paper a VARTA model (Biller and Nelson, 2003) to simulate term structures of the interest rates with arbitrary marginals. We will show that such an approach is able to simulate paths of the entire yield curve with distributional properties very close to those found in the empirical data.

10.1504/ijram.2011.042670http://hdl.handle.net/10447/60215