Stats › Volatiliteit en VIX › Jumps in variance
Published estimates of the jump share of index variance differ by a factor of seven
| Instrument and definition | Jump share | Steekproef |
|---|---|---|
| S&P 500 futures, unfiltered | 14.4% | Jan 1990 to Dec 2002 |
| 30 year bond futures, unfiltered | 12.6% | Jan 1990 to Dec 2002 |
| Mark against dollar, unfiltered | 7.2% | Dec 1986 to Jun 1999 |
| S&P 500 tracker, bipower based | ongeveer 2% | Jun 1997 to Jul 2008 |
| Average individual firm, bipower based | ongeveer 13% | Jun 1997 to Jul 2008 |
The unfiltered measure is the realised variance minus the bipower variation, floored at zero, with no significance filter applied. The bipower based figure uses a filtered decomposition. For the same underlying index the two published figures are 14.4 and about 2 per cent. No jump share number should be quoted without its definition, its instrument and its sample attached.
One study puts jumps at 14.4 per cent of S&P 500 futures quadratic variation and another at about two per cent for the index tracker. The difference is the jump definition, and neither figure means anything without it.
Alleen voor leden
De rest van deze pagina is voor leden
Below this point there are 5 sections, 1 table and 4 named sources, roughly 900 words of it. Every figure carries the source it came from and the date the data is from.
Je kunt elke statistiek in de bibliotheek gratis blijven bekijken. De intro en de samenvatting zijn altijd open.