• Tidak ada hasil yang ditemukan

M01439

N/A
N/A
Protected

Academic year: 2017

Membagikan " M01439"

Copied!
14
0
0

Teks penuh

(1)

A Comparison of MCMC Samplers for

Estimating Leveraged Stochastic Volatility

Model

Didit B. Nugroho1,2 and Takayuki Morimoto1

1Department of Mathematical Sciences, Kwansei Gakuin University, Japan 2Department of Mathematics, Satya Wacana Christian University, Indonesia

December 23, 2013, Hiroshima University of Economics

Abstract

(2)

1. Introduction: SV and MCMC methods

Stochastic volatility (SV) model is among the most important tools for modeling volatility of a financial time series.

A problem in parametric SV models is that it is not possible to obtain an explicit expression for the likelihood function of some unknown parameters.

An approach has become very attractive is Markov Chain Monte Carlo (MCMC) method proposed by Shephard (1993) and Jacquier et al (1994).

Omori and Watanabe (2008)proposed an efficient multi-move (block) Metropolis-Hastings sampler for sampling high-dimensional latent volatil-ity in the leveraged SV model.

(3)

2. Survey on MCMC Comparison

Kim et al. (1998) andJacquier-Polson (2011)compared the perfor-mance of the single-move and multi-move MH (MM-MH) samplers to estimate basic SV model. The MM-MH sampler has been proposed to reduce sample autocorrelations effectively. Jacquier-Polson par-ticularly note that the single-move and multi-move samplers deliver almost the same output.

Takaishi (2009) compared the performance of the single-move MH and HMC samplers and concluded that HMC sampler is superior to the single-move sampler.

(4)

3. Our Purpose

First purpose of this study is to extend the HMC and RMHMC sam-pling procedures proposed byGirolami and Calderhead (2011)for the leveraged SV model.

(5)

4. HMC and RMHMC Samplers

HMC-based methods are based on Hamiltonian dynamics system:

H(θ,ω) =−L(θ) +1

2log

n

(2π)D|M|o+12ω′M−1ω,

where L(θ) is the logarithm of the joint probability distribution for

the parameters θRD,Mis the covariance matrix, andωRDis

the independent auxiliary variable.

In the RMHMC sampling,Mdepends on the variableθand is chosen

to be the metric tensor, i.e.

(6)

4. HMC and RMHMC Samplers (Cont’ed)

The full algorithm for HMC or RMHMC can then be summarized in the following three steps.

(1) Randomly draw a sample momentum vector ω∼ N(ω|0,M). (2) Run the leapfrog algorithm for NL steps with step sizeτ to

generate a proposal (θ,ω)according to the Hamiltonian equations

dθ

dτ = H ∂ω and

dω

dτ =− H

θ.

over a fictitious time τ.

(3) Accept (θ,ω)with probability

(7)

5. Leveraged SV Model

Omori and Watanabe (2008) proposed a leveraged SV model with normal errors (LSV-N model, hereafter) formulated as

Rt = σre

using MH algorithm separately and the latent volatilityhtusing

(8)

6. Comparison on Real Data

(9)

6. Comparison on Real Data (Cont’ed)

Tabel: Tuning parameters for the HMC and RMHMC implementations.

Parameter of model Sampler Parameter of

sampler h φ (σr,σh,ρ)

HMC NL 100 100 100

τ 0.01 0.0125 0.0125

RMHMC

NL 50 6 6

τ 0.1 0.5 0.5

NFPI - 5 5

(10)

6. Comparison on Real Data (Cont’ed)

Tabel: Posterior summary statistics.

Parameter Mean (SD) 95%Interval IACT Time (sec) Panel A: Using MM-MH sampler

σr 1.259(0.070) [1.121, 1.398] 20.8

φ 0.945(0.019) [0.902, 0.974] 118.2

σh 0.193(0.033) [0.138, 0.267] 206.7

ρ −0.442(0.103) [−0.630,−0.231] 92.7 Panel B: Using HMC sampler

σr 1.241(0.070) [1.098, 1.377] 53.0

465.88

φ 0.954(0.014) [0.925, 0.980] 132.7

σh 0.169(0.025) [0.120, 0.219] 279.9

ρ −0.461(0.097) [−0.648,−0.272] 83.9 Panel C: Using RMHMC sampler

σr 1.238(0.070) [1.098, 1.378] 19.4

(11)

6. Comparison on Real Data (Cont’ed)

Tabel: Acceptance rates.

Acceptance rates Parameter

MM-MH HMC RMHMC

h 0.856 0.889 0.975

φ 0.955 0.910 0.901

(12)

7. Conclusion

Based on the empirical results, we conclude:

The RMHMC sampler give the best performance in terms of autocor-relation time.

In particular, the HMC sampler exhibits slightly slower convergence than MM-HMC sampler except for the leverage parameter.

(13)

Some References

Girolami, M. and Calderhead, B.(2011). Riemann manifold Langevin and

Hamiltonian Monte Carlo methods.Journal of the Royal Statistical Society, Series B,73(2), 1–37.

Jacquier, E. and Polson, N. G. (2011). Bayesian methods in finance. In J.

Geweke, G. Koop, and H. van Dijk (Eds.),Handbook of Bayesian Econometrics. Oxford University Press.

Kim, S. and Shephard, N. and Chib, S.(1998). Stochastic volatility: likelihood

inference and comparison with ARCH models. In N. Shephard (Ed.),Stochastic Volatility: Selected Readings. Oxford University Press.

Omori, Y. and Watanabe, T.(2008). Block sampler and posterior mode

esti-mation for asymmetric stochastic volatility models.Computational Statistics and Data Analysis,52, 2892–2910.

(14)

Referensi

Garis besar

Dokumen terkait

[r]

PEMERMTAH KABUMTEN TAFMUU TENGAH UNIT UYANAN PENGADAAN BARANG DAN

Sahabat MQ/ insiden yang terjadi pada saat dengar pendapat/ antara Komisi 3 DPR RI dengan sejumlah elemen masyarakat/ baru-baru ini/ dianggap sebagai pembajakan demokrasi//

Setelah semua program perkuliahan ini selesai, mahasiswa diharapkan memiliki pengetahuan dan keterampilan di dalam merencanakan dan melaksanakan evaluasi pendidikan

PENGARUH KOMPETENSASI TERHADAP KINERJA GURU TIDAK TETAP DI SMK WISATA LEMBANG Universitas Pendidikan Indonesia | repository.upi.edu | perpustakaan.upi.edu!.

Sehubungan dengan pelelangan paket tersebut diatas dan berdasarkan hasil evaluasi Pokja Pekerjaan Konstruksi terhadap penawaran perusahaan Saudara, diharapkan kehadirannya pada

Perhatikan bahwa huruf lam ( ' i atas adalah huruf jarr yang berarti ‘milik’ at dalam posisi majrur namun dia tidak berha tersebut adalah tetap dan tidak mengalam

Perilaku-perilaku pemilih ini dipengaruhi oleh pendekatan – pendekatan rasional, psikologis dan sosiologis yang akan dijabarkan dalam hasil kuesioner yang diberikan kepada