ARE VOLATILITY EXPECTATIONS CHARACTERIZED BY REGIME SHIFTS? EVIDENCE FROM IMPLIED VOLATILITY INDICES



Table 2. Regime-switching modelling of implied volatility
_____________________
(S&P 500 index)____________________

Model 1    Model 2 Model 3 Model 4

w1
w 2
δι
δ2
βι
β2

Y1

γ 2
Ψ1

Ψ2

W1 = w 2
δι = δ2
βι = β2
Yi = γ 2
Φ1 = V2
P11 = P 22

LL

Model parameters                      

0.2664a     -0.0129a    0.2581a     0.0033a

01612a      0.0093a    0.1561a     0.0035a

1.1093a                 0.9810a

0.9393a                 0.9796a

-0.5693a     -0.2328a    -0.6094a     -0.6226a

-0.3991a     0.0632a    -0.5627a    -1.4508a

40.4928a     7.0033a

90.7546a     9.9678a

Hypothesis tests                         

6074.104a   122.558a   5423.406a    0.0377

585.366a                0.0798

1.588      45.094a     0.118     1184.4911a

50.754a     12.8244a

2.022      50.034a     2.626     71.5032a

7166.36    11997.22   7369.75    13491.68

Notes: Significance at the 1, 5 and 10 % level is denoted by a, b and
c respectively. The estimated Markov regime-switching models
are represented by
vt = wi +βirt-1 +ζt for Model 1,
vt = wi + δivt-1 + βirt-1 +ζt        for        Model        2,

vt = wi + βirt-1 + γi rt2-1 +ζt     for Model      3,      and

vt = wi +δivt-1 + βirt-1 + γi rt2-1 +ζt for Model 4. The null

hypothesis tests are distributed asχ2(1) . LL is the log maximum

likelihood function.

22



More intriguing information

1. Transport system as an element of sustainable economic growth in the tourist region
2. A Rational Analysis of Alternating Search and Reflection Strategies in Problem Solving
3. The name is absent
4. The name is absent
5. DEMAND FOR MEAT AND FISH PRODUCTS IN KOREA
6. Une Classe de Concepts
7. The Role of Evidence in Establishing Trust in Repositories
8. Globalization, Divergence and Stagnation
9. Testing the Information Matrix Equality with Robust Estimators
10. The name is absent