how to fix an alpha model - mit

35
19 November 2009 Nomura Securities International, Inc., New York How to fix an alpha model Joseph Mezrich Nomura Securities International, Inc. Please read the analyst certifications and important disclosures on pp. 33–34. gl

Upload: others

Post on 11-Nov-2021

1 views

Category:

Documents


0 download

TRANSCRIPT

Nomura Securities International, Inc.U.S. Quantitative Research

19 November 2009

Nomura Securities International, Inc., New York

How to fix an alpha model

Joseph MezrichNomura Securities International, Inc.

Please read the analyst certifications and important disclosures on pp. 33–34. gl

2Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

Alpha after the crisis• Which crisis?

Regime change in 2000. Is it now all about risk?

• The recovery: Are you buying cheap assets or simply trading risk?

The illusion of the stock picker’s market

Needed: Asset/Factor allocation in crowds – there is an eco-system

3Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

Why S&P 500 earnings should climb faster than broad economy –the positive backdrop

Note: Earnings are defined as the 12-month aggregate of real net income of all companies in the S&P 500 whose quarter ended on a given month. GDP is defined as the chain weighted real GDP at constant dollar prices. Last data as of 9/30/2009 for S&P 500 earnings and GDP. Source: Nomura Securities International Inc., S&P, Compustat, BEA, NBER.

0

1

2

3

4

5

6

7

1968

1970

1972

1974

1976

1978

1980

1982

1984

1986

1988

1990

1992

1994

1996

1998

2000

2002

2004

2006

2008

S&P

500

Earn

ings

/ G

DP

(%)_ S&P 500 Earnings / GDP

Recession

4Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

All together now The legacy of financial engineering

Systemic risk will likely change in magnitude but won’t go away

Note: Shows the long-term relationship between the volatility implied in 1-year S&P500 index options and the spread between Moody’s Seasoned Baa corporate bonds and 10-year US treasuries. The vertical line in the chart separates what seem to be two regimes: “after” when these risk measures tracked each other and “before” when they did not track each other. Last data as of 10/30/09.Source: Nomura Securities International, Inc., Opitionmetrics, Federal Reserve and Moody’s.

0.00

0.05

0.10

0.15

0.20

0.25

0.30

0.35

0.40

0.45

0.50O

ct-9

2

Oct

-93

Oct

-94

Oct

-95

Oct

-96

Oct

-97

Oct

-98

Oct

-99

Oct

-00

Oct

-01

Oct

-02

Oct

-03

Oct

-04

Oct

-05

Oct

-06

Oct

-07

Oct

-08

Oct

-09

SPX

1 Ye

ar Im

plie

d Vo

l

0.000

0.008

0.016

0.024

0.032

0.040

0.048

0.056

0.064

Baa and 10 Yr Tbond Spread

← Before

After →SPX 1 Year Implied Volatility

Baa & 10 Year Tbond Spread

5Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

All together nowThe legacy of financial engineering

Systemic risk will likely change in magnitude but won’t go away

Note: Shows z scores of cumulative monthly long-short factor returns of B/P and default risk (long low B/P and long low default risk). Also shows z scores of SPX 1-year implied volatility and synthetic CDX (post 2004 Markit’s index of credit default swap market risk, before 2004 implied CDX values imputed by spread between Baa corporates and 10-year T-bonds). The “before” and “after” line in the exhibit is placed at November 2001, the end of the 2001 recession. B/P factor returns based on decile spreads in Russell 1000 and default probability factor returns based on quintile spreads in S&P500. Decile or quintile baskets are rebalanced at the beginning of month. Last data as of 10/23/2009. Factor returns do not include transaction costs.Source: Nomura Securities International, Inc., Russell, S&P, Compustat, Worldscope, IDC, Ex-Share.

-3

-2

-1

0

1

2

3

4

5

6

7

8

9

1993

1994

1995

1996

1997

1998

1999

2000

2001

2002

2003

2004

2005

2006

2007

2008

2009

Z Sc

ore

-9

-8

-7

-6

-5

-4

-3

-2

-1

0

1

2

3

Z Score

Default risk return (LHS)Synthetic CDX (LHS)SPX 1 year implied volatility (LHS)B/P return (RHS)

After -><- Before

6Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

S&P500 implied volatility –equity risk jumped, then exploded, then reverted

Note: Shows implied volatilities of 1-month and 1-year S&P500 index options. Last data as of 11/11/2009.Source: Nomura Securities International Inc. and Optionmetrics.

5%

10%

15%

20%

25%

30%

35%

40%

45%

50%

55%

60%

65%

70%

75%

80%

Jul-0

7

Aug

-07

Sep

-07

Oct

-07

Nov

-07

Dec

-07

Jan-

08

Feb-

08

Mar

-08

Apr

-08

May

-08

Jun-

08

Jul-0

8

Aug

-08

Sep

-08

Oct

-08

Nov

-08

Dec

-08

Jan-

09

Feb-

09

Mar

-09

Apr

-09

May

-09

Jun-

09

Jul-0

9

Aug

-09

Sep

-09

Oct

-09

Nov

-09

One Month vol (VIX)

One Year vol

0%

10%

20%

30%

40%

50%

60%

70%

80%

Nov

-95

Jul-9

6

Mar

-97

Nov

-97

Jul-9

8

Mar

-99

Nov

-99

Jul-0

0

Mar

-01

Nov

-01

Jul-0

2

Mar

-03

Nov

-03

Jul-0

4

Mar

-05

Nov

-05

Jul-0

6

Mar

-07

Nov

-07

Jul-0

8

Mar

-09

Nov

-09

One M onth vol One Year vol

9/11LTCM2002, Accounting Scandals

Asian Crisis

Iraq W ar Begins - vol slide begins

Credit Crisis

7Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

The world changed around 2000The odd case of one-year price momentum

Note: Shows one-year price momentum rebalanced at different times: end of month (blue line), middle of month (green line) and quarter end (red line). Universe is Russell 1000. Last data as of 10/31/09. Transaction costs are not considered.Source: Nomura Securities International, Inc., Russell, IDC.

0%

50%

100%

150%

200%

250%

300%

350%

400%

Sep-89

Sep-90

Sep-91

Sep-92

Sep-93

Sep-94

Sep-95

Sep-96

Sep-97

Sep-98

Sep-99

Sep-00

Sep-01

Sep-02

Sep-03

Sep-04

Sep-05

Sep-06

Sep-07

Sep-08

Sep-09

1 yr pm monthly, endmonth1 yr pm quarterly1 yr pm month, midmonth

8Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

Notes: Universe is Russell 1000. The exhibit shows the cumulative monthly return to owning the best three factors in 22 representative factors on the right table, based on the past five-year performances. The period of analysis is from Mar 1984 through Sep 2009. Transaction costs are not considered.Source: Nomura Securities International Inc., Compustat, I/B/E/S, IDC, Russell.

The change in factor persistence:five-year factor momentum fades

Winning factors based on five-year performances

0

50

100

150

200

250

300

1984

1985

1986

1987

1988

1989

1990

1991

1992

1993

1994

1995

1996

1997

1998

1999

2000

2001

2002

2003

2004

2005

2006

2007

2008

2009

Cum

ulat

ive

retu

rn (%

)_ Mar 2000

Aug 2007

Mar 2009

1 Mon. Price Momentum (Low - High)1 Year Price Momentum1 Year Dividend Growth5 Year EPS GrowthPredicted LT GrowthUp to Down RevisionsB/P

Dividend YieldE/PEBITDA/EVPEG (Low - High)Predicted E/P

Quality Accruals (Low - High)Leverage Debt/Equity (Low - High)

BetaDefault Risk (Safe - Risky)Estimate Dispersion (Low - High)

Profitability ROEMarket Cap (Small - Large)CapEx/Sales (Low - High)Analyst Coverage (Low - High)Share Buybacks

Other

Momentum

Growth

Value

Risk

9Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

Note: The bar chart displays the variance of the principal components derived from the factor set shown at right, and number above the bars corresponds to the cumulative percentage of variances. Universe is Russell 1000. The analysis is as of 4/30/2009.Source: Nomura Securities International Inc., Compustat, I/B/E/S, Russell, and IDC.

Principle components of fundamental factors… is it a single-factor world?

1 Mon. Price Momentum (Low - High)1 Year Price Momentum1 Year Dividend Growth5 Year EPS GrowthPredicted LT GrowthUp to Down RevisionsB/P

Dividend YieldE/PEBITDA/EVPEG (Low - High)Predicted E/P

Quality Accruals (Low - High)Leverage Debt/Equity (Low - High)

BetaDefault Risk (Safe - Risky)Estimate Dispersion (Low - High)

Profitability ROEMarket Cap (Small - Large)CapEx/Sales (Low - High)Analyst Coverage (Low - High)Share Buybacks

Growth

Value

Risk

Other

Momentum

0

2

4

6

8

10

12

14

Com

p.1

Com

p.2

Com

p.3

Com

p.4

Com

p.5

Com

p.6

Com

p.7

Com

p.8

Com

p.9

Com

p.10

Varia

nces

(%)

Since Jun 2007Since Sep 1984

62%

36%

63%

73%77%

86%78%90%

10Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

Note: The bars show the loadings of the factors that produce the primary, first principal component for the period since the crisis began. The principal components analysis is based on monthly time series of 22 representative factor returns shown on page 9 from Jun 2007 through Apr 2009. Universe is Russell 1000.Source: Nomura Securities International Inc., Compustat, I/B/E/S, Russell, and IDC.

Principle components of fundamental factors… is it a single-factor world?

1st component since June 2007

-0.3 -0.2 -0.1 0 0.1 0.2 0.3

1 Yr. Price MomentumDefault Risk (Safe-Risky)

Estimate Dispersion(Low-High)1 Year Dividend GrowthUp to Down RevisionsDebt/Equity(Low-High)

5 Year EPS GrowthROE

Predicted LT GrowthShare Buybacks

Predicted E/PCapEx/Sales(Low-High)

Analyst Coverage(Low-High)1 Mon. Price Momentum (Low - High)

Accruals(Low-High)PEG(Low-High)

Dividend YieldBetaE/P

EBITDA/EVMarket Cap (Small - Large)

B/P

11Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

How much is explained by a single factor?

Note: Weights of the first principal component in the factor-return variance are shown in time series. The principal component analysis is based on the past three-year performances of the 22 representative factors shown on page 9. Universe is Russell 1000. The analysis ranges from Dec 1991 through Sep 2009.Source: Nomura Securities International Inc., Compustat, I/B/E/S, IDC, Russell.

US

0

10

20

30

40

50

60

7019

87

1988

1989

1990

1991

1992

1993

1994

1995

1996

1997

1998

1999

2000

2001

2002

2003

2004

2005

2006

2007

2008

2009

Wei

ght o

f 1st

prin

cipa

l com

pone

nt (%

)

12Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

Notes: Universe is Russell 1000. Exhibit shows spreads of the cumulative weekly returns to owning the best three factors in 22 representative factors (see page 9), based on past four-week performances with different rebalance schedules. “Weekly rebalancing” indicates the case that winning factors are rebalanced at every Friday’s close, while “Month-end rebalancing” and “Avoiding month-end rebalancing” correspond to rebalancing at the first Friday’s close and the last Friday’s close every month, respectively. Period of analysis is from 27 Feb 1984 through 2 Oct 2009. Transaction costs are not considered.Source: Nomura Securities International Inc., Compustat, I/B/E/S, IDC, Russell.

Both speed and crowding are impacting factor strategy now

Diagnosing speed and crowding via rebalance scenario comparisons

-50

0

50

100

150

20019

84

1985

1986

1987

1988

1989

1990

1991

1992

1993

1994

1995

1996

1997

1998

1999

2000

2001

2002

2003

2004

2005

2006

2007

2008

2009

Spre

ad o

f cum

ulat

ive

retu

rns

(%)

(Avoiding month-end rebalancing) - (Month-end rebalancing) = " Crowding "

(Weekly rebalancing) - (Avoiding month-end rebalancing) = " Speed "

Aug 2007

Mar 2009

Jul 1999 Jan 2002

13Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

Note: Universe is Russell 1000. Exhibit shows spreads of the cumulative daily returns to owning the best three factors in 22 representative factors based on the past 21 trading day performances with four different rebalance schedules. Period of analysis is from 27 Feb 1987 through 15 Oct 2009. Transaction costs are not considered.Source: Nomura Securities International Inc., Compustat, I/B/E/S, IDC, Russell.

Rebalance timing, speed and crowding –the impact of being early or late

-250

-200

-150

-100

-50

0

50

100

150

1987

1988

1989

1990

1991

1992

1993

1994

1995

1996

1997

1998

1999

2000

2001

2002

2003

2004

2005

2006

2007

2008

2009

Cum

ulat

ive

retu

rns

rela

tive

to m

onth

-end

reba

lanc

ing

(%)_

Jan 2003Apr 1999

(Rebalancing 2 day after month-end) - (Month-end rebalancing)

(Rebalancing 1 day after month-end) - (Month-end rebalancing)

(Rebalancing 1 day before month-end) - (Month-end rebalancing)

(Rebalancing 2 day before month-end) - (Month-end rebalancing)

Aug 2007

Nov 2008

14Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

The odd case of one-month price momentum: Reversal or trend? Rebalance schedule lets you choose!

Note: Shows cumulative monthly returns to one-month price momentum (long bottom 100, short top 100) in Russell 1000. This is the opposite of the way that one-year momentum is defined, since one-month momentum is usually thought of as a reversal signal. The portfolios are rebalanced at the middle of month (blue line) and rebalanced at the end of the month (red line). Last data as of 7/31/2009. Transaction costs are not considered.Source: Nomura Securities International Inc., Russell, IDC.

-100

-80

-60

-40

-20

0

20

40

60

Dec

-06

Feb-

07

Apr-

07

Jun-

07

Aug-

07

Oct

-07

Dec

-07

Feb-

08

Apr-

08

Jun-

08

Aug-

08

Oct

-08

Dec

-08

Feb-

09

Apr-

09

Jun-

09

Cum

ulat

ive

mon

thly

retu

rns,

%

1 month price momentum rebalanced mid-month1 month price momentum rebalanced end-month

15Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

Alpha after the crisis

• Which crisis?

Regime change in 2000. Is it now all about risk?

• The recovery: Are you buying cheap assets or simply trading risk?

The illusion of the stock picker’s market

Needed: Asset/Factor allocation in crowds – there is an eco-system

16Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

Correlation of B/P with default risk and earnings uncertainty- why value investing works (or doesn’t)

Note: B/P-default probability and estimate dispersion correlation are based on the B/P score and the logarithm of default probability or estimate dispersion (FY1) in S&P500 universe with 0 default probability stocks excluded. Last data as of 10/23/09.Source: Nomura Securities International, Inc., S&P, Compustat, I/B/E/S.

-0.1

0

0.1

0.2

0.3

0.4

0.5

0.6

0.7

0.819

87

1988

1989

1990

1991

1992

1993

1994

1995

1996

1997

1998

1999

2000

2001

2002

2003

2004

2005

2006

2007

2008

Ran

k co

rrel

atio

n

B/P-EstDisp CorB/P-DefaultRisk Cor

17Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

US

-60

-40

-20

0

20

40

60

80N

ov-0

7D

ec-0

7Ja

n-08

Feb-

08M

ar-0

8Ap

r-08

May

-08

Jun-

08Ju

l-08

Aug-

08Se

p-08

Oct

-08

Nov

-08

Dec

-08

Jan-

09Fe

b-09

Mar

-09

Apr-

09M

ay-0

9Ju

n-09

Jul-0

9Au

g-09

Sep-

09

Cum

ulat

ive

daily

fact

or re

turn

(%) Estimate dispersion (low -high)

B/P

Nov 21Citigroupbailout

Jan 8US jobs

Japan

-60

-40

-20

0

20

40

60

80

Nov

-07

Dec

-07

Jan-

08Fe

b-08

Mar

-08

Apr-

08M

ay-0

8Ju

n-08

Jul-0

8Au

g-08

Sep-

08O

ct-0

8N

ov-0

8D

ec-0

8Ja

n-09

Feb-

09M

ar-0

9Ap

r-09

May

-09

Jun-

09Ju

l-09

Aug-

09Se

p-09

Cum

ulat

ive

daily

fact

or re

turn

(%) Estimate dispersion (low -high)

B/P

Nov 21Citigroupbailout

Jan 8US jobs

Dec 5China

Europe

-50

-40

-30

-20

-10

0

10

20

30

40

50

Nov

-07

Dec

-07

Jan-

08Fe

b-08

Mar

-08

Apr-

08M

ay-0

8Ju

n-08

Jul-0

8Au

g-08

Sep-

08O

ct-0

8N

ov-0

8D

ec-0

8Ja

n-09

Feb-

09M

ar-0

9Ap

r-09

May

-09

Jun-

09Ju

l-09

Aug-

09Se

p-09

Cum

ulat

ive

daily

fact

or re

turn

(%) Estimate dispersion (low -high)

B/P

Asia

-20

-10

0

10

20

30

40

50

Nov

-07

Dec

-07

Jan-

08Fe

b-08

Mar

-08

Apr-

08M

ay-0

8Ju

n-08

Jul-0

8Au

g-08

Sep-

08O

ct-0

8N

ov-0

8D

ec-0

8Ja

n-09

Feb-

09M

ar-0

9Ap

r-09

May

-09

Jun-

09Ju

l-09

Aug-

09Se

p-09

Cum

ulat

ive

daily

fact

or re

turn

(%) Estimate dispersion (low -high)

B/P

Nov 21Citigroupbailout

Jan 8US jobsDec 5

China

M ar 9

M ar 9

M ar 9

M ar 9

Value fails when risk aversion rises and vice versa: Estimate dispersion vs. B/P

Note: US = Russell 1000; Europe = MSCI Europe, Japan = NOMURA 400, Asia ex Japan = MSCI Asia Pacific ex Japan (Australia, Hong Kong, New Zealand and Singapore). Shows cumulative return of a factor portfolio that is long the lowest estimate dispersion stocks and short the highest estimate dispersion, and the cumulative return of a factor portfolio that is long the highest book-to-price (B/P) stocks while short the lowest B/P stocks. US is based on decile baskets, while other regions are based on quintile baskets. Long and short baskets are rebalanced monthly with equal weighting. Last data as of 10/29/2009 for Japan, 10/28/2009 for US, Europe and Asia. Factor returns do not include transaction costs. Source: Nomura Securities International Inc., Compustat, I/B/E/S, Russell, IDC, Worldscope, ExShare and MSCI.

18Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

Valuation and default probability –How fear and relief affect value stocks

Note: Green line shows average B/P for the 100 stocks in the S&P500 (US) and Nomura 400 (Japan) with the highest default probability, blue line shows average B/P for the 100 stocks with the lowest default probability. Returns do not include transaction costs. Last data as of 10/23/2009 for US and 10/29/2009 for Japan.Source: Nomura Securities International Inc., Compustat, I/B/E/S, Russell, and IDC.

US

Japan

0.0

0.5

1.0

1.5

2.0

1993

1994

1995

1996

1997

1998

1999

2000

2001

2002

2003

2004

2005

2006

2007

2008

2009

B/P

Corporate scandals

Subprime crisisChe

apE

xpen

sive

High default probability stocks

Low default probability stocks

Lehman bankruptcy

0.2

0.4

0.6

0.8

1.0

1.2

1.4

1.6

1.8

1993

1994

1995

1996

1997

1998

1999

2000

2001

2002

2003

2004

2005

2006

2007

2008

2009

B/P

Financial crisis

Subprime crisis

Chea

pEx

pens

ive

high default risk stocks

low default risk stocks

Lehman bankruptcyYamaichi bankruptcy

19Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

Revenge of the cheap losers – version 1

Note: Shows cumulative excess returns over Russell 1000 of each quintile of B/P and one-year price momentum from Jan 2007 to Oct 2009 in Russell 1000. Transaction costs are not included. Last data as of 10/31/2009.Source: Nomura Securities International Inc., Compustat, I/B/E/S, Russell, and IDC.

-60%

-40%

-20%

0%

20%

40%

60%

Nov

-06

Feb-

07

May

-07

Aug

-07

Nov

-07

Feb-

08

May

-08

Aug

-08

Nov

-08

Feb-

09

May

-09

Aug

-09

Cum

ulat

ive

Exc

ess

Ret

urn

Spread (Highest - Lowest)Q1 (Highest 1yrPM)Q2Q3Q4Q5 (Lowest 1yrPM)

1 Year Price Momentum

-60%

-50%

-40%

-30%

-20%

-10%

0%

10%

20%

30%

Nov

-06

Feb-

07

May

-07

Aug

-07

Nov

-07

Feb-

08

May

-08

Aug

-08

Nov

-08

Feb-

09

May

-09

Aug

-09

Cum

ulat

ive

Exc

ess

Ret

urn

Spread (Highest - Lowest)Q1 (Highest B/P)Q2Q3Q4Q5 (Lowest B/P)

Book/Price

20Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

Valuation and default probability –How fear and relief affect value stocks

Note: The B/P-default probability correlation is based on B/P score and logarithm of default probability in S&P500 universe with 0 default probability stocks excluded. B/P spread (high default risk – low default risk) is based on the gap between median B/P for top and bottom quintile in S&P500 universe due to the default probability. Synthetic CDX is CDX since the end of 2004, but extended before that by using the linear relationship with bond spreads, where the coefficients are estimated by the time series regression from 31 Dec 2004 to 4 Feb 2008. Transaction costs not included in factor returns. Last data as of 11/6/09.Source: Nomura Securities International, Inc., MarkitGroup Ltd., Optionmetrics, Federal Reserve, Moody’s, Bloomberg, S&P, Compustat,, IDC,.

-3.0

-2.0

-1.0

0.0

1.0

2.0

3.0

4.0

5.0

6.0

7.0

Jan-

96

Jul-9

6

Jan-

97

Jul-9

7

Jan-

98

Jul-9

8

Jan-

99

Jul-9

9

Jan-

00

Jul-0

0

Jan-

01

Jul-0

1

Jan-

02

Jul-0

2

Jan-

03

Jul-0

3

Jan-

04

Jul-0

4

Jan-

05

Jul-0

5

Jan-

06

Jul-0

6

Jan-

07

Jul-0

7

Jan-

08

Jul-0

8

Jan-

09

Jul-0

9

Z-SC

OR

E

B/P default correlationB/P spread ( high default risk - low default risk )

-3.0

-2.0

-1.0

0.0

1.0

2.0

3.0

4.0

Jan-

96

Jul-9

6

Jan-

97

Jul-9

7

Jan-

98

Jul-9

8

Jan-

99

Jul-9

9

Jan-

00

Jul-0

0

Jan-

01

Jul-0

1

Jan-

02

Jul-0

2

Jan-

03

Jul-0

3

Jan-

04

Jul-0

4

Jan-

05

Jul-0

5

Jan-

06

Jul-0

6

Jan-

07

Jul-0

7

Jan-

08

Jul-0

8

Jan-

09

Jul-0

9

z-sc

ore

B/P Default CorrelationSynthetic CDX

-3.0

-2.0

-1.0

0.0

1.0

2.0

3.0

4.0

5.0

Jan-

96

Jul-9

6

Jan-

97

Jul-9

7

Jan-

98

Jul-9

8

Jan-

99

Jul-9

9

Jan-

00

Jul-0

0

Jan-

01

Jul-0

1

Jan-

02

Jul-0

2

Jan-

03

Jul-0

3

Jan-

04

Jul-0

4

Jan-

05

Jul-0

5

Jan-

06

Jul-0

6

Jan-

07

Jul-0

7

Jan-

08

Jul-0

8

Jan-

09

Jul-0

9

z-sc

ore

B/P Default CorrelationSPX 1Y Volatility

21Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

Alpha after the crisis

• Which crisis?

Regime change in 2000. Is it now all about risk?

• The recovery: Are you buying cheap assets or simply trading risk?

The illusion of the stock picker’s market

Needed: Asset/Factor allocation in crowds – there is an eco-system

22Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

Regime changes:Beta as proxy for earnings uncertainty and earnings quality

Note: Shows cross-sectional correlations between factors beta vs. estimate dispersion and accruals. Universe is Russell 1000. Last data as of 9/30/2009.Source: Nomura Securities International Inc., Compustat, I/B/E/S, IDC, Russell.

-0.4

-0.3

-0.2

-0.1

0

0.1

0.2

0.3

0.4

0.5

Oct

-84

Oct

-86

Oct

-88

Oct

-90

Oct

-92

Oct

-94

Oct

-96

Oct

-98

Oct

-00

Oct

-02

Oct

-04

Oct

-06

Oct

-08

Ran

k C

orre

latio

n

Beta and Earnings Uncertainty (Estimate Dispersion)

Beta and Earnings Quality (Accruals)

23Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

Note: Shows cumulative daily factor returns (long top decile, short bottom decile) for B/P, E/P, predicted E/P, and sales/price for stocks in the Russell 1000. Last data as of 11/10/2009. Transaction costs are not considered.Source: Nomura Securities International Inc., Compustat, I/B/E/S, Russell, and IDC.

Value strategies: the odd divide

Russell 1000: Value Factor Returns

-60

-40

-20

0

20

40

60

80

10012

-May

-08

2-Ju

n-08

23-J

un-0

814

-Jul

-08

4-Au

g-08

25-A

ug-0

815

-Sep

-08

6-O

ct-0

827

-Oct

-08

17-N

ov-0

88-

Dec

-08

29-D

ec-0

819

-Jan

-09

9-Fe

b-09

2-M

ar-0

923

-Mar

-09

13-A

pr-0

94-

May

-09

25-M

ay-0

915

-Jun

-09

6-Ju

l-09

27-J

ul-0

917

-Aug

-09

7-Se

p-09

28-S

ep-0

919

-Oct

-09

9-N

ov-0

9

Cum

ualti

ve D

aily

Ret

urns

(%)

B/P

E/P

Predicted E/P

Sales/Price

24Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

Note: Shows cross-sectional correlation between book/price and predicted earnings/price (red line) and the cumulative monthly factor return (in this case, cheap minus expensive decile) spreads of B/P and predicted E/P (blue line). Universe is Russell 1000. Last data as of 10/31/2009.Source: Nomura Securities International Inc., Compustat, I/B/E/S, Russell, and IDC.

Correlation breakdown – B/P and Predicted E/P

0

0.1

0.2

0.3

0.4

0.5

Nov

-02

May

-03

Nov

-03

May

-04

Nov

-04

May

-05

Nov

-05

May

-06

Nov

-06

May

-07

Nov

-07

May

-08

Nov

-08

May

-09

Nov

-09

Corr

elat

ion

-160

-112

-64

-16

32

80

Mon

thly

Cum

ulat

ive

Spre

ads,

%

B/P and Predicted E/P Correlation (LHS)

B/P - Predicted E/P (RHS)

2/28/2009

When "factor correlation breakdown and a trade" published

25Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

Note: Shows cross-sectional correlation between book/price and predicted earnings/price (red line) and the cumulative monthly factor return (in this case, cheap minus expensive decile) spreads of B/P and predicted E/P (blue line), excluding transaction costs. Universe is Russell 1000. Last data as of 10/31/2009.Source: Nomura Securities International Inc., Compustat, I/B/E/S, Russell, and IDC.

Correlation breakdown —B/P vs. Predicted E/P and S/P vs. E/P

Pred EP and BP

0

0.1

0.2

0.3

0.4

0.5

0.6

0.7

0.8

1990

1992

1994

1996

1998

2000

2002

2004

2006

2008

2010

Cor

relatio

n

-200

-180

-160

-140

-120

-100

-80

-60

-40

-20

0

Mon

thly C

umulative Sp

read

, %

Correlation (LHS)

B/P - Predicted E/P spread (RHS)

When we publishedlast piece

EP and SP

-0.1

0

0.1

0.2

0.3

0.4

0.5

0.6

0.7

0.8

1990

1992

1994

1996

1998

2000

2002

2004

2006

2008

2010

Cor

relatio

n

-80

-60

-40

-20

0

20

40

60

Mon

thly C

umulative Sp

read

, %

Correlation (LHS)

B/P - S/P spread (RHS)

26Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

Correlation breakdown – A summary table for different value pairs

Note: Shows average correlation, lowest correlation since March 2009, current correlation (10/31/2009), annualized average spread (11/1984 to 10/2009) and cumulative spread from March to October 2009 between four value pairs, B/P vs. PredE/P, B/P vs. E/P, S/P vs. PredE/P and S/P vs. E/P. Universe is Russell 1000. Last data as of 10/31/2009.Source: Nomura Securities International Inc., Compustat, I/B/E/S, Russell, and IDC.

B/P vs Pred E/P B/P vs E/P S/P vs Pred E/P S/P vs E/PAverage Correlation (11/1984 -- 10/2009) 0.47 0.35 0.46 0.28Lowest Correlation

reached after March 2009 0.02 -0.14 0.14 -0.05

Current Correlation (10/31/2009) 0.08 -0.10 0.26 0.06Average Spread (annualized,

11/1984 -- 10/2009) -3.78% 0.96% 0.47% -4.26%Cumulative Spread, March

to October 2009 86% 38% 86% 38%

27Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

Revenge of the cheap losers – version 2

Note: Shows 6-month rolling returns of the losing decile with lowest scores of 1-year price momentum plus the cheapest deciles of book/price, earnings/price and predicted earnings/price, respectively. Universe is Russell 1000. Transaction costs are not considered. Last data as of 10/31/09.Source: Nomura Securities International Inc., Compustat, I/B/E/S, Russell, and IDC.

-400

-300

-200

-100

0

100

200

300

400

500

Nov

-81

Nov

-83

Nov

-85

Nov

-87

Nov

-89

Nov

-91

Nov

-93

Nov

-95

Nov

-97

Nov

-99

Nov

-01

Nov

-03

Nov

-05

Nov

-07

Nov

-09

Rol

ling

6-m

onth

retu

rns,

%

B/P (top decile) + 1 yr PM (bottom decile)

E/P (top decile) + 1 yr PM (bottom decile)

Pred E/P (top decile) + 1 yr PM (bottom decile)

28Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

Revenge of the cheap losers – version 2

Note: Shows 6-month rolling returns of the losing decile with lowest scores of 1-year price momentum plus the cheapest deciles of book/price, earnings/price and predicted earnings/price, respectively. Universe is Russell 1000. Transaction costs not considered. Last data as of 10/31/09.Source: Nomura Securities International Inc., Compustat, I/B/E/S, Russell, and IDC.

-400

-300

-200

-100

0

100

200

300

400

500

Dec

-05

Feb-

06

Apr

-06

Jun-

06

Aug

-06

Oct

-06

Dec

-06

Feb-

07

Apr

-07

Jun-

07

Aug

-07

Oct

-07

Dec

-07

Feb-

08

Apr

-08

Jun-

08

Aug

-08

Oct

-08

Dec

-08

Feb-

09

Apr

-09

Jun-

09

Aug

-09

Rol

ling

6-m

onth

retu

rns,

%

B/P (top decile) + 1 yr PM (bottom decile)

E/P (top decile) + 1 yr PM (bottom decile)

Pred E/P (top decile) + 1 yr PM (bottom decile)

29Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

40

45

50

55

60

65

70

75

80

1/2/

08

3/2/

08

5/2/

08

7/2/

08

9/2/

08

11/2

/08

1/2/

09

3/2/

09

5/2/

09

7/2/

09

9/2/

09

11/2

/09

Impl

ied

Cor

rela

tion

10

20

30

40

50

60

70

80

90

Vix

(ICJ) January 2010(JCJ) January 2011VIX

S&P500 Index Options are pricing high stock correlation

Note: Shows VIX index and different implied correlation indices, ICJ and JCJ. Last data as of 11/2/09.Source: Nomura Securities International Inc., Chicago Board Options Exchange.

30Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

Current and historical alpha-repair factor weights in US

Optimal Factors

Nov 2009 Oct 2009 Sep 2009 Aug 2009 Jul 2009 Jun 2009 May 2009 Apr 2009 Mar 2009 Feb 2009 Jan 2009 Dec 2008

Operating Income before deprec/price 27.8 39.6 40.4 40.3 39.1

Estimate Dispersion 34.6 31.7 35.2 33.9 30.5 28.0 42.4 41.2 37.0

Asset Turnover 31.0 32.2 25.6 28.7 24.4 25.8 30.5 22.7 25.4

EBITDA/EV 26.6 49.3 27.1 27.4 33.1 39.9

EBIT/EV 30.6 31.5

1 Year EPS Growth 34.7

Share Buybacks 41.2

Sales/Price 39.8

ROIC x B/P 29.9

Decreasing CapEx/Sales 41,2

Monthly Factor Selection and Weights (%)

Note: Shows monthly factor selection for Alpha Repair. Universe is Russell 1000. Data as of 10/31/2009. See Appendix L of US Quant Monthly for factor definitions. For details, see Nomura quant reports, Alpha Repair: a factor competition approach to stock selection, 22 January 2007, and Black swans and portfolio protection: factor constraints and alpha repair, 8 April 2008.Source: Nomura Securities International Inc., Compustat, I/B/E/S, Russell, and IDC.

31Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

Note: Last data as of 10/31/2009. Transaction costs are not included. For explanation of Alpha Repair Long Only portfolio, see Nomura quant report, Alpha Repair, 22 January 2007. Details of model performance, which should not and cannot be viewed as an indicator of future performance, are available upon request.

Source: Nomura Securities International Inc., Compustat, I/B/E/S, Russell, and IDC.

Alpha Repair:What we learned from two crises …

-15%

-5%

5%

15%

25%

35%

45%

55%

Jan-

97

Jul-9

7

Jan-

98

Jul-9

8

Jan-

99

Jul-9

9

Jan-

00

Jul-0

0

Jan-

01

Jul-0

1

Jan-

02

Jul-0

2

Jan-

03

Jul-0

3

Jan-

04

Jul-0

4

Jan-

05

Jul-0

5

Jan-

06

Jul-0

6

Jan-

07

Jul-0

7

Jan-

08

Jul-0

8

Jan-

09

Jul-0

9

Exce

ss R

etur

ns o

ver R

usse

ll 10

00Annual Excess Returns

Alpha-Repair Long-only Portfolio, Style-Factors Constrained

Out of SamplePortfolio

12/31/2006End of Backtest

regression line from backtest

32Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

Alpha after the crisis

• Which crisis?

Regime change in 2000. Is it now all about risk?

• The recovery: Are you buying cheap assets or simply trading risk?

The illusion of the stock picker’s market

Needed: Asset/Factor allocation in crowds – there is an eco-system

33Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

Any Authors named on this report are Research Analysts unless otherwise indicated

ANALYSTS CERTIFICATIONS

I, Joseph Mezrich, a research analyst employed by Nomura Securities International Inc, hereby certify that all of the views expressed in this research report accurately reflect my personal views about any and all of the subject securities or issuers discussed herein. In addition, I hereby certify that no part of my compensation was, is, or will be, directly or indirectly related to the specific recommendations or views that I have expressed in this research report, nor is it tied to any specific investment banking transactions performed by Nomura Securities International, Inc., Nomura International plc or by any other Nomura Group company or affiliates thereof.

Online availability of research and additional disclosuresNomura Japanese Equity Research is available electronically for clients in the US on NOMURA.COM, REUTERS, BLOOMBERG and THOMSON ONE ANALYTICS. For clients in Europe, Japan and elsewhere in Asia it is available on NOMURA.COM, REUTERS and BLOOMBERG.

Important disclosures may be accessed through the left hand side of the Nomura Disclosure web page http://www.nomura.com/research or requested from Nomura Securities International, Inc., on 1-877-865-5752. If you have any difficulties with the website, please email [email protected] for technical assistance.

The analysts responsible for preparing this report have received compensation based upon various factors including the firm's total revenues, a portion of which is generated by Investment Banking activities.

MSCI indicesRegarding reference to or use of its data, MSCI requires disclosure that: The MSCI sourced information is the exclusive property of Morgan Stanley Capital International Inc. (MSCI). Without prior written permission of MSCI, this information and any other MSCI intellectual property may not be reproduced, redisseminated or used to create any financial products, including any indices. This information is provided on an “as is” basis. The user assumes the entire risk of any use made of this information. MSCI, its affiliates and any third party involved in, or related to, computing or compiling the information hereby expressly disclaim all warranties of originality, accuracy, completeness, merchantability or fitness for a particular purpose with respect to any of this information. Without limiting any of the foregoing, in no event shall MSCI, any of its affiliates or any third party involved in, or related to, computing or compiling the information have any liability for any damages of any kind. MSCI, Morgan Stanley Capital International and the MSCI indexes are services marks of MSCI and its affiliates.

DISCLAIMERSThis publication contains material that has been prepared by the Nomura entity identified on the banner at the top or the bottom of page 1 herein and, if applicable, with the contributions of one or more Nomura entities whose employees and their respective affiliations are specified on page 1 herein or elsewhere identified in the publication. Affiliates and subsidiaries of Nomura Holdings, Inc. (collectively, the "Nomura Group"), include: Nomura Securities Co., Ltd. ("NSC") Tokyo, Japan; Nomura International plc, United Kingdom; Nomura Securities International, Inc. ("NSI"), New York, NY; Nomura International (Hong Kong) Ltd., Hong Kong; Nomura Singapore Ltd., Singapore; Nomura Australia Ltd., Australia; P.T. Nomura Indonesia, Indonesia; Nomura Securities Malaysia Sdn. Bhd., Malaysia; Nomura International (Hong Kong) Ltd., Taipei Branch, Taiwan; Nomura International (Hong Kong) Ltd., Seoul Branch, Korea; Nomura Financial Advisory and Securities (India) Private Limited, Mumbai, India (Registered Address: 2nd Floor, Ballard House, Adi Marzban Path, Ballard Pier, Fort, Mumbai, 400 001; SEBI Registration No:- BSE INB011299030, NSE INB231299034, INF231299034).

This material is: (i) for your private information, and we are not soliciting any action based upon it; (ii) not to be construed as an offer to sell or a solicitation of an offer to buy any security in any jurisdiction where such offer or solicitation would be illegal; and (iii) based upon information that we consider reliable, but we do not represent that it is accurate or complete, and it should not be relied upon as such.

34Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research

Opinions expressed are current opinions as of the original publication date appearing on this material only and the information, including the opinions contained herein, are subject to change without notice. If and as applicable, NSI's investment banking relationships, investment banking and non-investment banking compensation and securities ownership (identified in this report as "Disclosures Required in the United States"), if any, are specified in disclaimers and related disclosures in this report. In addition, other members of the Nomura Group may from time to time perform investment banking or other services (including acting as advisor, manager or lender) for, or solicit investment banking or other business from, companies mentioned herein. Further, the Nomura Group, and/or its officers, directors and employees, including persons, without limitation, involved in the preparation or issuance of this material may, to the extent permitted by applicable law and/or regulation, have long or short positions in, and buy or sell, the securities (including ownership by NSI, referenced above), or derivatives (including options) thereof, of companies mentioned herein, or related securities or derivatives. In addition, the Nomura Group, excluding NSI, may act as a market maker and principal, willing to buy and sell certain of the securities of companies mentioned herein. Further, the Nomura Group may buy and sell certain of the securities of companies mentioned herein, as agent for its clients.

Investors should consider this report as only a single factor in making their investment decision and, as such, the report should not be viewed as identifying or suggesting all risks, direct or indirect, that may be associated with any investment decision.

NSC and other non-US members of the Nomura Group (i.e., excluding NSI), their officers, directors and employees may, to the extent it relates to non-US issuers and is permitted by applicable law, have acted upon or used this material prior to, or immediately following, its publication.

Foreign currency-denominated securities are subject to fluctuations in exchange rates that could have an adverse effect on the value or price of, or income derived from, the investment. In addition, investors in securities such as ADRs, the values of which are influenced by foreign currencies, effectively assume currency risk.

The securities described herein may not have been registered under the U.S. Securities Act of 1933, and, in such case, may not be offered or sold in the United States or to U.S. persons unless they have been registered under such Act, or except in compliance with an exemption from the registration requirements of such Act. Unless governing law permits otherwise, you must contact a Nomura entity in your home jurisdiction if you want to use our services in effecting a transaction in the securities mentioned in this material.

This publication has been approved for distribution in the United Kingdom and European Union as investment research by Nomura International plc ("NIPlc"), which is authorised and regulated by the U.K. Financial Services Authority ("FSA") and is a member of the London Stock Exchange. It does not constitute a personal recommendation, as defined by the FSA, or take into account the particular investment objectives, financial situations, or needs of individual investors. It is intended only for investors who are "eligible counterparties" or "professional clients" as defined by the FSA, and may not, therefore, be redistributed to retail clients as defined by the FSA. This publication may be distributed in Germany via Nomura Bank (Deutschland) GmbH, which is authorised and regulated in Germany by the Federal Financial Supervisory Authority ("BaFin"). This publication has been approved by Nomura International (Hong Kong) Ltd. ("NIHK"), which is regulated by the Hong Kong Securities and Futures Commission, for distribution in Hong Kong by NIHK. Neither NIPlc nor NIHK hold an Australian financial services licence as both are exempt from the requirement to hold this license in respect of the financial services either provides. This publication has also been approved for distribution in Malaysia by Nomura Securities Malaysia Sdn. Bhd. In Singapore, this publication has been distributed by Nomura Singapore Limited (“NSL”). NSL accepts legal responsibility for the content of this publication, where it concerns securities, futures and foreign exchange, issued by its foreign affiliate in respect of recipients who are not accredited, expert or institutional investors as defined by the Securities and Futures Act (Chapter 289). Recipients of this publication may contact NSL in respect of matters arising from, or in connection with, this publication. NSI accepts responsibility for the contents of this material when distributed in the United States.

No part of this material may be (i) copied, photocopied, or duplicated in any form, by any means, or (ii) redistributed without the prior written consent of the Nomura Group member identified in the banner on page 1 of this report. Further information on any of the securities mentioned herein may be obtained upon request. If this publication has been distributed by electronic transmission, such as e-mail, then such transmission cannot be guaranteed to be secure or error-free as information could be intercepted, corrupted, lost, destroyed, arrive late or incomplete, or contain viruses. The sender therefore does not accept liability for any errors or omissions in the contents of this publication, which may arise as a result of electronic transmission. If verification is required, please request a hard-copy version.

Additional information available upon request.

NIPlc and other Nomura Group entities manage conflicts identified through the following: their Chinese Wall, confidentiality and independence policies, maintenance of a Stop List and a Watch List, personal account dealing rules, policies and procedures for managing conflicts of interest arising from the allocation and pricing of securities and impartial investment research and disclosure to clients via client documentation.

Disclosure information is available at the Nomura Disclosure web page:

http://www.nomura.com/research

35Joseph Mezrich, 212.667.9316, [email protected]

U.S. Quantitative Research