• Like
Does Idiosyncratic Volatility Matter?
Upcoming SlideShare
Loading in...5
×
Uploaded on

NES 20th Anniversary Conference, Dec 13-16, 2012 …

NES 20th Anniversary Conference, Dec 13-16, 2012
Does Idiosyncratic Volatility Matter? (based on the article presented by Serguey Khovansky at the NES 20th Anniversary Conference). Authors: Serguey Khovansky; Oleksandr Zhylyevskyy

  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Be the first to comment
    Be the first to like this
No Downloads

Views

Total Views
1,458
On Slideshare
0
From Embeds
0
Number of Embeds
0

Actions

Shares
Downloads
2
Comments
0
Likes
0

Embeds 0

No embeds

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
    No notes for slide

Transcript

  • 1. Does Idiosyncratic Volatility Matter? Serguey Khovansky† Oleksandr Zhylyevskyy∗ † Clark University ∗ Iowa State University 2012 New Economic School Moscow
  • 2. Research ObjectivesObtain current (up-to-date) parameters of a financial market modelDevelop a method to consistently estimate parameters of afinancial market model using a single cross-section of return dataEstimate Parameters of Idiosyncratic Risk
  • 3. Plan of the TalkMarket ModelLiterature Review Procedure: GMM CSEstimation Results
  • 4. Market Model Risk-free interest rate r > 0 Market index Mt follows geometric Brownian motion dMt Mt = µm dt + σm dWt µm = r + δσm δ - market risk premium σm > 0 -market volatility Wt - Brownian motion (systematic risk)
  • 5. Market Model Stocks Sti with i=1,2,3... and t = 0, T affected by systematic Wt and idiosyncratic Zti risks Stocks observed only at two time moments t=0 and t=T dSti Sti = µi dt + βi σm dWt + σi dZti µi = r + δβi σm + γσi Wt - Brownian motions (source of systematic risk) -Common Shock Zti - Brownian motions (idiosyncratic risk) γ - idiosyncratic risk premium σi - idiosyncratic volatility of stock i, σi ∼ i.i.d.UNI[0, λσ ] βi - beta of a stock i, βi ∼ i.i.d.UNI[κβ , κβ + λβ ]
  • 6. Estimation difficulties i ST Dependence in the stock returns i S0 caused by systematic risk W -Common Shocks Standard Law of Large Numbers and Central Limit Theorem not applicable. Hint to resolve the issue: 1 2 3 ST ST ST The random variables represented by stock returns 1, 2, 3 ... S0 S0 S0 MT are conditionally i.i.d. given the market index return M0
  • 7. Relevant Literature Andrews (2005) ’Cross-Section Regression with Common Shocks’, Econometrica Examines properties of OLS estimation of models with common shocks Fu (2009) ’Idiosyncratic risk and the cross-section of expected stock returns’, Journal of Financial Economics Estimates positive idiosyncratic premium Ang et al.(2006) ’The cross-section of volatility and expected returns’, Journal of Finance Estimates negative idiosyncratic premium
  • 8. Estimation To carry out GMM CS estimation construct a function gi (ξ, θ) i ST ξ i ST ξ gi (ξ, θ) = i S0 − Eθ i S0 | MT M0 GMM objective function 1 i=n −1 1 i=n Qn (θ) = n i=1 gi (θ) n i=1 gi (θ) GMM estimator θn = argminθ Qn (θ) Qn (θ) converges to stochastic function dependent on systematic risk
  • 9. Properties of the EstimatesTheorem (Consistency) The estimator θn −→ θ0 as n −→ ∞ Consistency as n −→ ∞ means that quality of estimates improves as the number of stocks grows Consistency of Fama-MacBeth method requires that T −→ ∞ means that quality of estimates improves as history of dataset grows
  • 10. Properties of the EstimatesTheorem (Asymptotic Mixed Normality) √ n θ n − θ 0 →d MN 0, V MT , M0where V MT is asymptotic conditional covariance. M0 MN - mixed normal distribution Mixed normality is caused by systematic risk
  • 11. Monte Carlo Analysisσm > 0 -market volatilityγ - idiosyncratic risk premiumσi - idiosyncratic volatility of stock i, σi ∼ i.i.d.UNI[0, λσ ]βi - beta of a stock i, βi ∼ i.i.d.UNI[κβ , κβ + λβ ] Means of estimates Sample size n (in thousands) 25 50 250 1, 000 10, 000 True value σm 0.2526 0.2382 0.2205 0.2116 0.2011 0.2000 γ 0.5560 0.5339 0.5161 0.5076 0.5020 0.5000 κβ −0.1316 −0.1484 −0.1476 −0.1817 −0.1978 −0.2000 λβ 3.6166 3.5798 3.4874 3.4722 3.4303 3.4000 λσ 0.4989 0.4996 0.4998 0.4999 0.5000 0.5000
  • 12. Empirical Estimation: Data CRSP database January 2008 October 2008 Stock returns are computed using weekly data The market index is approximated by the S&P 500 index Risk free rate is derived from 4-week T-bill
  • 13. Empirical Estimation: Illustrationσm > 0 -market volatilityγ - idiosyncratic risk premiumσi - idiosyncratic volatility of stock i, σi ∼ i.i.d.UNI[0, λσ ]βi - beta of a stock i, βi ∼ i.i.d.UNI[κβ , κβ + λβ ] Moment order vector ξ = (−2, −1.5, −1, −0.5, 0.5, 1, 1.5, 2) January 22-29, 2008 October 23-30, 2008 Parameter Estimate P-value Estimate P-value σm 0.0537 0.00 0.0672 0.00 γ −2.1117 0.34 −1.2936 0.56 κβ 0.3417 0.74 −0.3058 0.74 λβ 3.0475 0.00 2.8367 0.00 λσ 1.0580 0.00 1.7478 0.00
  • 14. Empirical Estimation: Idiosyncratic Volatility, Jan. 2008 Idiosyncratic volatility Average idiosyncratic Return interval premium, γ volatility, λσ /2 Estimate P-value Estimate P-value January 02-09 −4.7251 0.00 0.5609 0.02 03-10 −5.0907 0.00 0.5370 0.00 04-11 −8.0336 0.00 0.4747 0.00 08-15 −4.4627 0.00 0.5106 0.00 09-16 −9.1830 0.00 0.4816 0.00 10-17 −6.2418 0.00 0.5357 0.00 11-18 −9.2725 0.00 0.5077 0.00 Mean −6.0666 0.5452 Std. dev. 3.6396 0.0519
  • 15. Empirical Estimation: Idiosyncratic Volatility, Oct. 2008 Idiosyncratic volatility Average idiosyncratic Return interval premium, γ volatility, λσ /2 Estimate P-value Estimate P-value October 01-08 −8.5104 0.00 0.8095 0.00 02-09 −8.4123 0.00 0.8858 0.00 03-10 −8.4921 0.00 0.8999 0.00 06-13 −7.8321 0.00 0.7532 0.00 07-14 −5.9003 0.00 0.7949 0.00 08-15 −0.8830 0.00 0.8595 0.01 Mean −5.5748 0.8372 Std. dev. 3.9705 0.0725
  • 16. Expected Return Decomposition i ST MT E i | S0 M0 ≡ E = exp (rT ) · S( MT ) · I M0 exp (rT )- the risk-free component S( MT )−the market risk component M0 I -the idiosyncratic volatility component
  • 17. Expected Return Decomposition: January 2008 E-erT S erT (S-I) Interval E S I E E Jan.03-10 0.9647 1.0173 0.9477 -0.0552 0.0722 04-11 0.9762 1.0512 0.9280 -0.0776 0.1263 07-14 0.9870 0.9955 0.9909 -0.0092 0.0047 08-15 0.9833 1.0277 0.9561 -0.0459 0.0729 09-16 0.9857 1.0741 0.9172 -0.0903 0.1593 10-17 0.9535 1.0175 0.9365 -0.0678 0.0850 Mean 0.9890 1.0488 0.9430 -0.0615 0.1071 Std.dev. 0.0311 0.0337 0.0311 0.0346 0.0571
  • 18. Expected Return Decomposition: October 2008 E-erT S erT (S-I) Interval E S I E E Oct.01-08 0.8211 0.9384 0.8750 -0.1429 0.0773 02-09 0.8022 0.9267 0.8657 -0.1551 0.0760 03-10 0.8163 0.9463 0.8626 -0.1593 0.1026 06-13 0.9455 1.0605 0.8916 -0.1216 0.1787 07-14 0.9852 1.0797 0.9125 -0.0959 0.1698 08-15 0.9352 0.9494 0.9851 -0.0151 -0.0382 Mean 0.9438 1.0270 0.9184 -0.0929 0.1162 Std.dev. 0.0834 0.0564 0.0574 0.0654 0.0778
  • 19. Contribution Develop a novel econometric framework to estimate a financial model featuring a common shock Estimate instantaneous parameters of a financial market model using only a cross-section of returns Find that idiosyncratic volatility premium was negative in January and October 2008 Find that average idiosyncratic volatility increased in October 2008 by at least 50 % relative to January 2008