persistency of the GARCH model specified above? Comment on the
persistency.
- A Describe And Interpret The Estimation Results What Is The Persistency Of The Garch Model Specified Above Comment On 1 (91.82 KiB) Viewed 67 times
a) Describe and interpret the estimation results. What is the persistency of the GARCH model specified above? Comment on
-
answerhappygod
- Site Admin
- Posts: 899603
- Joined: Mon Aug 02, 2021 8:13 am
a) Describe and interpret the estimation results. What is the persistency of the GARCH model specified above? Comment on
a) Describe and interpret the estimation results. What is the
persistency of the GARCH model specified above? Comment on the
persistency.
Background. Adam is a quantitative risk analyst working for Sigma Value Investments. He is building a model of volatility using daily excess returns of the S&P 500 index from 1990 to 2016. Adam has specified the following GARCH-in-mean(1,1) model: Mean equation R¢ = y + Mo + € Variance equation: oft1 = w + aet + Bot where Rt is the excess returns of S&P 500 index, & is the residual term from the mean equation, and of is the GARCH term. He has obtained the following estimation results: Dependent Variable: ER Method: ML ARCH - Normal distribution (BFGS / Marquardt Convergence achieved after 30 iterations Coefficient covariance computed using Bollerslev- sandwich with expected Hessian Presample variance: backcast (parameter = 0.7) GARCH = C(3) + C14)*RESID(-1)^2 + C(5)*GARCH(-1) Variable Coefficient Std. Error Prob. @SORT(GARCH) 0.089295 0.040052 2.229464 0.0258 ce -0.000292 0.000331 -0.881544 0.37802 Variance Equation се 1.17E-06 2.70E-07 4.353596 0.0000 RESID(-1)^2 0.079690 0.008935 8.919183 0.0000 GARCH(-1) 0.910699 0.008437 107.9381 0.0000 R-sauared -0.003023 Mean dependent 0.000149– Adiusted R- -0.003183 S.D. dependent 0.011424 S.E. of regression 0.011442 Akaike info Sum squared 0.824045 Schwarz criterion Log likelihood 20541.59 Hannan-Ouinn Durbin-Watson 2.102602 Z- ܒܟ
persistency of the GARCH model specified above? Comment on the
persistency.
Background. Adam is a quantitative risk analyst working for Sigma Value Investments. He is building a model of volatility using daily excess returns of the S&P 500 index from 1990 to 2016. Adam has specified the following GARCH-in-mean(1,1) model: Mean equation R¢ = y + Mo + € Variance equation: oft1 = w + aet + Bot where Rt is the excess returns of S&P 500 index, & is the residual term from the mean equation, and of is the GARCH term. He has obtained the following estimation results: Dependent Variable: ER Method: ML ARCH - Normal distribution (BFGS / Marquardt Convergence achieved after 30 iterations Coefficient covariance computed using Bollerslev- sandwich with expected Hessian Presample variance: backcast (parameter = 0.7) GARCH = C(3) + C14)*RESID(-1)^2 + C(5)*GARCH(-1) Variable Coefficient Std. Error Prob. @SORT(GARCH) 0.089295 0.040052 2.229464 0.0258 ce -0.000292 0.000331 -0.881544 0.37802 Variance Equation се 1.17E-06 2.70E-07 4.353596 0.0000 RESID(-1)^2 0.079690 0.008935 8.919183 0.0000 GARCH(-1) 0.910699 0.008437 107.9381 0.0000 R-sauared -0.003023 Mean dependent 0.000149– Adiusted R- -0.003183 S.D. dependent 0.011424 S.E. of regression 0.011442 Akaike info Sum squared 0.824045 Schwarz criterion Log likelihood 20541.59 Hannan-Ouinn Durbin-Watson 2.102602 Z- ܒܟ