• Like
Widespread Worry and the Stock Market
Upcoming SlideShare
Loading in...5
×

Thanks for flagging this SlideShare!

Oops! An error has occurred.

Widespread Worry and the Stock Market

  • 397 views
Published

 

Published in Technology
  • 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
397
On SlideShare
0
From Embeds
0
Number of Embeds
0

Actions

Shares
Downloads
1
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. WIDESPREAD WORRY AND THE STOCK MARKET Eric Gilbert & Karrie Karahalios University of Illinois
  • 2. LAB EXPERIMENTS in psych & behavioral econ emotions affect our choices DOLAN, SCIENCE 2002 ZAJONC, AM. PSYCHOLOGIST 1980 fear affects our investment choices LERNER, J. P&SP 2001 LOEWENSTEIN, PSYCH. BULLETIN 2002
  • 3. If we estimate broad WORRY & FEAR, does it tell us anything about the MARKET?
  • 4. NATURAL EXPERIMENTS nance & computer science stock market is probably not ef cient TETLOCK, J. FINANCE 2007 HIRSHLEIFER & SHUMWAY, J. FINANCE 2003 online media have predictive information CHOI & VARIAN, GOOGLE 2009 GRUHL ET AL, KDD 2005
  • 5. 2008
  • 6. 2008 LiveJournal Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 7. THE ANXIETY INDEX training data 624,905 LJ mood-annotated posts from 2004 extracted 12,923 anxious, worried, nervous, fearful & trained two classi ers to discriminate
  • 8. THE ANXIETY INDEX classi ers C1: boosted decision tree with top 100 stems 28% TRUE POSITIVE; 3% FALSE POSITIVE C2: bagged complement naive bayes 32% TRUE POSITIVE; 6% FALSE POSITIVE (RENNIE, 2003 ICML)
  • 9. THE ANXIETY INDEX frequency & differencing Ct = max(C1t, C2t) At = log(Ct+1) – log(Ct) TIME MEASURED IN TRADING DAYS
  • 10. MARKET DATA returns Let SPt be S&P 500 closing price Rt = log(SPt+1) – log(SPt) Mt = Rt+1 – Rt
  • 11. MARKET DATA controls VLMt = log(VOLUMEt+1) – log(VOLUMEt) VOLt = Rt+1 · Rt+1 – Rt ·Rt
  • 12. S&P 500 1400 S&P moving avg Anxiety index 1300 1200 1100 1000 900 4σ 800 3σ 2σ 1σ 0σ -1σ Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
  • 13. METHOD granger causality ￿3 ￿3 Mt = α + i=1 βi Mt−i + i=1 γi V OLt−i ￿3 + i=1 δi V LMt−i + ￿t ￿3 ￿3 Mt = α + i=1 βi Mt−i + i=1 γi V OLt−i ￿3 ￿3 + i=1 δi V LMt−i + i=1 λi At−i + ￿t
  • 14. METHOD granger causality ￿3 ￿3 Mt = α + i=1 βi Mt−i + i=1 γi V OLt−i ￿3 + i=1 δi V LMt−i + ￿t ￿3 ￿3 Mt = α + i=1 βi Mt−i + i=1 γi V OLt−i ￿3 ￿3 + i=1 δi V LMt−i + i=1 λi At−i + ￿t
  • 15. ENDOGENOUS MODEL Mt Coe . Std. Err. t p -1 day -0.858 0.110 -7.83 <0.001† -2 days -0.655 0.095 -6.88 <0.001† -3 days -0.171 0.098 -1.73 0.085 VOLt -1 day 0.149 0.076 1.96 0.051 -2 days 0.152 0.087 1.74 0.084 -3 days 0.176 0.117 1.51 0.132 VLMt -1 day 0.054 0.080 0.68 0.497 -2 days 0.132 0.074 1.78 0.077 -3 days 0.067 0.058 1.16 0.247 Summary DW Adj. R2 F9,161 p 2.054 0.509 20.58 <0.001†
  • 16. + FEAR MODEL Mt Coe . Std. Err. t p -1 day -0.872 0.105 -8.36 <0.001† -2 days -0.667 0.085 -7.81 <0.001† -3 days -0.182 0.087 -2.08 0.039† VOLt -1 day 0.182 0.063 2.90 0.004† -2 days 0.184 0.083 2.22 0.028† -3 days 0.177 0.109 1.63 0.105 VLMt -1 day 0.056 0.078 0.712 0.477 -2 days 0.133 0.071 1.89 0.061 -3 days 0.071 0.059 1.20 0.232 At -1 day -0.064 0.052 -1.24 0.216 -2 days -0.128 0.060 -2.14 0.034† -3 days -0.136 0.084 -1.62 0.107
  • 17. 0.184 0.083 2.22 0.028† -3 days 0.177 0.109 1.63 0.105 VLMt + FEAR MODEL 0.056 -1 day 0.078 0.712 0.477 -2 days 0.133 0.071 1.89 0.061 -3 days 0.071 0.059 1.20 0.232 At -1 day -0.064 0.052 -1.24 0.216 -2 days -0.128 0.060 -2.14 0.034† -3 days -0.136 0.084 -1.62 0.107 Summary DW Adj. R2 F12,158 p 2.032 0.527 16.77 <0.001† Granger causality F3,158 p MC p 3.01 0.032† 0.045†
  • 18. 3σ Mt A t-2 2σ 1σ 0σ -1σ -2σ Aug 1 Sep 30
  • 19. MONTE CARLO SIMULATION con rmation some statistical violations threaten results NORMALITY, HETEROSCEDASTICITY F DRIFT rst principles approach PERFORM MANY TESTS WITH NEW, SYNTHETIC At
  • 20. Ct density estimate -1σ 0 1σ 2σ 3σ 4σ
  • 21. 2σ 1σ 0σ -1σ -2σ 2σ 1σ 0σ -1σ -2σ 2σ 1σ 0σ -1σ -2σ
  • 22. Monte Carlo p = 0.0453, up from 0.0322.
  • 23. Estimating worry & fear seems to contain SOME market direction information.
  • 24. WIDESPREAD WORRY AND THE STOCK MARKET Eric Gilbert & Karrie Karahalios University of Illinois