Stock Selection in Emerging Markets

advertisement
Global Asset Allocation and Stock Selection
Quantitative Stock Selection
Campbell R. Harvey
Duke University
National Bureau of Economic Research
Quantitative Stock Selection
1. Introduction
Research coauthored with
•
Dana Achour
•
Greg Hopkins
•
Clive Lang
Quantitative Stock Selection
1. Introduction
Issue
Two decisions are important:
• Asset Allocation (country picks)
• Asset Selection (equity picks)
Quantitative Stock Selection
1. Introduction
Issue
• Considerable research on the asset
allocation side
• Research has paid off in that many models
avoided “overvalued” Asian markets in
mid-1990s
• Many models began overweighing after the
onset of the Asia Crisis
Quantitative Stock Selection
1. Introduction
Issue
• Little research on the stock selection side.
Why?
– Sparse data on individual stocks
– Information asymmetries among local and
global investors
– Extremely high transactions costs
Quantitative Stock Selection
1. Introduction
With recent plummet in emerging markets,
stock selection is important.
If market is deemed “cheap,” (as many
asset allocation models would now suggest),
which stocks do we select?
Quantitative Stock Selection
2. Stock Selection Metrics
Ingredients for success:
• Identify stable relationships
• Attempt to model unstable relationships
• Use predictor variables that reflect the
future, not necessarily the past
• Do not overfit
• Validate in up-markets as well as down
• Tailor to country characteristics in emerging
markets
Quantitative Stock Selection
2. Stock Selection Metrics
Methodologies:
• Cross-sectional regression
• Sorting
• Hybrids
Quantitative Stock Selection
2. Stock Selection Metrics
Cross-sectional regression:
For country j, estimate:
Ri ,t  g 0  g 1 Ai ,t 1   i ,t
where
i denotes firm i;
A is a firm specific attribute (could be multiple)
g are common regression coefficients
Quantitative Stock Selection
2. Stock Selection Metrics
Cross-sectional regression:
• Used in developed market stock selection
• Problem with unstable coefficients
• Bigger problem given noisy emerging market
returns
Quantitative Stock Selection
2. Stock Selection Metrics
Sorting:
• Used in developed market stock selection
• Potentially similar in stability problems
• Can be cast in regression framework
– (a regression on ranks, or a multinomial probit
regression)
• Rank regression may have advantages given
the high variance (high noise) in emerging
equity returns
Quantitative Stock Selection
2. Stock Selection Metrics
Sorting:
• Simple methodology that provides a good
starting point to investigate stock selection
Quantitative Stock Selection
2. Stock Selection Metrics
Hybrid:
• Create portfolios based on stocks sorted by
attributes
• Use regression or optimization to weight
portfolios
• Produces a flexible, highly nonlinear way to
select stocks
Quantitative Stock Selection
3. Our methodology
Focus on three emerging markets:
• Malaysia (representative of Asia)
• Mexico (indicative of Latin America)
• South Africa (unique situation)
Quantitative Stock Selection
3. Our methodology
Specify exhaustive list of firm specific factors
• Includes many traditional factors
• Extra emphasis on expectations factors
Specific a number of diagnostic variables
• Includes factors that reflect the type of firm we
are selecting
Quantitative Stock Selection
3. Our methodology
Identify the best stocks and the worst stocks
• Do not impose the constraints of a tracking
error methodology
[Tracking error can be dealt with at a later
stage of the analysis]
Quantitative Stock Selection
3. Our methodology
Steps:
1. Specify list of factors
2. Univariate screens (in sample)
3. Bivariate diagnostic screens
4. Battery of additional diagnostics emphasizing
performance through time
5. Bivariate selection screens
Quantitative Stock Selection
3. Our methodology
Steps:
6. Optimize to form “scoring screen” (in sample)
7. Run scoring screen on out-of-sample period
8. Diagnostics on scoring screen
9. Form “buy list” and “sell lists”
10. Purge “buy list” of stocks that are identified
by predetermined set of “knock out criteria”
Quantitative Stock Selection
3. Our methodology
Steps:
11. Investigate turnover of portfolio
– various holding periods analyzed
Quantitative Stock Selection
4. Past research
Very few papers:
• Rouwenhorst (JF) looks at IFC data
• Claessens, Dasgupta and Glen (EMQ) look at
IFC data
• Fama and French (JF) look at IFC data
• Achour, Harvey, Hopkins, Lang (1998, 1999,
2000)
Quantitative Stock Selection
4. Past research
What we offer:
• No one has merged IFC, MSCI, Worldscope,
and IBES data
• First paper to look at comprehensive list of
firm attributes
• First paper to look at expectational attributes
Quantitative Stock Selection
4. Factors
Fundamental factors
• Dividend yield
• Earnings yield
• Book to price ratio
• Cash earnings to price yield
• Change in return on equity
• Revenue growth
• Rate of re-investment
• Return on equity
Quantitative Stock Selection
4. Factors
Expectational
• Change in consensus FY1 estimate - last 3
or 6 months
• Consensus FY2 to FY1 estimate change
• Consensus forecast earnings estimate
revision ratio
• 12 months prospective earnings growth rate
• 3 year prospective earnings growth rate
• 12 month prospective earnings yield
Quantitative Stock Selection
4. Factors
Momentum
• One month/ 1 year price momentum
• One year historical earnings
growth/momentum
• Three year historical earnings growth rate
Quantitative Stock Selection
4. Factors
Diagnostic
• Market capitalization
• Debt to common equity ratio
Quantitative Stock Selection
5. Diagnostics
•
•
•
•
•
•
•
Average return
Average excess return
Standard deviation
T-stat (hypothesis that excess return=0)
Beta (against benchmark index)
Alpha
R2
Quantitative Stock Selection
5. Diagnostics
•
•
•
•
•
Average capitalization
% periods > market index (hit rate)
% periods > market index in up markets
% periods > market index in down markets
Max number of consecutive benchmark
outperformances
Quantitative Stock Selection
5. Diagnostics
•
•
•
•
•
Max observed excess return
Min observed excess return
Max number of consecutive negative returns
Max number of consecutive positive returns
Year by year returns
Quantitative Stock Selection
5. Diagnostics
• Factor average for constructed portfolio
• Factor median
• Factor standard deviation
Quantitative Stock Selection
6. Summary Statistics: Malaysia Benchmark
400
350
300
250
200
150
87% drop
100
50
0
1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000
Malaysia IFC US$
Data through January 2001
Malaysia FX
Quantitative Stock Selection
6. Summary Statistics: Mexico Benchmark
1000
900
800
700
600
500
68% drop
400
300
200
100
0
1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000
Mexico IFC
Data through January 2001
Mexico FX
Quantitative Stock Selection
6. Summary Statistics: South Africa Benchmark
300
250
200
150
55% drop
100
50
0
1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000
South Africa IFC US$
Data through January 2001
South Africa FX
E
FY /P
I
D 3m
FY o
FY I 6m
1
to o
F
Re Y2
v
Ra
t io
B/
P
1 CE
m /P
o
M
o
1
yr m
M
Pr P om
op rop
3
E
12 y r D /P
m
o Ea
24 Pr rn
m op
o
E
Pr /P
op
E/
P
D
R
Re ev
in
ve
st
In RO
de
xr E
et
ur
n
D
Ca
p
D
RO
I
D
/E
1
Yr
D
E
3 arn iv
Yr
M
Ea om
rn
M
om
Quantitative Stock Selection
6. Malaysia: Factor returns
15
10
5
0
-5
-10
-15
-20
-25
-30
Top
Bottom
E
FY /P
I
D 3m
FY o
FY I 6m
1
to o
F
Re Y2
v
Ra
t io
B/
P
1 CE
m /P
o
M
o
1
yr m
M
Pr P om
op rop
3
E
12 y r D /P
m
o Ea
24 Pr rn
m op
o
E
Pr /P
op
E/
P
D
R
Re ev
in
ve
st
In RO
de
xr E
et
ur
n
D
Ca
p
D
RO
I
D
/E
1
Yr
D
E
3 arn iv
Yr
M
Ea om
rn
M
om
Quantitative Stock Selection
6. Mexico: Factor returns
35
30
25
20
15
10
5
0
-5
Top
Bottom
E
FY /P
I
D 3m
FY o
FY I 6m
1
to o
F
Re Y2
v
Ra
t io
B/
P
1 CE
m /P
o
M
o
1
yr m
M
Pr P om
op rop
3
E
12 y r D /P
m
o Ea
24 Pr rn
m op
o
E
Pr /P
op
E/
P
D
R
Re ev
in
ve
st
In RO
de
xr E
et
ur
n
D
Ca
p
D
RO
I
D
/E
1
Yr
D
E
3 arn iv
Yr
M
Ea om
rn
M
om
Quantitative Stock Selection
6. South Africa: Factor returns
30
25
20
15
10
5
0
Top
Bottom
E
FY /P
I
D 3m
FY o
FY I 6m
1
to o
F
Re Y2
v
Ra
t io
B/
P
1 CE
m /P
o
M
o
1
yr m
M
Pr P om
op rop
3
E
12 y r D /P
m
o Ea
24 Pr rn
m op
o
E
Pr /P
op
E/
P
D
R
Re ev
in
ve
st
RO
E
D
Ca
p
D
RO
I
D
/E
1
Yr
D
E
3 arn iv
Yr
M
Ea om
rn
M
om
Quantitative Stock Selection
6. Malaysia: % Periods Benchmark Outperformance
70
60
50
40
30
20
10
0
Top
Bottom
E
FY /P
I
D 3m
FY o
FY I 6m
1
to o
F
Re Y2
v
Ra
t io
B/
P
1 CE
m /P
o
M
o
1
yr m
M
Pr P om
op rop
3
E
12 y r D /P
m
o Ea
24 Pr rn
m op
o
E
Pr /P
op
E/
P
D
R
Re ev
in
ve
st
RO
E
D
Ca
p
D
RO
I
D
/E
1
Yr
D
E
3 arn iv
Yr
M
Ea om
rn
M
om
Quantitative Stock Selection
6. Mexico: % Periods Benchmark Outperformance
70
60
50
40
30
20
10
0
Top
Bottom
E
FY /P
I
D 3m
FY o
FY I 6m
1
to o
F
Re Y2
v
Ra
t io
B/
P
1 CE
m /P
o
M
o
1
yr m
M
Pr P om
op rop
3
E
12 y r D /P
m
o Ea
24 Pr rn
m op
o
E
Pr /P
op
E/
P
D
R
Re ev
in
ve
st
RO
E
D
Ca
p
D
RO
I
D
/E
1
Yr
D
E
3 arn iv
Yr
M
Ea om
rn
M
om
Quantitative Stock Selection
6. South Africa: % Periods Benchmark Outperformance
70
60
50
40
30
20
10
0
Top
Bottom
Quantitative Stock Selection
6. Malaysia: Dividend Yield Screen: Index=100 each year
250
200
150
100
50
Top
Benchmark
Bottom
19
98
19
97
19
96
19
95
19
94
19
93
19
92
19
91
19
90
19
89
0
Quantitative Stock Selection
6. Mexico: Historical Earnings Momentum Screen:
Index=100 each year
300
250
200
150
100
50
Top
Benchmark
Bottom
19
98
19
97
19
96
19
95
19
94
19
93
19
92
19
91
19
90
19
89
0
Quantitative Stock Selection
6. South Africa: Change in Consensus FY1-3 mo. Screen:
Index=100 each year
200
180
160
140
120
100
80
60
40
20
Top
Benchmark
Bottom
19
98
19
97
19
96
19
95
19
94
19
93
0
Quantitative Stock Selection
South Africa
Mexico
19
98
19
97
19
96
19
95
19
94
19
93
19
92
19
91
19
90
19
89
50
40
30
20
10
0
-10
-20
-30
-40
-50
Malaysia
6. Book to Price: Low-High Spread
Quantitative Stock Selection
South Africa
Mexico
19
98
19
97
19
96
19
95
19
94
19
93
19
92
19
91
19
90
19
89
50
40
30
20
10
0
-10
-20
-30
-40
-50
Malaysia
6. IBES Revision Ratio: Low-High Spread
Quantitative Stock Selection
South Africa
Mexico
19
98
19
97
19
96
19
95
19
94
19
93
19
92
19
91
19
90
19
89
50
40
30
20
10
0
-10
-20
-30
-40
-50
Malaysia
6. IBES 12-month Prospective Earnings Yield: L-H Spread
Quantitative Stock Selection
South Africa
Mexico
19
98
19
97
19
96
19
95
19
94
19
93
19
92
19
91
19
90
19
89
50
40
30
20
10
0
-10
-20
-30
-40
-50
Malaysia
6. One-year Momentum: Low-High Spread
Quantitative Stock Selection
South Africa
Mexico
19
98
19
97
19
96
19
95
19
94
19
93
19
92
19
91
19
90
19
89
50
40
30
20
10
0
-10
-20
-30
-40
-50
Malaysia
6. Size Effect: Low-High Spread
Quantitative Stock Selection
6. Malaysia: Scoring Screen Various Holding Periods
15
10
5
0
-5
-10
-15
Bottom
M
ar
ke
t
w/
KO
Se
m
ian
nu
al
Top
Se
m
ian
nu
al
ua
rte
rly
Q
M
on
th
ly
-20
Quantitative Stock Selection
6. Mexico: Scoring Screen Various Holding Periods
35
30
25
20
15
10
5
Bottom
ke
t
ar
M
nu
al
Se
Top
m
ian
rly
ar
te
Qu
M
on
th
ly
0
Quantitative Stock Selection
6. South Africa: Scoring Screen Various Holding Periods
20
15
10
5
0
-5
Bottom
ke
t
ar
M
nu
al
Se
Top
m
ian
rly
ar
te
Qu
M
on
th
ly
-10
Quantitative Stock Selection
6. Malaysia: Scoring Screen
% Periods Benchmark Outperformance
Bottom
w/
KO
Se
m
ian
nu
al
Top
Se
m
ian
nu
al
ua
rte
rly
Q
M
on
th
ly
100
90
80
70
60
50
40
30
20
10
0
Quantitative Stock Selection
6. Mexico: Scoring Screen
% Periods Benchmark Outperformance
Top
Bottom
Se
m
ian
nu
al
ua
rte
rly
Q
M
on
th
ly
100
90
80
70
60
50
40
30
20
10
0
Quantitative Stock Selection
6. South Africa: Scoring Screen
% Periods Benchmark Outperformance
Top
Bottom
Se
m
ian
nu
al
Q
ua
rte
rly
M
on
th
ly
100
90
80
70
60
50
40
30
20
10
0
Quantitative Stock Selection
6. Malaysia: Scoring Screen: Index=100 each year
250
200
150
100
50
Top
Bottom
19
98
19
97
19
96
19
95
19
94
19
93
19
92
19
91
19
90
19
89
0
Quantitative Stock Selection
6. Mexico: Scoring Screen: Index=100 each year
300
250
200
150
100
50
Top
Bottom
19
98
19
97
19
96
19
95
19
94
19
93
19
92
19
91
19
90
19
89
0
Quantitative Stock Selection
6. South Africa: Scoring Screen: Index=100 each year
200
180
160
140
120
100
80
60
40
20
Bottom
19
98
19
96
Top
19
97
19
95
19
94
19
93
0
Quantitative Stock Selection
6. Malaysia: Scoring Screen
IN SAMPLE
OUT OF SAMPLE
900.00
160.00
T OP
FR
800.00
CUMULATIVE RETURNS - IN SAMPLE
700.00
120.00
600.00
100.00
500.00
IFCG MALAYSIA
80.00
400.00
IBES DATA
ADDED
60.00
300.00
40.00
200.00
BOT T OM
20.00
100.00
0.00
12/31/88
0.00
12/31/89
12/31/90
12/31/91
12/31/92
12/31/93
12/31/94
12/31/95
12/31/96
12/31/97
CUMULATIVE RETURNS - OUT OF SAMPLE
140.00
Quantitative Stock Selection
6. Mexico: Scoring Screen
IN SAMPLE
OUT OF SAMPLE
2100.00
250.00
T OP
2000.00
1900.00
1700.00
200.00
CUMULATIVE RETURNS - IN SAMPLE
1600.00
1500.00
1400.00
1300.00
150.00
1200.00
IFCG MEXICO
1100.00
1000.00
900.00
100.00
800.00
700.00
600.00
500.00
BOT T OM
50.00
400.00
300.00
200.00
100.00
0.00
12/31/88
0.00
12/31/89
12/31/90
12/31/91
12/31/92
12/31/93
12/31/94
12/31/95
12/31/96
12/31/97
CUMULATIVE RETURNS - OUT OF SAMPLE
1800.00
Quantitative Stock Selection
6. South Africa: Scoring Screen
IN SAMPLE
350.00
OUT OF SAMPLE
120.00
T OP
300.00
250.00
80.00
IFCG SOUT H
AFRICA
200.00
60.00
150.00
BOT T OM
40.00
100.00
20.00
50.00
0.00
12/31/92
0.00
12/31/93
12/31/94
12/31/95
12/31/96
12/31/97
CUMULATIVE RETURNS - OUT OF SAMPLE
CUMULATIVE RETURNS - IN SAMPLE
100.00
Quantitative Stock Selection
7. Research Directions
1) Comparison of regression method and
multivariate screening process
– Panel multinomial probit models
– How do we reduce the noise in emerging market
equity returns?
Quantitative Stock Selection
7. Research Directions
2) What are the characteristics of countries that
make some factors work and other not work?
–
–
–
–
Stage of market integration process
Industrial mix
Openness of economy
Microstructure factors
Quantitative Stock Selection
7. Research Directions
3) What causes the shifting importance of factors
through time, e.g. value versus growth?
– Can the cross-section of many stock returns help
us identify when a factor is likely to work?
Quantitative Stock Selection
7. Research Directions
4) Can the country selection process be merged
with the stock selection exercise?
– Should “buy” portfolios be used in top-down
optimizations?
– Does country-specific tracking error really matter
in global asset allocation?
Quantitative Stock Selection
7. Research Directions
5) Stability and migration tracking
– Should we consider the behavior of the stock
moving from fractile to fractile?
Quantitative Stock Selection
7. Research Directions
6) Should we expand our view of risk in both the
stock selection and country selection exercises?
– Mean, variance, skewness?
– What are the driving forces of changing variance?
– What are the determinants of skewness?
Download