. 6
( 7)


˜less-one™ method) weekly squared
GARCH deviations to are not in¬‚uenced
by ˜outliers™.
GARCH-t proxy ˜actual
(ranked) vol.™ Performance of
GARCH-t is
consistently much
worse. Same results
for all four stock
Data Data Forecasting Forecasting Evaluation
Author(s) Asset(s) period frequency methods and rank horizon and R-squared Comments

41. Franses and Stock indices 1986“94 W QGARCH 1 week ahead MedSE QGARCH is best if
Van Dijk (Germany, RW GARCH estimated from data has no
(1996) Netherlands, GJR rolling 4 years. extremes. RW is
Spain, Italy, (ranked) Use weekly best when 87™s crash
Sweden) squared is included. GJR
deviations to cannot be
proxy ˜actual recommended.
vol.™ Results are likely to
be in¬‚uenced by
MedSE that penalize
Brailsford and Faff
(1996) support GJR
as best model
although it
underpredicts over
70% of the time
42. Frennberg and VW Swedish In: M 1 month ahead MAPE, R 2 is S: seasonality
AR12 (ABS)-S RW,
Hansson stock market 1919“1976 estimated from 2“7% in ¬rst adjusted. RW model
ImpliedBS ATM Call
(1996) returns Out: 1977“82, (option maturity recursively period and seems to perform
1983“90 closest to 1 month) re-estimated 11“24% in remarkably well in
Index option Jan87“Dec90 GARCH-S, ARCH-S expanding second, more such a small stock
(European (ranked) sample. Use volatile period. market where
style) daily ret. to returns exhibit
H0 : ±implied = 0
Models that are not
compile strong seasonality.
and βimplied = 1
adj. for seasonality
monthly vol., cannot be Option was
did not perform as
adjusted for rejected with introduced in 86 and
autocorrelation robust SE covered 87™s crash;
outperformed by
did not perform as
well in the more
volatile second
43. Fung, Lie and £/$, C$/$, 1/84“2/87 D Option RMSE, MAE of Each day, 5 options
Moreno FFr$, DM/$, (pre-crash) maturity; overlapping were studied; 1
Impliedvega, elasticity
(1990) ¥/$ & SrFr/$ overlapping forecasts ATM, 2 just in and 2
Impliedequal weight
options on periods. Use just out. De¬ne
HIS40 days , ImpliedITM
PHLX (ranked, all implied sample SD of ATM as S = X,
are from calls) daily returns OTM marginally
over option outperformed ATM.
maturity to Mixed together
proxy ˜actual implied of different
vol.™ contract months
Data Data Forecasting Forecasting Evaluation
Author(s) Asset(s) period frequency methods and rank horizon and R-squared Comments

44. Fung and S&P500, DM$ 3/83“7/89 D (15 min) RV-AR(n) 1 day ahead. RMSE and MAE RV: Realized vol.
Hsieh (1991) US T-bond (DM/$ Use 15-min from 15-min returns.
ImpliedBAW NTM Call/Put of log σ
futures from RV, RW (C-t-C) data to AR(n):
Futures and 26 Feb 85) HL construct autoregressive lags
futures options (ranked, some of the ˜actual vol.™ of order n. RW
differences are (C-t-C): random
small) walk forecast based
on close to close
returns. HL:
Parkinson™s daily
high-low method.
Impact of 1987
crash does not
appear to be drastic
possibly due to
taking log. In
high-frequency data
forecasting power
45. Gemmill 13 UK stocks May78“Jul83 M 13“21 non- ME, RMSE, Adding HIS
(1986) LTOM options. overlapping MAE aggregated increases R 2 from
ImpliedATM, vega WLS
option maturity across stocks and 12% to 15%. But ex
Impliedequal, OTM, elasticity
Stock price Jan 78“Nov83 D
(each average time. R 2 are ante combined
HIS20 Weeks
(ranked, all implied are 19 weeks). Use 6“12% (pooled) forecast from HIS
from calls) sample SD of and 40% (panel and ImpliedITM
weekly returns with ¬rm speci¬c turned out to be
over option intercepts). All worse than
maturity to individual forecasts.
± > 0, β < 1
proxy ˜actual Suffered small
vol.™ sample and
problems and
omitted dividends
Data Data Forecasting Forecasting Evaluation
Author(s) Asset(s) period frequency methods and rank horizon and R-squared Comments

46. Gray (1996) US 1m T-Bill 1/70“4/94 W RSGARCH with time 1 week ahead R 2 calculated Volatility follows
varying probability (model not without constant GARCH and CIR
GARCH re-estimated). term, is 4 to 8% square root process.
Constant variance Use weekly for RSGARCH, Interest rate rise
(ranked) squared negative for increases probability
deviation to some CV and of switching into
proxy volatility GARCH. high-volatility
Comparable regime
RMSE and MAE Low-volatility
between persistence and
GARCH and strong rate level
RSGARCH mean reversion at
high-volatility state.
At low-volatility
state, rate appears
random walk and
volatility is highly
47. Guo (1996a) PHLX US$/¥ Jan91“Mar93 D Information not Regression with Use mid of bid“ask
options available robust SE. No option price to limit
information on ˜bounce™ effect.
GARCH R 2 and forecast Eliminate
biasedness ˜nonsynchroneity™
(ranked) by using
exchange rate and
option price. HIS
and GARCH contain
no incremental
ImpliedHeston and
ImpliedHW are
comparable and are
marginally better
than ImpliedBS .
Only have access to
Data Data Forecasting Forecasting Evaluation
Author(s) Asset(s) period frequency methods and rank horizon and R-squared Comments

48. Guo (1996b) PHLX US$/¥, Jan86“Feb93 Tick 60 days ahead. US$/DM R 2 is 4, Conclusion same as
ImpliedHW (WLS, 0.8
US$/DM Use sample 3, 1% for the Guo (1996a). Use
< S/X < 1.2, 20 <
options variance of three methods. Barone-
T < 60 days)
GARCH (1, 1) daily returns to (9, 4, 1% for Adesi/Whaley
Spot rate D
proxy actual US$/¥) All approximation for
HIS60 days
(ranked) volatility forecasts are American options.
biased No risk premium for
volatility variance
± > 0, β < 1
with robust SE risk. GARCH has no
information. Visual
inspection of ¬gures
suggests implied
forecasts lagged
49. Hamid (1998) S&P500 futures 3/83“6/93 D 13 schemes (including Non- RMSE, MAE Implied is better
options HIS, implied cross- overlapping 15, than historical and
strike average and 35 and 55 days cross-strike
intertemporal ahead averaging is better
averages) than intertemporal
(ranked, see comment) averaging (except
during very
turbulent periods)
50. Hamilton and Excess stock 1/65“6/93 M Bivariate RSARCH 1 month ahead. MAE Found economic
Lin (1996) returns Univariate RSARCH Use squared recessions drive
(S&P500 minus GARCH+L monthly ¬‚uctuations in stock
T-Bill) & Ind. ARCH+L residual returns returns volatility. ˜L™
Production AR(1) to proxy denotes leverage
(ranked) volatility effect. RS model
51. Hamilton and NYSE VW 3/7/62“ W RSARCH+L 1, 4 and 8 MSE, MAE, Allowing up to
Susmel stock index 29/12/87 GARCH+L weeks ahead. MSLE, MALE. 4 regimes with t
(1994) ARCH+L Use squared Errors calculated distribution.
(ranked) weekly residual from variance RSARCH with
returns to proxy and log variance leverage (L)
volatility provides best
forecast. Student-t is
preferred to GED
and Gaussian
52. Harvey and S&P100 (OEX) Oct85“Jul89 D 1 day ahead R 2 is 15% for Implied volatility
ImpliedATM calls+puts
Whaley (American binomial, implied for use calls and 4% for changes are
(1992) in pricing next puts (excluding statistically
shortest maturity >
15 days) day option 1987 crash) predictable, but
(predict changes in market was ef¬cient,
implied) as simulated
transactions (NTM
call and put and
delta hedged using
futures) did not
produce pro¬t
Data Data Forecasting Forecasting Evaluation
Author(s) Asset(s) period frequency methods and rank horizon and R-squared Comments

53. Heynen and 7 stock indices 1/1/80“ D SV(?) Non- MedSE SV appears to
Kat (1994) and 5 exchange 31/12/92 EGARCH overlapping 5, dominate in index
rates GARCH 10, 15, 20, 25, but produces errors
In: 80“87 RW 50, 75, 100 that are 10 times
Out: 88“92 (ranked, see also days horizon larger than
comment) with constant (E)GARCH in
(87™s crash
update of exchange rate. The
included in
parameters impact of 87™s crash
estimates. Use is unclear. Conclude
sample standard that volatility model
deviations of forecasting
daily returns to performance
proxy ˜actual depends on the asset
vol.™ class
54. Hol and S&P100 (VXO) 2/1/86“ D SIV 1, 2, 5, 10, 15 R 2 ranges SVX is SV with
Koopman 29/6/2001 SVX+ and 20 days between 17 and impliedVXO as an
(2002) SV ahead. Use 33%, MSE, exogenous variable
(ranked) 10-min returns MedSE, MAE. while SVX+ is SVX
to construct with persistence
± and β not
˜actual vol.™ reported. All adjustment. SIV is
forecasts stochastic implied
underestimate with persistence
actuals parameter set equal
to zero
55. Hwang and LIFFE stock 23/3/92“ D Log-ARFIMA-RV Forecast
1, 5, 10, 20, . . . , MAE, MFE
Satchell options 7/10/96 Scaled truncated 90, 100, 120 impliedATM BS of
(1998) Detrended days ahead IV shortest maturity
240 daily out-
Unscaled truncated estimated from option (with at 15
a rolling sample trading days to
MAopt n=20 -IV
of 778 daily maturity). Build MA
Adj MAopt n=20 -RV
GARCH-RV observations. in IV and ARIMA
(ranked, forecast Different on log (IV). Error
implied) estimation statistics for all
intervals were forecasts are close
tested for except those for
robustness GARCH forecasts.
The scaling in
is to adjust for
Jensen inequality
56. Jorion (1995) DM/$, ¥/$, 1/85“2/92 D 1 day ahead and R 2 is 5% (1-day) Implied is superior
ImpliedATM BS call+put
SrFr/$ futures 7/86“2/92 option maturity. or 10“15% to the historical
GARCH (1, 1), MA20
options on 3/85“2/92 (ranked) Use squared (option methods and least
CME returns and maturity). With biased. MA and
aggregate of robust SE, GARCH provide
square returns only marginal
±implied > 0 and
to proxy actual incremental
βimplied < 1 for
volatility long horizon and information
is unbiased for
1-day forecasts
Data Data Forecasting Forecasting Evaluation
Author(s) Asset(s) period frequency methods and rank horizon and R-squared Comments

57. Jorion (1996) DM/$ futures Jan85“Feb92 D 1 day ahead, R 2 about 5%. R 2 increases from
ImpliedBlack, ATM
options on GARCH(1, 1) use daily 5% to 19% when
H0 : ±implied = 0,
CME (ranked) squared to unexpected trading
βimplied = 1
proxy actual cannot be volume is included.
volatility rejected with Implied volatility
robust SE subsumed
information in
GARCH forecast,
expected futures
trading volume and
bid“ask spread
58. Karolyi 74 stock 13/1/84“ M 20 days ahead MSE Bayesian adjustment
Bayesian impliedCall
(1993) options 11/12/85 volatility to implied to
(Predict option price cross-sectional
not ˜actual vol.™) information such as
¬rm size, leverage
and trading volume
useful in predicting
next period option
59. Klaassen US$/£, 3/1/78“ D RSGARCH 1 and 10 days MSE of variance, GARCH(1, 1)
(1998) US$/DM and 23/7/97 RSARCH ahead. Use regression forecasts are more
US$/¥ GARCH(1, 1) mean adjusted though R 2 is not variable than RS
Out: 20/10/87“
(ranked) 1- and 10-day reported models. RS provides
return squares statistically
to proxy actual signi¬cant
volatility improvement in
forecasting volatility
for US$/DM but not
the other exchange
60. Kroner, Futures options Jan87“Dec90 D 225 calendar MSE, ME GR: Granger and
Kneafsey and on cocoa, (kept last 40 days (160 Ramanathan
ImpliedBAW Call
Claessens cotton, corn, observations working days) (1984)™s regression
(1995) gold, silver, for out-of- ahead, which is weighted combined
> ATM)
sugar, wheat sample longer than forecast, COMB: lag
HIS7 weeks > GARCH
forecast) (ranked) average implied in GARCH
conditional variance
Futures prices Jan87“ Jul91
equation. Combined
method is best
suggests option
market inef¬ciency
Data Data Forecasting Forecasting Evaluation
Author(s) Asset(s) period frequency methods and rank horizon and R-squared Comments

61. Lamoureux Stock options for 19/4/82“ D 90 to 180 days ME, MAE, Implied volatility is
ImpliedHull-White NTM Call
and 10 non-dividend- 31/3/84 (intermediate term to matching option RMSE. best but biased. HIS
Lastrapes paying stocks maturity, WLS) maturity estimated Average provides incremental
(1993) (CBOE) using rolling 300 implied is info. to implied and
HISupdated expanding estimate
GARCH observations and lower than has the lowest RMSE.
(ranked, based on expanding sample. actual for all When all three
regression result) Use sample stocks. R 2 on forecasts are included;
variance of daily variance varies ± > 0,
returns to proxy between 3 and 1 > βimplied > 0,
˜actual vol.™ 84% across βGARCH = 0,
stocks and βHIS < 0 with robust
models SE. Plausible
explanations include
option traders
overreact to recent
volatility shocks, and
volatility risk
premium is nonzero
and time-varying
62. Latane and 24 stock options 5/10/73“ W In-sample forecast Cross-section Used European model on
Implied vega weighted
Rendleman from CBOE 28/6/74 and forecast that correlation American options and
HIS4 years
omitted dividends.
(1976) (ranked) extend partially into between
volatility ˜Actual™ is more
the future. Use
weekly and monthly estimates for 38 correlated (0.686) with
returns to calculate weeks and a ˜Implied™ than HIS
actual volatility of 2-year period volatility (0.463) Highest
various horizons correlation is that
between implied and
actual standard
deviations which were
calculated partially into
the future

63. Lee (1991) $/DM, $/£, $/¥, 7/3/73“ W Kernel (Gaussian, 1 week ahead (451 RMSE, MAE. It Nonlinear models are, in
$/FFr, $/C$ 4/10/89 (Wed, truncated) observations in is not clear how general, better than linear
(Fed. Res. 12pm) Index (combining sample and 414 actual volatility GARCH. Kernel method
Out: 21
Bulletin) ARMA and observations was estimated is best with MAE. But
GARCH) out-of-sample) most of the RMSE and
EGARCH (1, 1) MAE are very close.
GARCH (1, 1) Over 30 kernel models
IGARCH with were ¬tted, but only
trend those with smallest
(rank changes see RMSE and MAE were
comment for reported. It is not clear
general how the nonlinear
assessment) equivalence was
constructed. Multi-step
forecast results were
mentioned but not shown
Data Data Forecasting Forecasting Evaluation
Author(s) Asset(s) period frequency methods and rank horizon and R-squared Comments

64. Li (2002) $/DM, $/£, $/¥ 3/12/86“ Tick 1, 2, 3 and 6 months MAE. R 2 ranges Both forecasts have
30/12/99 (5 min) ahead. Parameters 0.3“51% (implied), incremental
In: 12/8/86“ (implied better at not re-estimated. 7.3“47% (LM), information
11/5/95 shorter horizon Use 5-min returns 16“53% especially at long
$/£, $/¥
D and ARFIMA to construct ˜actual (encompass). For horizon. Forcing:
D better at long vol.™ both models, H0 :
13/6/99 ± = 0, β = 1
19/6/94“ horizon) produce
± = 0, β = 1 are
30/12/98 rejected and low/negative R 2
(especially for long
typically β < 1
with robust SE horizon). Model
realized standard
deviation as
ARFIMA without
log transformation
and with no
constant, which is
awkward as a
theoretical model
for volatility
65. Lopez C$/US$, 1980“1995 D SV-AR(1)-normal 1 day ahead and MSE, MAE, LL is the logarithmic
(2001) DM/US$, GARCH-gev probability forecasts LL, HMSE, loss function from Pagan
¥/US$, US$/£ EWMA-normal for four ˜economic GMLE and QPS and Schwert (1990),
In: 1980“1993
events™, viz. cdf of (quadratic HMSE is the
Out: GARCH-normal, -t
speci¬c regions. Use probability heteroscedasticity-adj.
1994“1995 EWMA-t
daily squared residuals scores) MSE from Bollerslev
AR(10)-Sq, -Abs
to proxy volatility. Use and Ghysels (1996) and
empirical distribution GMLE is the Gaussian
(approx. rank, see
to derive cdf quasi-ML function from
Bollerslev, Engle and
Nelson (1994). Forecasts
from all models are
indistinguishable. QPS
favours SV-n, GARCH-g
and EWMA-n

66. Loudon, FT All Share Jan71“Oct97 D EGARCH, GJR, Parameters estimated TS-GARCH is an
regression on
Watt and TS-GARCH, in period 1 (or 2) used absolute return version
log volatility
Yadav TGARCH to produce conditional of GARCH. All
(2000) NGARCH, variances in period 2 and a list of GARCH speci¬cations
diagnostics. R 2
VGARCH, (or 3). Use GARCH have comparable
GARCH, squared residuals as is about 4% in performance though
MGARCH ˜actual™ volatility period 2 and 5% nonlinear, asymmetric
(no clear rank, in period 3 versions seem to fare
forecast better. Multiplicative
GARCH vol.) GARCH appears worst,
followed by NGARCH
and VGARCH (Engle
and Ng 1993)
Data Data Forecasting Forecasting Evaluation
Author(s) Asset(s) period frequency methods and rank horizon and R-squared Comments

67. Martens S&P500 Jan94“ Tick Heteroscedasticity Scaled down one large
ImpliedBAW VXOstyle Non-overlapping 1, 5,
and futures, Dec2000 Log-ARFIMA 10, 20, 30 and 40 days adjusted RMSE. oil price.
Zein ¥/US$ futures, Jan96“ GARCH ahead. 500 daily R 2 ranges Log-ARFIMA
(2004) Dec2000 (ranked, see observations in 25“52% truncated at lag 100.
Crude Jun93“ comment also) in-sample which (implied), Based on R 2 , Implied
oil futures Dec2000 expands on each 15“48% (LM) outperforms GARCH
iteration across assets and in every case, and
horizons. Both beats Log-ARFIMA in
models provide ¥/US$ and crude oil.
incremental info. Implied has larger
to encompassing HRMSE than
regr. Log-ARFIMA in most
cases. Dif¬cult to
comment on implied™s
biasedness from
information presented

68. McKenzie 21 A$ bilateral Various length D Square vs. power 1 day ahead absolute RMS, ME, MAE. The optimal power is
(1999) exchange rates from 1/1/86 or transformation returns Regressions closer to 1 suggesting
4/11/92 to (ARCH models suggest all ARCH squared return is not
31/10/95 with various lags. forecasts are the best speci¬cation
See comment for biased. No R 2 in ARCH type model
rank) was reported for forecasting purpose
ME, MAE, CGARCH is the
69. McMillan, FTSE100 Jan84“Jul96 D, W, RW, MA, ES, EWMA j = 1 day, 1 week and
RMSE for component GARCH
Speight and FT All Share Jan69“Jul96 M GARCH, 1 month ahead based
on the three data symmetry loss model. Actual
Gwilym TGARCH,
function. volatility is proxied by
(2000) EGARCH, frequencies. Use j
Out: period squared returns MME(U) and mean adjusted squared
1996“1996 for to proxy actual MME(O), mean returns, which is likely
HIS, regression,
both series. (ranked) volatility mixed error that to be extremely noisy.
penalize Evaluation conducted
under/over on variance, hence
predictions forecast error statistics
are very close for most
models. RW, MA, ES
dominate at low
frequency and when
crash is included.
Performances of
GARCH models are
similar though not as
Data Data Forecasting Forecasting Evaluation
Author(s) Asset(s) period frequency methods and rank horizon and R-squared Comments

70. Noh, Engle S&P500 index Oct85“Feb92 D GARCH adj. for Option maturity. Equate Regression with
and options weekend and Based on 1000 days forecastability with call+put implieds,
Kane hols rolling period pro¬tability under daily dummies and
(1994) estimation the assumption of previous day returns to
weighted by an inef¬cient option predict next day
trading volume market implied and option
(ranked, predict prices. Straddle
option price strategy is not vega
not ˜actual neutral even though it
vol.™) might be delta neutral
assuming market is
complete. It is possible
that pro¬t is due to
now well-documented
post 87™s crash higher
option premium

M EGARCH(1, 2) 1 month ahead. Use
71. Pagan and US stock market 1834“1937 R 2 is 7“11% for The nonparametric
squared residual
Schw- Out: 1900“ GARCH(1, 2) 1900“25 and 8% models fared worse
2-step conditional monthly returns to
ert 1925 (low for 1926“37. than the parametric
(1990) volatility), variance proxy actual Compared with R 2 models. EGARCH
1926“1937 RS-AR(m) for variance, R 2 for came out best because
(high Kernel (1 lag) log variance is of the ability to capture
volatility) Fourier (1 or 2 smaller in 1900“25 volatility asymmetry.
lags) and larger in Some prediction bias
(ranked) 1926“37 was documented
72. Pong, US$/£ In: Jul87“ 1 month and 3 ME, MSE, Implied, ARMA and
5-, 30-min ImpliedATM, OTC
Shackleton, Dec93 (bias adj. months ahead at regression. R 2 ARFIMA have similar
Taylor and Out: Jan94“ using rolling 1-month interval ranges between performance.
Xu (2004) Dec98 regr. on last 22 and 39% GARCH(1, 1) clearly
5 years monthly (1-month) and inferior. Best
data) 6 and 21% combination is
Log-ARMA(2, 1) (3-month) Implied + ARMA
Log-ARFIMA (2, 1). Log-AR(FI)MA
(1, d, 1) forecasts adjusted for
GARCH(1, 1) Jensen inequality.
Dif¬cult to comment
on implied™s
biasedness from
information presented

73. Poteshman S&P500 1Jun88“ D Option maturity BS R 2 is over
ImpliedHeston F test for H0 : ±BS = 0,
(2000) (SPX) & 29Aug97 (about 3.5 to 4 50%. Heston
ImpliedBS (both βBS = 1 are rejected
futures implieds are weeks, non- implied produced though t-test supports
Heston futures
from WLS of all overlapping). Use similar R 2 but H0 on individual
estimation: Tick
5-min futures very close to coef¬cients. Show
options <7
inferred index being unbiased biasedness is not
months but >6
calendar days) return to proxy caused by bid“ask
˜actual vol.™
HIS1, 2, 3, 6 months spread. Using in σ ,
S&P500 7Jun62“May93 M (ranked) high-frequency
realized vol., and
Heston model, all help
to reduce implied
Data Data Forecasting Forecasting Evaluation
Author(s) Asset(s) period frequency methods and rank horizon and R-squared Comments

74. Randolph S&P500 2/1/1986“ Daily Non-overlapping 20 ME, RMSE, MAE, Mean reversion model
and Najand futures options 31/12/88 opening days ahead, re- MAPE (MRM) sets drift rate of
MRMATM implied
(1991) (crash included) Tick GARCH(1, 1) estimated using volatility to follow a
expanding sample. mean reverting process
HIS20 day
ATM calls only In: First 80
ImpliedBlack taking impliedATM (or
HIS) as the previous day
(ranked though the
vol. Argue that GARCH
error statistics
did not work as well
are close)
because it tends to
provide a persistent
forecast, which is valid
only in period when
changes in vol. are small

75. Schmalensee 6 CBOE stock 29/4/74“23/5/75 W 1 week ahead. Statistical tests Find implied rises when
ImpliedBS call
and Trippi options (simple average ˜Actual™ proxied by reject the stock price falls, negative
56 weekly
(1978) of all strikes and weekly range and hypothesis that IV serial correlation in
all maturities) average price responds positively changes of IV and a
(Forecast implied deviation to current volatility tendency for IV of
not actual different stocks to move
volatility) together. Argue that IV
might correspond better
with future volatility
76. Scott and DM/$, £/$, 14/3/83/“ Daily Non-overlapping MSE, R 2 ranges Simple B-S forecasts
ImpliedGk (vega,
Tucker C$/$, ¥/$ & 13/3/87 closing Inferred ATM, option maturity: 3, 6 from 42 to 49%. just as well as
(1989) SrFr/$ (pre-crash) tick NTM) and 9 months. Use In all cases, sophisticated CEV
American sample SD of daily model. Claimed
ImpliedCEV ± > 0, β < 1.
options on (similar rank) returns to proxy HIS has no omission of early
PHLX ˜actual vol.™ incremental info. exercise is not
content important. Weighting
scheme does not matter.
Forecasts for different
currencies were mixed

77. Sill (1993) S&P500 1959“1992 M HIS with exo 1 month ahead R 2 increase from Volatility is higher in
variables 1% to 10% when recessions than in
HIS additional expansions, and the
(see comment) variables were spread between
added commercial-paper and
T-Bill rates predict
stock market volatility

78. Szakmary, Futures options Various dates D Overlapping option R 2 smaller for
ImpliedBk, NTM HIS30 and GARCH
Ors, Kim on S&P500, 9 between maturity, shortest but ¬nancial have little or no
2Calls + 2Puts eq al weight
and interest rates, 5 Jan 83 and (23“28%), higher incremental
HIS30 , >10 days. Use sample
Davidson currency, 4 May 2001 GARCH SD of daily returns for metal and information content.
(2002) energy, 3 (ranked) over forecast horizon agricult. ±implied > 0 for 24
metals, 10 to proxy ˜actual vol.™ (30“37%), highest cases (or 69%), all 35
agriculture, 3 for livestock and cases βimplied < 1 with
livestock energy (47“58%) robust SE
Data Data Forecasting Forecasting Evaluation
Author(s) Asset(s) period frequency methods and rank horizon and R-squared Comments

79. Taylor JW DAX, 6/1/88“30/8/95 W STES (E, AE, 1 week ahead using ME, MAE, Models estimated based
(2004) S&P500, (equally split EAE) a moving window RMSE, R 2 on minimizing in-sample
Hang Seng, between in- and GJR of 200 weekly (about 30% for forecast errors instead of
FTSE 100, out-) (+Smoothed returns. Use daily HK and Japan ML. STES-EAE (smooth
Amsterdam variations) squared residual and 6% for US) transition exponential
EOE, Nikkei, GARCH returns to construct smoothing with return
Singapore All weekly ˜actual™ and absolute return as
MA20 weeks,
Share Riskmetrics volatility transition variables)
(ranked) produced consistently
better performance for
1-step-ahead forecasts

Represent one of the
80. Taylor SJ 15 US stocks Jan66“Dec76 D EWMA 1 and 10 days ahead Relative MSE
earliest studies in ARCH
(1986) FT30 Jul75“Aug82 Log-AR(1) absolute returns.
Various length ARMACH-Abs 2/3 of sample used class forecasts. The issue
6 metal
Nov74“Sep82 ARMACH-Sq in estimation. Use of volatility stationarity
5 agricultural Various length HIS daily absolute is not important when
futures (ranked) returns deviation as forecast over short
4 interest rate ˜actual vol.™ horizon. Nonstationary
Various length ARMACH-Sq is
futures series (e.g. EWMA) has
similar to
the advantage of having
fewer parameter
estimates and forecasts
respond to variance
change fairly quickly
81. Taylor SJ DM/$ futures 1977“83 D High, low and 1, 5, 10 and 20 days RMSE Best model is a weighted
(1987) closing prices ahead. Estimation average of present and
(see comment) period, 5 years past high, low and
closing prices with
adjustments for weekend
and holiday effects

82. Taylor SJ DM/$ 1/10/92“30/9/93 1 hour ahead MAE and MSE on 5-min return has
Quote Implied + ARCH
and Xu In: 9 months combined estimated from 9 std deviation and information incremental
(1997) Out: 3 months Implied, months in-sample variance to daily implied when
ARCH period. Use 5-min forecasting hourly
returns to proxy volatility
HIS9 months
DM/$ options ˜actual vol.™
D HISlast hour realised vol Friday macro news ARCH model includes
on PHLX (ranked) seasonal factors with hourly and 5-min
See comment for have no impact on returns in the last hour
details on implied forecast accuracy plus 120 hour/day/week
and ARCH seasonal factors. Implied
derived from NTM
shortest maturity (>9
calendar days) Call+Put
using BAW
Data Data Forecasting Forecasting Evaluation
Author(s) Asset(s) period frequency methods and rank horizon and R-squared Comments

83. Tse (1991) Topix Nikkei In: 1986“1987 D EWMA 25 days ahead ME, RMSE, MAE, Use dummies in mean
Stock Average Out: 88“89 HIS estimated from MAPE of variance equation to control for
ARCH, GARCH rolling 300 of 21 non- 1987 crash.
(ranked) observations overlapping 25-day Nonnormality provides
periods a better ¬t but a poorer
forecast. ARCH/GARCH
models are slow to
react to abrupt change
in volatility. EWMA
adjust to changes very

84. Tse and Singapore, 5 19/3/75 to D EWMA 25 days ahead RMSE, MAE EWMA is superior,
Tung (1992) VW market & 25/10/88 HIS estimated from GARCH worst.
industry GARCH rolling 425 Absolute returns > 7%
indices (ranked) observations are truncated. Sign of
nonstationarity. Some
85. Vasilellis Stock options In: W 3 months ahead. RMSE Implied: 5-day average
Combine (Implied +
and Meade 12 UK stocks 28/3/86“27/6/86 GARCH) Use sample SD of dominates 1-day
(1996) (LIFFE) Implied (various, see daily returns to implied vol. Weighting
In2 (for combined
comment) proxy ˜actual vol.™ scheme: max vega >
GARCH vega weighted >
EWMA elasticity weighted >
Out: 6/7/88’ max elasticity with ˜>™
HIS3 months
21/9/91 (ranked, results indicates better
not sensitive to forecasting
basis use to performance.
combine) Adjustment for div.
and early exercise:
Rubinstein > Roll >
constant yield. Crash
period might have
disadvantaged time
series methods

86. Vilasuso C$/$, FFr/$, In: 13/3/79“ D FIGARCH 1, 5 and 10 days MSE, MAE, and Signi¬cantly better
(2002) DM/$, ¥/$, 31/12/97 GARCH, ahead. Used daily Diebold- forecasting
£/$ IGARCH squared returns to Mariano™s test for performance from
Out: 1/1/98“ (ranked, proxy actual sig. difference FIGARCH. Built
31/12/99 GARCH volatility FIARMA (with a
marginally better constant term) on
than IGARCH) conditional variance
without taking log.
Truncated at lag 250

Data Data Forecasting Forecasting Evaluation
Author(s) Asset(s) period frequency methods and rank horizon and R-squared Comments

87. Walsh and Australian 1Jan 93“ 5-min to form EWMA GARCH 1 hour, 1 day and 1 MSE, RMSE, Index with larger
Tsou (1998) indices: 31 Dec95 H, D and W (not for weekly week ahead MAE, MAPE number of stock is
VW20, VW50 returns returns) estimated from a easier to forecast due to
In: 1 year
& VW300 HIS, IEV 1-year rolling diversi¬cation, but gets
Out: 2 years (improved sample. Use square harder as sampling
extreme-value of price changes interval becomes
method) (non-cumulative) as shorter due to problem
(ranked) ˜actual vol.™ of nonsynchronous
trading. None of the
GARCH estimations
converged for the
weekly series, probably
too few observations

88. Wei and SrFr/$, 2/83“1/90 M Use European formula
Implied GK ATM call Non-overlapping 1 R 2 30%(£), 17%
Frankel DM/$, ¥/$, (shortest month ahead. Use (DM), 3%(SrFr), for American style
(1991) £/$ options maturity) option. Also suffers
sample SD of daily 0%(¥). ± > 0,
(PHLX) from nonsynchronicity
exchange rate return β < 1 (except that
problem. Other tests
to proxy ˜actual vol.™ for £/$, ± > 0,
reveal that implied
β = 1) with
Spot rates heterosced. tends to overpredict
consistent SE high vol. and
underpredict low vol.
Forecast/implied could
be made more accurate
by placing more weight
on long-run average
89. West and C$/$, FFr/$, 14/3/73“ W GARCH(1, 1) RMSE and Some GARCH forecasts
j = 1, 12, 24 weeks
Cho (1995) DM/$, ¥$/$, 20/9/89 IGARCH (1, 1) estimated from regression test on mean revert to
£/$ AR(12) in absolute rolling 432 weeks. variance, R 2 varies unconditional variance in
In: 14/3/73“
AR(12) in squares Use j period squared from 0.1% to 4.5% 12 to 24 weeks. It is
Homoscedastic returns to proxy dif¬cult to choose
Out: 24/6/81“ Gaussian kernel actual volatility between models.
12/4/89 (no clear rank) Nonparametric method
came out worst though
statistical tests for do not
reject null of no
signi¬cance difference in
most cases

90. Wiggins S&P500 4/82“12/89 D ARMA model with 1 week ahead and 1 Bias test, ef¬ciency Modi¬ed Parkinson
(1992) futures 2 types of month ahead. test, regression approach is least biased.
estimators: Compute actual C-t-C estimator is three
1. Parkinson/Garmen- volatility from daily times less ef¬cient than
Klass extreme observations EV estimators. Parkinson
value estimators estimator is also better
2. Close-to-close than C-t-C at forecasting.
estimator 87™s crash period
(ranked) excluded from analysis
Data Data Forecasting Forecasting Evaluation
Author(s) Asset(s) period frequency methods and rank horizon and R-squared Comments

91. Xu and £/$, DM/$, ¥/$ In: Jan 85“Oct89 D ME, MAE, Implied works best and is
ImpliedBAW NTM TS or Non-overlapping 4
Taylor & SrFr/$ weeks ahead, RMSE, When unbiased. Other forecasts
(1995) PHLX options 18Oct89“4Feb92 have no incremental
GARCHNormal or GED estimated from a ±implied is set
rolling sample of equal to 0, information. GARCH
HIS4 weeks
(ranked) 250 weeks daily forecast performance not
βimplied = 1
futures rates
data. Use cannot be sensitive to distributional
cumulative daily rejected assumption about
squared returns to returns. The choice of
proxy ˜actual vol.™ implied predictor (term
structure, TS, or short
maturity) does not affect

92. Yu (2002) NZSE40 Jan80“Dec98 D SV (of log variance) 1 month ahead RMSE, MAE, Range of the evaluation
GARCH (3, 2), estimated from Theil-U and measures for most
In: 1980“1993
GARCH (1, 1) previous 180 to 228 LINEX on models is very narrow.
Out: 1994“1998
months of daily variance Within this narrow
HIS, MA5 yr or 10 yr
data. Use aggregate range, SV ranked ¬rst,
of daily squared performance of GARCH
(monthly revision)
returns to construct was sensitive to
actual monthly evaluation measure;
ARCH(9), RW,
volatility regression and EWMA
methods did not perform
well. Worst performance
from ARCH(9) and RW.
Volatile periods (Oct 87
and Oct 97) included in
in- and out-of-samples
93. Zumbach USD/CHF, 1/1/89“ H LM-ARCH 1 day ahead RMSE. Realized LM-ARCH, aggregates
(2002) USD/JPY 1/7/2000 F-GARCH estimated from volatility measured high-frequency squared
GARCH previous 5.5 years using hourly returns returns with a set of
And their integrated power law weights, is the
counterparts best though difference is
(ranked) small. All integrated
versions are more stable
across time

Ranked: models appear in the order of forecasting performance; best performing model at the top. If two weighting schemes or two forecasting models appear
at both sides of ˜>™, it means the l.h.s. is better than the r.h.s. in terms of forecasting performance. SE: Standard error. ATM: At the money. NTM: Near the
money. OTM: Out of the money. WLS: an implied volatility weighting scheme used in Whaley (1982) designed to minimize the pricing errors of a collection of
options. In some cases the pricing errors are multiplied by trading volume or vega to give ATM implied a greater weight. HIS: Historical volatility constructed
based on past variance/standard deviation. VXO: Chicago Board of Option Exchange™s volatility index derived from S&P100 options. VXO was renamed VXO
in September 2003. The current VXO is compiled using a model-free implied volatility estimate. All the research papers reviewed have used VXO (i.e. the old
VIX.) RS: Regime switching. BS: Black“Scholes. BK: Black model for pricing futures option. BAW: Barone-Adesi and Whaley American option pricing formula.
HW: Hull and White option pricing model with stochastic volatility. FW: Fleming and Whaley (1994) modi¬ed binomial method that takes into account wildcard
option. GK: Garman and Kohlhagan model for pricing European currency option. HJM: Heath, Jarrow and Morton (1992) forward rate model for interest rates.

Aggarwal, R., C. Inclan and R. Leal (1999) Volatility in emerging stock markets, Journal
of Financial and Quantitative Analysis, 34, 1, 33“55.
Ait-Sahalia, Y., P. A. Mykland and L. Zhang (2003) How often to sample a continuous-
time process in the presence of market microstructure noise, Working paper, Univer-
sity of Princeton.
Akgiray, V. (1989) Conditional heteroskedasticity in time series of stock returns: evi-
dence and forecasts, Journal of Business, 62, 55“80.
Alexander, C. (2001), Market Models: A Guide to Financial Data Analysis, John Wiley
& Sons Ltd, Chichester.
Alford, A.W., and J.R. Boatsman (1995) Predicting long-term stock return volatility:
Implications for accounting and valuation of equity derivatives, Accounting Review,
70, 4, 599“618.
Alizadeh, S., M.W. Brandt and F.X. Diebold (2002) Range-based estimation of stochastic
volatility models, Journal of Finance, 57, 3, 1047“1092.
Amin, K., and V. Ng (1997) Inferring future volatility from the information in implied
volatility in Eurodollar options: A new approach, Review of Financial Studies, 10,
Andersen, T.G. (1996) Return volatility and trading volume: An information ¬‚ow inter-
pretation of stochastic volatility, Journal of Finance, 51, 1, 169“204.
Andersen, T.G., L. Benzoni and J. Lund (2002) An empirical investigation of continuous
time equity return models, Journal of Finance, 57, 1239“1284.
Andersen, T., and T. Bollerslev (1998) Answering the skeptics: Yes, standard volatility
models do provide accurate forecasts, International Economic Review, 39, 4, 885“
Andersen, T.G., T. Bollerslev, F.X. Diebold and H. Ebens (2001) The distribution of
realized stock return volatility, Journal of Financial Economics, 61, 1, 43“76.
Andersen, T.G., T. Bollerslev, F.X. Diebold and P. Labys (2001) The distribution of
realized exchange rate volatility, Journal of American Statistical Association, 96,
453, 42“57.
Andersen, T.G., T. Bollerslev and S. Lange (1999) Forecasting ¬nancial market volatility:
Sample frequency vis-` -vis forecast horizon, Journal of Empirical Finance, 6, 5,
Andersen, T.G., T. Bollerslev, F.X. Diebold and P. Labys, 2003, Modeling and forecasting
realized volatility, Econometrica, 71, 2, 529“626.
202 References

Andersen, T.G., and B.E. Sorensen (1997) GMM and QML asymptotic standard
deviations in stochastic volatility models, Journal of Econometrics, 76, 397“
Artzner, P., F. Delbaen, J. Eber and D. Heath (1997) Thinking coherently, RISK Maga-
zine, 10, 11, 68“71.
Artzner, P., F. Delbaen, J. Eber and D. Heath (1999) Coherent measures of risk, Mathe-
matical Finance, 9, 3, 203“228.
Baillie, R.T., and T. Bollerslev (1989) The message in daily exchange rates: a conditonal-
variance tale, Journal of Business and Economic Statistics, 7, 3, 297“305.
Baillie, R.T., T. Bollerslev and H.O. Mikkelsen (1996) Fractionally integrated general-
ized autoregressive conditional heteroskedasticity, Journal of Econometrics, 74, 1,
Baillie, R.T., T. Bollerslev and M.R. Redfearn (1993) Bear squeezes, volatility spillovers
and speculative attacks in the hyperin¬‚ation 1920s foreign exchange, Journal of
International Money and Finance, 12, 5, 511“521.
Bakshi, G., C. Cao and Z. Chen (1997) Empirical performance of alternative option
pricing models, Journal of Finance, 52, 5, 2003“2049.
Bakshi, G., and N. Kapadia (2003) Delta-hedged gains and the negative market volatility
risk premium, Review of Financial Studies, 16, 2, 527“566.
Bali, T.G. (2000) Testing the empirical performance of stochastic volatility models of
the short-term interest rate, Journal of Financial and Quantitative Analysis, 35, 2,
Ball, C.A., and W.N. Torous (1984) The maximum likelihood estimation of security price
volatility: Theory, evidence and application to option pricing, Journal of Business,
57, 1, 97“113.
Bandi, F.M., and J.R. Russell (2004) Separating microstructure noise from volatility,
Working paper, University of Chicago.
Banks, E. (2004) Alternative risk transfer: Integrated risk management through insur-
ance, reinsurance and the capital markets, John Wiley & Sons Ltd, Chichester.
Barndorff-Nielsen, O.E., and N. Shephard (2003) Power and bipower variation with
stochastic volatility and jumps, Working paper, Oxford University.
Barone-Adesi, G., and R.E. Whaley (1987) Ef¬cient analytic approximation of American
option values, Journal of Finance, 42, 2, 301“320.
Bates, D.S. (1996) Testing option pricing models, in: Maddala, G.S., and C.R. Rao
(eds), Handbook of Statistics, vol. 14: Statistical Methods in Finance, Elsevier, North
Holland, Amsterdam, pp. 567“611.
Bates, D.S. (2000) Post-87 crash fears in S&P 500 futures options, Journal of Econo-
metrics, 94, 181“238.
Beckers, S. (1981) Standard deviations implied in option prices as predictors of future
stock price variability, Journal of Banking and Finance, 5, 363“382.
Beckers, S, (1993) Variances of security price returns based on high, low and closing
prices, Journal of Business, 56, 97“112.
Benzoni, L. (2001) Pricing options under stochastic volatility: An empirical investiga-
tion, Working paper, Carlson School of Management, Minneapolis, MN.
Bera, A.K., and M.L. Higgins (1993) ARCH models: properties, estimation and testing,
Journal of Economic Surveys, 7, 4, 305“365.
Bera, A., and M. Higgins (1997) ARCH and bilinearity as competing models for non-
linear dependence, Journal of Business and Economic Statistics, 15, 1, 43“50.
Beran, J. (1994) Statistics for Long Memory Process, John Ryland, Chapman & Hall.
Black, F. (1975) Fact and fantasy in the use of options, Financial Analysts Journal, 31,
References 203

Black, F, (1976) Studies of stock price volatility of changes, American Statistical Asso-
ciation Journal, 177“181.
Blair, B., S.-H. Poon and S.J. Taylor (2001) Forecasting S&P 100 volatility: The incre-
mental information content of implied volatilities and high frequency index returns,
Journal of Econometrics, 105, 5“26.
Bluhm, H.H.W., and J. Yu (2000) Forecasting volatility: Evidence from the German
stock market, Working paper, University of Auckland.
Bollen, B., and B., Inder (2002) Estimating daily volatility in ¬nancial markets utilizing
intraday data, Journal of Empirical Finance, 9, 551“562.
Bollerslev, T. (1986) Generalized autoregressive conditional heteroskedasticity, Journal
of Econometrics, 31, 307“328.
Bollerslev, T. (1987) A conditionally heteroskedastic time series model for speculative
prices and rates of return, Review of Economics and Statistics, 69, 3, 542“547.
Bollerslev, T. (1990) Modelling the coherence in short-run nominal exchange rates:
A multivariate generalized ARCH model, Review of Economics and Statistics, 72,
Bollerslev, T., R.Y. Chou and K.P. Kroner (1992) ARCH modeling in ¬nance: A Review
of the theory and empirical evidence, Journal of Econometrics, 52, 5“59.
Bollerslev, T., R.F. Engle and D.B. Nelson (1994) ARCH models, in: Engle, R.F.,
and D.L. McFadden (eds), Handbook of Econemetrics, Vol. IV, North Holland,
Amsterdam, pp. 2959“3038.
Bollerslev, T., R.F. Engle and J.M. Wooldridge (1988) A capital asset pricing model
with time-varying covariances, Journal of Political Economy, 96, 1, 116“131.
Bollerslev, T., and E. Ghysels (1996) Periodic autoregressive conditional heteroskedas-
ticity, Journal of Business and Economic Statistics, 14, 2, 139“151.
Bollerslev, T., and H.O. Mikkelsen (1996) Modeling and pricing long memory in stock
market volatility, Journal of Econometrics, 73, 1, 151“184.
Bollerslev, T., and H. O. Mikkelsen (1999) Long-term equity anticipation securities and
stock market volatility dynamics, Journal of Econometrics, 92, 75“99.
Boudoukh, J., M. Richardson and R.F. Whitelaw (1997) Investigation of a class of
volatility estimators, Journal of Derivatives, 4, 3, 63“71.
Brace, A., and A. Hodgson (1991) Index futures options in Australia “ An empirical
focus on volatility, Accounting and Finance, 31, 2, 13“31.
Brailsford, T.J., and R.W. Faff (1996) An evaluation of volatility forecasting techniques,
Journal of Banking and Finance, 20, 3, 419“438.
Brooks, C. (1998) Predicting stock market volatility: Can market volume help? Journal
of Forecasting, 17, 1, 59“80.
Buraschi, A., and J. C. Jackwerth (2001) The price of a smile: Hedging and spanning in
option markets, Review of Financial Studies, 14, 2, 495“527.
Canina, L., and S. Figlewski (1993) The informational content of implied volatility,
Review of Financial Studies, 6, 3, 659“681.
Cao, C.Q., and R.S. Tsay (1992) Nonlinear time-series analysis of stock volatilities,
Journal of Applied Econometrics, December, Supplement, 1, S165“S185.
Chan, K.C., G.A. Karolyi, F.A. Longstaff and A.B. Sanders (1992) An empirical com-
parision of alternative models of the short-term interest rate, Journal of Finance, 47,
3, 1209“1227.
Chernov, M. (2001) Implied volatilities as forecasts of future volatility, the market risk
premia, and returns variability, Working paper, Columbia Business School.
Chernov, M., and E. Ghysels (2000) A study towards a uni¬ed approach to the joint es-
timation of objective and risk neutral measures for the purposes of options valuation,
Journal of Financial Economics, 56, 3, 407“458.
204 References

Chiras, D., and S. Manaster (1978) The information content of option prices and a test
of market ef¬ciency, Journal of Financial Economics, 6, 213“234.
Chong, Y.Y., and D.F. Hendry, (1986) Econometric evaluation of linear macro-economic
models, Review of Economics Studies, 53, 671“690.
Christensen, B.J., and N.R. Prabhala (1998) The relation between implied and realized
volatility, Journal of Financial Economics, 50, 2, 125“150.
Christie, A.A. (1982) The stochastic behaviour of common stock variances: Value,
leverage, and interest rate effect, Journal of Financial Economics, 10, 407“
Christodoulakis, G.A., and S.E. Satchell (1998) Hashing GARCH: A re-assessment
of volatility forecast and perfomance, Chapter 6, pp. 168“192, in: Knight, J., and
S. Satchell (eds), Forecasting Volatility in the Financial Markets, Butterworth.
Christoffersen, P.F., and F.X. Diebold (2000) How relevant is volatility forecasting for
risk management? Review of Economics and Statistics, 82, 1, 12“22.
Clark, P. (1973) A subordinated stochastic process model with ¬nite variance for spec-
ulative prices, Econometrica, 41, 135“156.
Corradi, V. (2000) Reconsidering the continuous time limit of the GARCH(1,1) process,
Journal of Econometrics, 96, 145“153.
Cox, J.C., S.A. Ross and M. Rubinstein (1979) Option pricing: A simpli¬ed approach,
Journal of Financial Economics, 7, 229“263.
Cumby, R., S. Figlewski and J. Hasbrouck (1993) Forecasting volatilities and correlations
with EGARCH models, Journal of Derivatives, 1, 51“63.
Danielsson, J. (1994) Stochastic volatility in asset prices: Estimation with simulated
maximum likelihood, Journal of Econometrics, 64, 375“400.
Danielsson, J., and C.G. de Vries (1997) Tail index and quantile estimation with very
high frequency data, Journal of Empirical Finance, 4, 241“257.
Das, S.R., and R.K. Sundaram (1999) Of smiles and smirks: A term structure perpective,
Journal of Financial and Quantitative Analysis, 34, 2.
Davidian, M., and R.J. Carroll (1987) Variance function estimation, Journal of American
Statistical Association, 82, 1079“1091.
Day, T.E., and C.M. Lewis (1992) Stock market volatility and the information content
of stock index options, Journal of Econometrics, 52, 267“287.
Day, T.E., and C.M. Lewis (1993) Forecasting futures market volatility, Journal of
Derivatives, 1, 33“50.
Diebold, F.X. (1988) Empirical Modeling of Exchange Rate Dynamics, Springer Verlag,
New York.
Diebold, F.X., A. Hickman, A. Inoue and T. Schuermann (1998) Scale models, RISK
Magazine, 11, 104“107.
Diebold, F.X., and A. Inoue (2001) Long memory and regime switching, Journal of
Econometrics, 105, 1, 131“159.
Diebold, F.X., and J.A. Lopez (1995) Modelling volatility dynamics, in: Hoover, K.
(ed.), Macroeconomics: Developments, Tensions and Prospects, Kluwer, Dordtecht,
pp. 427“466.
Diebold, F.X., and R.S. Mariano (1995) Comparing predictive accuracy, Journal of
Business and Economic Statistics, 13, 253“263.
Dimson, E., and P. Marsh (1990) Volatility forecasting without data-snooping, Journal
of Banking and Finance, 14, 2“3, 399“421.
Ding, Z., C.W.J. Granger and R.F. Engle (1993) A long memory property of stock market
returns and a new model, Journal of Empirical Finance, 1, 83“106.
Doidge, C., and J.Z. Wei (1998) Volatility forecasting and the ef¬ciency of the Toronto
35 index options market, Canadian Journal of Administrative Science, 15, 1, 28“38.
References 205

Drost, F.C., and T.E. Nijman (1993) Temporal aggregation of GARCH process, Econo-
metrica, 61, 4, 909“927.
Duan, J. (1997) Augmented GARCH(p,q) process and its diffusion limit, Journal of
Econometrics, 79, 97“127.
Duf¬e, D., and K.J. Singleton (1993) Simulated moments estimation of Markov models
of asset prices, Econometrica, 61, 929“952.
Dunis, C.L., J. Laws and S. Chauvin (2000) The use of market data and model combi-
nation to improve forecast accuracy, Working paper, Liverpool Business School.
Durbin, J., and S.J. Koopman (2000) Time series analysis of non-Gaussian observations
based on state space models from both classical and Bayesian perpectives, Journal
of Royal Statistical Society Series, 62, 1, 3“56.
Ederington, L.H., and W. Guan (1999) The information frown in option prices, Working
paper, University of Oklahoma.
Ederington, L.H., and W. Guan (2000a) Forecasting volatility, Working paper, University
of Oklahoma.
Ederington, L.H., and W. Guan (2000b) Measuring implied volatility: Is an average
better? Working paper, University of Oklahoma.
Ederington, L.H., and W. Guan (2002) Is implied volatility an informationally ef¬cient
and effective predictor of future volatility? Journal of Risk, 4, 3.
Ederington, L.H., and J.H. Lee (2001) Intraday volatility in interest rate and foreign
exchange markets: ARCH, announcement, and seasonality effects, Journal of Futures
Markets, 21, 6, 517“552.
Edey, M., and G. Elliot (1992) Some evidence on option prices as predictors of volatility,
Oxford Bulletin of Economics & Statistics, 54, 4, 567“578.
Engle, R.F. (1982) Autoregressive conditional heteroscedasticity with estimates of the
variance of United Kingdom in¬‚ation, Econometrica, 50, 4, 987“1007.
Engle, R.F. (1993) Statistical models for ¬nancial volatility, Financial Analysts Journal,
49, 1, 72“78.
Engle, R.F., and T. Bollerslev (1986) Modelling the persistence of conditional variances,
Econometric Reviews, 5, 1“50.
Engle, R., and K.F. Kroner (1995) Multivariate simultaneous generalized ARCH, Econo-
metric Theory, 11, 122“150.
Engle, R.F., and G.J. Lee (1999) A long-run and short-run component model of stock
return volatility, in: Engle, R.F., and H. White (ed.), Cointegration, Causality and
Forecasting, Oxford University Press, Oxford, Chapter 10, pp. 475“497.
Engle, R.F., and V.K. Ng (1993) Measuring and testing the impact of news on volatility,
Journal of Finance, 48, 1749“1778.
Engle, R. F., V. Ng and M. Rothschild (1990) Asset pricing with a factor-ARCH covari-
ance structure: Empirical estimates for Treasury Bills, Journal of Econometrics, 45,
Fair, R.C., and R.J. Shiller (1989) The informational content of ex ante forecasts, Review
of Economics and Statistics, 71, 2, 325“332.
Fair, R.C., and R.J. Shiller (1990) Comparing information in forecasts from econometric
models, American Economic Review, 80, 3, 375“380.
Feinstein, S.P. (1989a) The Black“Scholes formula is nearly linear in sigma for at-the-
money options; therefore implied volatilities from at-the-money options are virtually
unbiased, Working paper, Federal Reserve Bank of Atlanta.
Feinstein, S.P. (1989b) Forecasting stock market volatility using options on index futures,
Economic Review (Federal Reserve Bank of Atlanta), 74, 3, 12“30.
Ferreira, M.A. (1999) Forecasting interest rate volatility from the information in histori-
cal data, Working paper, Department of Finance, University of Wisconsin-Madison.
206 References

Figlewski, S. (1997) Forecasting volatility, Financial Markets, Institutions and Instru-
ments (New York University Salomon Center), 6, 1, 1“88.
Figlewski, S., and T.C. Green (1999) Market risk and model risk for a ¬nancial institution
writing options, Journal of Finance, 54, 4, 1465“1999.
Fiorentini, G., A. Leon and G. Rubio (2002) Estimation and empirical performance of
Heston™s stochastic volatility model: The case of a thinly traded market, Journal of
Empirical Finance, 9, 225“255.
Fleming, J. (1998) The quality of market voltility forecasts implied by S&P 100 index
option prices, Journal of Empirical Finance, 5, 4, 317“345.
Fleming, J., and C. Kirby (2003) A closer look at the relation between GARCH and
stochastic autoregressive volatility, Journal of Financial Econometrics, 1, 365“
Fleming, J., and R.E. Whaley (1994) The value of wildcard options, Journal of Finance,
49, 1, 215“236, March.
Fleming, J., C. Kirby and B. Ostdiek (2000) The economic value of volatility timing
Journal of Finance, 56, 1.
Fleming, J., C. Kirby and B. Ostdiek (2002) The economic value of volatility timing
using realized volatility, Journal of Financial Economics, 67, 473“509.
Fleming, J., B. Ostdiek and R.E. Whaley (1995) Predicting stock market volatility: A
new measure, Journal of Futures Market, 15, 3, 265“302.
Forbes, K.J., and R. Rigobon (2002) No contagion, only interdependence: measuring
stock market co-movements, Journal of Finance, 57, 5, 2223“2262.
Fouque, J.-P., G. Papanicolaou and K.R. Sircar (2000) Derivatives in Financial Markets
with Stochastic Volatility, Cambridge University Press, Cambridge.
Franke, G., R.C. Stapleton and M.G. Subrahmanyam (1998) Who buys and who sells op-
tions: The role of options in an economy with background risk, Journal of Economic
Theory, 82, 1, 89“109.
Franses, P.H., and H. Ghijsels (1999) Additive outliers, GARCH and forecasting volatil-
ity, International Journal of Forecasting, 15, 1“9.
Franses, P.H., and D. Van Dijk (1996) Forecasting stock market volatility using (non-
linear) Garch models, Journal of Forecasting, 15, 3, 229“235.
Franses, P.H. and D. van Dijk (2000) Non-Linear Time Series Models in Empirical
Finance, Cambridge University Press, Cambridge.
French, K.R., G.W. Schwert and R.F. Stambaugh (1987) Expected stock returns and
volatility, Journal of Financial Economics, 19, 1, 3“30.
Frennberg, P., and B. Hansson (1996) An evaluation of alternative models for predicting
stock volatility, Journal of International Financial Markets, Institutions and Money,
5, 117“134.
Fridman, M., and L. Harris (1998) A maximum likelihood approach for non-Gaussian
stochastic volatility models, Journal of Business and Economic Statistics, 16, 284“
Friedman, B.M., and D.I. Laibson (1989) Economic implications of extraordinary move-
ments in stock prices, Brooking Papers on Economic Activity, 2, 137“189.
Fung, H.-G., C.-J. Lie and A. Moreno (1990) The forecasting performance of the implied
standard deviation in currency options, Managerial Finance, 16, 3, 24“29.
Fung, W.K.H., and D.A. Hsieh (1991) Empirical analysis of implied volatility: Stocks,
bonds and currencies, Working paper, Department of Finance, Fuqua School of
Gallant, A.R., P.E. Rossi and G. Tauchen (1993) Nonlinear dynamic structures, Econo-
metrica, 61, 4, 871“907.
References 207

Garman, M.B., and M.J. Klass (1980) On the estimation of security price volatilities
from historical data, Journal of Business, 53, 1, 67“78.
Gemmill, G. (1986) The forecasting performance of stock options on the London Traded
Options Markets, Journal of Business Finance and Accounting, 13, 4, 535“546.
Geske, R. (1979) The valuation of compound options, Journal of Financial Economics,
7, 63“81.
Ghysels, E., A. Harvey and E. Renault (1996) Stochastic volatility, pp. 119“191, in:
Maddala, G.S., and C.R. Rao (eds), Handbook of Statistics: Statistical Methods in
Finance, Vol. 14, Elsevier Science, Amsterdam.
Glosten, L.R., R. Jagannathan and D.E. Runkle (1993) On the relation between the
expected value and the volatility of the nominal excess return on stocks, Journal of
Finance, 48, 1779“1801.
Gourieroux, C. (1997) ARCH Models and Financial Applications, Springer, New York.
Granger, C.W.R. (1999) Empirical Modeling in Economics. Speci¬cation and Evalua-
tion. Cambridge University Press, Cambridge.
Granger, C.W.J. (2001) Long memory processes “ an economist™s viewpoint, Working
paper, University of California, San Diego.
Granger, C.W.J., and Z. Ding (1995) Some properties of absolute return: An alternative
measure of risk, Annales dEconomie et de Statistique, 40, 67“91.
Granger, C.W.J., Z. Ding and S. Spear (2000) Stylized facts on the temporal and dis-
tributional properties of absolute returns: An update, Working paper, University of
California, San Diego.
Granger, C.W.J., and N. Hyung (2004) Occasional structural breaks and long memory
with an application to the S&P500 absolute stock returns, Journal of Empirical
Finance, 11, 3, 399“421.
Granger, C.W.J., and R. Joyeux (1980) An introduction to long memory time series and
fractional differencing, Journal of Time Series Analysis, 1, 15“39.
Gray, S.F. (1996) Modeling the conditional distribution of interest rates as a regime-
switching process, Journal of Financial Economics, 42, 1, 27“62.
Guo, D. (1996a) The predictive power of implied stochastic variance from currency
options, Journal of Futures Markets, 16, 8, 915“942.
Guo, D. (1996b) The information content of implied stochastic volatility from currency
options, Canadian Journal of Economics, 29, S, 559“561.
Hamao, Y., R.W. Masulis and V. Ng (1989) Correlations in price changes and volatility
across international stock markets, Review of Financial Studies, 3, 281“307.
Hamid, S. (1998) Ef¬cient consolidation of implied volatilities and a test of intertemporal
averaging, Derivatives Quarterly, 4, 3, 35“49.
Hamilton, J.D. (1989) A new approach to the economic analysis of nonstationary time
series and the business cycle, Econometrica, 57, 357“384.
Hamilton, J.D., and G. Lin (1996) Stock market volatility and the business cycle, Journal
of Applied Econometrics, 11, 5, 573“593.
Hamilton, J.D., and R. Susmel (1994) Autoregressive conditional heteroskedasticity and
changes in regime, Journal of Econometrics, 64, 1“2, 307“333.
Hansen, L.P., and R.J. Hodrick (1980) Forward exchange rates as optimal predictors
of future spot rates: An econometric analysis, Journal of Political Economy, 88,
Hansen, P.R., and A. Lunde (2004a) A forecast comparison of volatility models: Does
anything beat a GARCH(1,1), Journal of Applied Econometrics, Forthcoming.
Hansen, P.R., and A. Lunde (2004b) Consistent ranking of volatility models, Journal of
Econometrics, Forthcoming.
208 References

Harvey, A.C. (1998) Long memory in stochastic volatility, Chapter 12, pp. 307“320,
in: Knight, J., and S. Satchell (eds), Forecasting Volatility in the Financial Markets,
Butterworth, Oxford.
Harvey, A.C., E. Ruiz and N. Shephard (1994) Multivariate stochastic variance models,
Review of Economic Studies, 61, 247“264.
Harvey, C.R., and R.E. Whaley (1992) Market volatility prediction and the ef¬-
ciency of the S&P100 Index option market, Journal of Financial Economics, 31, 1,
Heath, D., R. Jarrow, and A. Morton (1992) Bond pricing and the term structure of
interest rates: A new methodology for contingent claim valuation, Econometrica,
60, 77“105.
Hentschel, L. (2001) Errors in implied volatility estimation, working paper, University
of Rochester.
Heston, S.L (1993) A closed solution for options with stochastic volatility, with ap-
plication to bond and currency options, Review of Financial Studies, 6, 2, 327“
Heynen, R.C. (1995) Essays on Derivatives Pricing Theory, Thesis Publishers, Amster-
Heynen, R.C., and H.M. Kat (1994) Volatility prediction: A comparison of stochastic
volatility, GARCH(1,1) and EGARCH(1,1) models, Journal of Derivatives, 2, 50“
Hol, E., and S.J. Koopman (2002) Forecasting the variability of stock index returns with
stochastic volatility models and implied volatility, Working paper, Free University,
Hong, Y. (2001) A test for volatility spillover with application to exchange rates, Journal
of Econometrics, 103, 183“224.
Hosking, J.R.M. (1981) Fractional differencing, Biometrika, 68, 165“176.
Hsieh, D.A. (1989) Modeling heteroscedasticity in daily foreign exchange rates, Journal
of Business and Economic Statistics, 7, 3, 307“317.
Huber, P.J. (1981) Robust Statistics, John Wiley and Sons Canada Ltd, Ontario.
Hull, J. (2002) Options, Futures and Other Derivative Securities, 5th edn, Prentice Hall,
Englewood Cliffs, NJ.
Hull, J., and A. White (1987) The pricing of options on assets with stochastic volatilities,
Journal of Finance, 42, 2, 281“300.
Hull, J., and A. White (1988) An analysis of the bias in option pricing caused by a
stochastic volatility, Advances in Futures and Options Research, 3, 27“61.
Hwang, S., and S. Satchell (1998) Implied volatility forecasting: A comparison of dif-
ferent procedures including fractionally integrated models with applications to UK
equity options, Chapter 7, pp. 193“225, in: Knight, J., and S. Satchell (eds), Fore-
casting Volatility in the Financial Markets, Butterworth, Oxford.
Jacquier, E., N.G. Polson and P.E. Rossi (1994) Bayesian analysis of stochastic
volatility models: reply, Journal of Business and Economic Statistics, 12, 4, 413“
Jarrow, R. (ed) (1998) Volatility: New Estimation Techniques for Pricing Derivatives,
Risk Books, London.
Johnson, H., and D. Shanno (1987) Option pricing when the variance is changing,
Journal of Financial and Quantitative Analysis, 22, 143“151.
Jones, C.S. (2001) The dynamics of stochastic volatility: Evidence from underlying
and options markets, Working paper, Simon School of Business, University of
References 209

Jones, C., O. Lamont and R. Lumsdaine (1998) Macroeconomic news and bond market
volatility, Journal of Financial Economics, 47, 315“337.
Jorion, P. (1995) Predicting volatility in the foreign exchange market, Journal of Finance,
50, 2, 507“528.
Jorion, P. (1996) Risk and turnover in the foreign exchange market, in: Frankel, J.A.,
G. Galli and A. Giovannini (eds), The Microstructure of Foreign Exchange Markets,
The University of Chicago Press, Chicago.
Jorion, P. (2001) Value at Risk: The New Benchmark for Managing Financial Risk, 2nd
edn, McGraw-Hill, New York.
Karatzas, I., and S.E. Shreve (1988) Brownian Motion and Stochastic Calculus, Springer
Verlag, New York.
Karolyi, G.A. (1993) A Bayesian approach to modeling stock return volatility and option
valuation, Journal of Financial and Quantitative Analysis, 28, 4, 579“595.
Karolyi, G.A. (1995) A multivariate GARCH model of international transimissions of
stock returns and volatility: The case of the United States and Canada, Journal of
Business and Economic Statistics, 13, 1, 11“25.
Karpoff, J.M. (1987) The relation between price changes and trading volume: A survey,
Journal of Financial and Quantitative Analysis, 22, 1, 109“126.
Kearns, P., and A.R. Pagan (1993) Australian stock market volatility, 1875“1987, Eco-
nomic Record, 69, 163“178.
Kim, S., N. Shephard and S. Chib (1998) Stochastic volatility: likelihood inference and
comparison with ARCH models, Review of Economic Studies, 65, 361“393.
King, M.A., and S. Wadhwani (1990) Transmission of volatility between stock markets,
Review of Financial Studies, 3, 1, 5“33.
Klaassen, F. (1998) Improving GARCH volatility forecasts, Empirical Economics, 27,
Knight, J., and S. Satchell (ed) (2002) Forecasting Volatility in the Financial Markets,
2nd edn, Butterworth, Oxford.
Koutmos, G., and G.G. Booth (1995) Asymmetric volatility transmission in international
stock markets, Journal of International Money and Finance, 14, 6, 747“762.
Kroner, K., Kneafsey K. and S. Claessens (1995) Forecasting volatility in commodity
markets, Journal of Forecasting, 14, 77“95.
Kroner, K.F., and V.K. Ng (1998) Modeling asymmetric co-movements of asset returns,
Review of Financial Studies, 11, 4, 817“844.
Lamoureux, C.G., and W.D. Lastrapes (1990) Persistence in variance, structural change
and the GARCH model, Journal of Business and Economic Statistics, 8, 2, 225“
Lamoureux, C., and W. Lastrapes (1993) Forecasting stock-return variance: toward an
understanding of stochastic implied volatilities, Review of Financial Studies, 6, 2,
Latane, H., and R.J. Rendleman (1976) Standard deviations of stock price ratios implied
in option prices, Journal of Finance, 31, 2, 369“381.
Lee, K.Y. (1991) Are the GARCH models best in out-of-sample performance? Eco-
nomics Letters, 37, 3, 305“308.
Li, K. (2002) Long-memory versus option-implied volatility prediction, Journal of
Derivatives, 9, 3, 9“25.
Liesenfeld, R., and J.-F. Richard (2003) Univariate and multivariate stochastic volatility
models: estimation and diagnostics, Journal of Empirical Finance, 10, 4, 505“531.
Lin, Y., N. Strong and X. Xu (2001) Pricing FTSE-100 index options under stochastic
volatility, Journal of Futures Markets, 21, 3, 197“211.
210 References

Lopez, J.A. (1998) Methods for evaluating value-at-risk estimates, Economic Policy
Review (Federal Reserve Bank of New York), 4, 3, 119“129.
Lopez, J.A. (2001) Evaluating the predictive accuracy of volatility models, Journal of
Forecasting, 20, 2, 87“109.
Loudon, G.F., W.H. Watt and P.K. Yadav (2000) An empirical analysis of alternative
parametric ARCH models, Journal of Applied Econometrics, 15, 117“136.
Martens, M., and S.-H. Poon (2001) Returns synchronization and daily correlation dy-
namics between international stock markets, Journal of Banking and Finance, 25,
10, 1805“1827.
Martens, M., and J. Zein (2004) Predicting ¬nancial volatility: High-frequency time-
series forecasts vis-` -vis implied volatility, Journal of Futures Markets, 24, 11, 1005“
Mayhew, S. (1995) Implied volatility, Financial Analyst Journal, 51, 8“20.
McCurdy, T.H., and I. Morgan (1987) Tests of the martingale hypothesis for foreign
currency futures with time varying volatility, International Journal of Forecasting,
3, 131“148.
McKenzie M.D. (1999) Power transformation and forecasting the magnitude of exchange
rate changes, International Journal of Forecasting, 15, 49“55.
McMillan, D.G., A.H. Speight and O.A.P. Gwilym (2000) Forecasting UK stock market
volatility, Journal of Applied Economics, 10, 435“448.
McNeil, A.J., and R. Frey (2000) Estimation of tailed-related risk measures for het-
eroscedastic ¬nancial time series: An extreme value approach, Journal of Empirical
Finance, 7, 271“300.
Merton, R.C. (1980) On estimating expected return on the market: An exploratory
investigation, Journal of Financial Economics, 8, 323“361.
Milhoj, A. (1987) A conditional variance model for daily observations of an exchange
rate, Journal of Business and Economic Statistics, 5, 99“103.
Nandi, S. (1998) How important is the correlation between returns and volatility in a
stochastic volatility model? Empirical evidence from pricing and hedging S&P500
index option market, Journal of Banking and Finance, 22, 5, 589“610.
Nelson, D.B. (1991) Conditional heteroskedasticity in asset returns: A new approach,
Econometrica, 59, 2, 347“370.
Nelson, D.B. (1992) Filtering and forecasting with misspeci¬ed ARCH models I: Getting
the right variance with the wrong model, Journal of Econometrics, 52, 61“90.
Nelson, D.B., and C.Q. Cao (1992) Inequality constraints in the univariate GARCH
model, Journal of Business and Economic Statistics, 10, 2, 229“235.
Nelson, D.B., and D.P. Foster (1995) Filtering and forecasting with misspeci¬ed ARCH
models II: Making the right forecast with the wrong model, Journal of Econometrics,
67, 2, 303“335.
Noh, J. R.F., Engle and A. Kane (1994) Forecasting volatility and option prices of the
S&P 500 index, Journal of Derivatives, 2, 17“30.
Ohanissian, A., J.R. Russell and R.S. Tsay (2003) True or spurious long memory in
volatility: Does it matter for pricing options? Working Paper, University of Chicago.
Pagan, A.R., and G.W. Schwert (1990) Alternative models for conditional models for
conditional stock volatility, Journal of Econometrics, 45, 1“2, 267“290.
Parkinson, M. (1980) The extreme value method for estimating the variance of the rate
of return, Journal of Business, 53, 61“65.
Pitt, M.J., and N. Shephard (1997) Likelihood analysis of non-Gaussian measurement
time series, Biometrika, 84, 653“667.
Peria, M.S.M. (2001) A regime-switching approach to the study of speculative attacks:
A focus on EMS crises. Working paper, World Bank.
References 211

Pong, S., M.B. Shackleton, S.J. Taylor and X. Xu (2004) Forecasting Sterling/Dollar
volatility: A comparison of implied volatilities and AR(FI)MA models, Journal of
Banking and Finance, 28, 2541“2563.
Poon, S.-H., and C.W.J. Granger (2003) Forecasting ¬nancial market volatility: A review,
Journal of Economic Literature, 41, 2, 478“539.
Poon, S.-H., and C.W.J. Granger (2005) Practical issues in forecasting volatility, Finan-
cial Analyst Journal, 61, 1, 45“65.
Poon, S.-H., M. Rockinger and J. Tawn (2003) Extreme value dependence in international
stock markets and ¬nancial applications, Statistica Sinica, 13, 929“953.
Poon, S.-H., M. Rockinger and J. Tawn (2004) Extreme-value dependence in ¬nancial
markets: Diagnostics, models and ¬nancial implications, Review of Financial Studies,
17, 2, 581“610.
Poon, S., and S.J. Taylor (1992) Stock returns and stock market volatilities, Journal of
Banking and Finance, 16, 37“59.
Poteshman, A.M. (2000) Forecasting future volatility from option prices, Working paper,
University of Illinois at Urbana-Champaign.
Randolph, W.L., and M. Najand (1991) A test of two models in forecasting stock index
futures price volatility, Journal of Futures Markets, 11, 2, 179“190.
Robinson, P.M. (ed.) (2003) Time Series with Long Memory. Oxford University Press,
Rogers, L.C.G., and S.E. Satchell (1991) Estimating variance from high, low and closing
prices, Annals of Applied Probability, 1, 504“512.
Rogers, L.C.G., S.E. Satchell and Y. Yoon (1994) Estimating the volatility of stock
prices: A comparison of methods that use high and low prices, Applied Financial
Economics, 4, 3, 241“248.
Roll, R. (1977) An analytic valuation formula for unprotected American call options on
stocks with known dividends, Journal of Financial Economics, 5, 251“258.
Rossi, P. (ed.) (1996) Modelling Stock Market Volatility: Bridging the Gap to Continuous
Time, Academic Press, London.
Schmalensee, R., and R.R. Trippi (1978) Common stock volatility expectations implied
by option premia, Journal of Finance, 33, 1, 129“147.
Scott, E., and A.L. Tucker (1989) Predicting currency return volatility, Journal of Bank-
ing and Finance, 13, 6, 839“851.
Scott, L.O. (1987) Option pricing when the variance changes randomly: Theory, es-
timation and an application, Journal of Financial and Quantitative Analysis, 22,
Sentana, E. (1998) The relation between conditionally heteroskedastic factor models


. 6
( 7)