Docstoc

GTC

Document Sample
GTC Powered By Docstoc
					Golden Toque Capital
Carrington Bradley, Patrick Kane, Peter Rudnick, Dennis Wu




Assignment 01 – Screening Based Stock Selection,
            Industry Comparisons
                         Professor Campbell R. Harvey




                               Page 1 / 17
         Golden Toque Capital
         Carrington Bradley, Patrick Kane, Peter Rudnick, Dennis Wu



                                           Table of Contents
1.    Objective ............................................................................................................ 4
2.    Market Selection.................................................................................................. 4
3.    Industry Selection ............................................................................................... 4
4.    Time Period ........................................................................................................ 5
5.    Factor Selection .................................................................................................. 5
 Factor 1: One month price momentum ....................................................................... 5
 Factor 2: Three month price momentum .................................................................... 5
 Factor 3: Dividend yield ........................................................................................... 6
 Factor 4: Rate of reinvestment .................................................................................. 6
 Factor 5: Consensus forecast earnings estimate revision ratio ....................................... 6
 Factor 6: Change in consensus FY1 estimates ............................................................. 6
 Factor 7: Operating cash flow / Sales ......................................................................... 6
 Factor 8: Interest coverage (EBIT / Annual interest expense) ....................................... 7
6.    Findings ............................................................................................................. 7
 Industry: Oil and gas extraction (SIC code = 13xx) ..................................................... 7
 Industry: Food and tobacco products (SIC code = 20xx + 21xx) ................................... 8
 Industry: Electronic & other electric equipment (SIC code = 36xx) ................................ 9
 Industry: Communication (SIC code = 48xx) ............................................................ 10
 Industry: Depository institutions (SIC code = 60xx) .................................................. 11
 US Common Stocks ............................................................................................... 12
7.    Analysis ........................................................................................................... 12
8.    Bi-variate Screens ............................................................................................. 12
 Industry: Oil and gas extraction (SIC code = 13xx) ................................................... 13
 Industry: Depository institutions (SIC code = 60xx) .................................................. 14
9.    Optimizing Weights ............................................................................................ 15
 Industry: Oil and gas extraction (SIC code = 13xx) ................................................... 15
 Industry: Depository institutions (SIC code = 60xx) .................................................. 15
10.      Closing Thoughts............................................................................................ 16
11.      Appendix A .................................................................................................... 17
12.      Appendix B .................................................................................................... 17
 Mutual Fund Evaluation .......................................................................................... 17
 Asian Markets Evaluation ........................................................................................ 17



                                                  Page 2 / 17
Golden Toque Capital
Carrington Bradley, Patrick Kane, Peter Rudnick, Dennis Wu




                               Page 3 / 17
       Golden Toque Capital
       Carrington Bradley, Patrick Kane, Peter Rudnick, Dennis Wu




   1. Objective
The main goal of our project is to explore and extend the findings from the “Stock Selection
in Emerging Markets: Portfolio Strategies for Malaysia, Mexico and South Africa” (Harvey, et
al.) into another area of interest. This idea was prompted by the recent availability of
FactSet as a learning tool and the potential practical applications resulting. After a number
of iterations, we found great interest in exploring applications segmented by industries
within the US market, and the potential to optimize on these constraints.


   2. Market Selection
In selecting a different area to explore based on discussions, we considered the mutual fund
industry and other Asian countries beyond Malaysia. On the basis of data availability during
initial trial, we opted for the more data-rich US market. An elaboration on why we thought
these would be good projects is included in Appendix B, and perhaps worthy of another look
given access to more information.
The refinement of our market selection was also very much influenced by the screening
factors we chose, which will be explained in detail below. Specifically, we had found that the
eight factors we chose produced very little tradable spreads in a US common stock universe
within the historic in-sample time frame of 1990.01 – 2000.12.
In our discussion as to why these would vary in substance to the three countries considered
in the paper, we hypothesized that perhaps the less developed nature of these countries
were more dependent on some core industries, and that perhaps the US market does
achieve noticeable spreads if we consider individual industries instead of the market as a
whole, which is significantly more diversified. In addition, we saw value in exploring whether
certain screening factors were industry specific, and how that would relate to the market as
a whole.


   3. Industry Selection
To standardize our selection of industries, we decided to base our study on Standard
Industrial Classification (SIC) codes. This was reinforced by the fact that FactSet provides
for the creation of universes by these codes. We evaluated each code based on a subjective
assessment of the industry relevance to our study, as well as a dataset minimum of 100
companies. The minimum was set to allow us the ability to look for meaningful patterns
within each industry without being adversely skewed by a disproportionate number of “N/A”
listings for our factors.
The industries selected are listed below:
Code              Industry                                          Dataset size (Companies)
13xx              Oil and gas extraction                            199
20xx + 21xx       Food & kindred and tobacco products               128
36xx              Electronic & other electric equipment             506
48xx              Communication                                     245
60xx              Depository institutions                           766


                                      Page 4 / 17
       Golden Toque Capital
       Carrington Bradley, Patrick Kane, Peter Rudnick, Dennis Wu


We recognize that both the companies listed within the SIC codes and the companies
themselves can change over time. However, as new companies emerge and others falter,
we believe this was a reasonable universe since the overall selection was still a
representation of the particular industry. Some companies may change their main business
over time as well by entering new markets or exiting their primary market. We felt that this
impact would be minor overall.


   4. Time Period
The aim was to balance the time period selected with the time it would take FactSet to run
the factor screens. We decided on an 11 year period (1990.01 – 2000.12) as our in-sample
run. The desire was to include a small measure of the recent recession to balance the
exceptional run in the US market in the 1990s. This left 2001.01 – 2003.12 for our out-of-
sample comparisons. Although this is a relatively short out-of-sample period, we believe
that the results will allow us to gain insight into whether these factors are still relevant for
our chosen industries. In hindsight, although the 11 year period provided a great data
screen, it proved cumbersome to run. Most runs took between 20 to 45 minutes to complete.


   5. Factor Selection
When picking screening factors we considered three criteria. First, we chose factors that had
plenty of data available. Second, we chose at least two momentum, fundamental, and
expectation factors. Third, we chose factors that performed well when used in predictive
regression models. Note that in our analysis, we refer back to this as reference and
generally refer to our factors by their designation number. Our eight main variables are:


       Factor 1: One month price momentum
Data source: COMPUSTAT
Formula: G_PRICE_1MCHG
Reasoning: We chose one month momentum because we wanted to see if the contrarian
nature of this factor held true over a range of industries. Additionally, momentum factors
have performed well in past predictive regressions.


       Factor 2: Three month price momentum
Data source: COMPUSTAT
Formula: G_PRICE_3MCGH
Reasoning: The three month momentum variable provides a nice comparison for the one
month momentum results. We suspected that the one month momentum factor would lead
to a superior long/short spread since that data set contained more information than the
three month data. Additionally, momentum factors have performed well in past predictive
regressions.




                                      Page 5 / 17
       Golden Toque Capital
       Carrington Bradley, Patrick Kane, Peter Rudnick, Dennis Wu



       Factor 3: Dividend yield
Data source: COMPUSTAT
Formula: G_DIV_YLD(NR 0 L45D)
Reasoning: Strong dividend yields and dividend growth are consistently solid indicators of
healthy companies.


       Factor 4: Rate of reinvestment
Data source: COMPUSTAT
Formula: G_REINV_RATE(NR 0 L45D)
Reasoning: We believe this variable will capture the upside performance of the large, non-
dividend paying firms. This variable also describes the general health of a firm. Firms with
surplus cash and long term growth prospects tend to have greater reinvestment.


       Factor 5: Consensus forecast earnings estimate revision ratio
Data source: COMPUSTAT
Formula: (IH_UP_FY1R(0)-IH_DOWN_FY1R(0))/IC_NEST_FY1R(0)
Reasoning: We are interested in factors that incorporated a change in values. We guess that
firms with a greater number of upward (downward) revisions will over (under) perform.


       Factor 6: Change in consensus FY1 estimates
Data source: COMPUSTAT
Formula: G_IH_MEAN_FYIR_3MCHG(0)
Reasoning: Again, we are interested in factors that incorporated a change in values. We
guess that firms with greater per cent changes in earning estimates will benefit (suffer)
from the effect of good (bad) news on the market


       Factor 7: Operating cash flow / Sales
Data source: COMPUSTAT
Formula: G_CASH_FLOW(NR 0 L45D)/G_SALES(NR 0 L45D)
Reasoning: An interesting valuation ratio. We guess that companies with higher quality of
sales will have superior returns.




                                      Page 6 / 17
        Golden Toque Capital
        Carrington Bradley, Patrick Kane, Peter Rudnick, Dennis Wu



        Factor 8: Interest coverage (EBIT / Annual interest expense)
Data source: COMPUSTAT
Formula: G_INT_COV(NR 0 L45D)
Reasoning: An interesting valuation ratio. We looked for a variable that captured the idea of
leverage. We guess that a firm with a lower coverage ratio will have lower returns since a
larger portion of its capital is going towards interest commitments.


   6. Findings
Upon evaluating our FactSet results (see MS Excel file A1_GTC.xls), we determined to focus
on a few key factors and industries. Specific discussions are below. Note that some of the
findings were difficult to rationalize.


        Industry: Oil and gas extraction (SIC code = 13xx)
Factor 1                      1        2        3        4           5      L-S       Benchmark
Fractile returns            1.84%    8.50%   10.37%   19.93%   31.34%       -29.51%      16.30%
Std Dev                    31.97%   28.83%   31.34%   31.27%   37.41%        24.07%      13.68%
Avg Relative Performance     3.00     2.50     2.75     2.00         1.63


Factor 2                      1        2        3        4           5      L-S       Benchmark
Fractile returns            3.32%    7.74%   14.82%   17.58%   21.98%       -18.67%      16.30%
Std Dev                    35.53%   31.90%   29.12%   33.55%   37.27%        26.45%      13.68%
Avg Relative Performance     3.06     2.56     2.19     2.25         1.81


Factor 3                      1        2        3        4           5      L-S       Benchmark
Fractile returns           12.86%   15.60%   18.35%   33.33%   11.44%         1.42%      16.30%
Std Dev                    25.51%   33.32%   38.75%   63.94%   35.72%        16.11%      13.68%
Avg Relative Performance     2.38     2.44     2.19     2.44         2.44


Factor 4                      1        2        3        4           5      L-S       Benchmark
Fractile returns           22.03%   18.76%   13.23%    4.92%    1.82%        20.21%      16.30%
Std Dev                    34.81%   28.46%   26.94%   30.86%   37.79%        26.52%      13.68%
Avg Relative Performance     1.63     2.06     2.31     2.94         2.94


Factor 5                      1        2        3        4           5      L-S       Benchmark
Fractile returns           13.73%   18.24%   16.04%    9.26%   11.76%         1.97%      16.30%
Std Dev                    30.89%   28.08%   31.31%   30.55%   30.40%        21.51%      13.68%
Avg Relative Performance     2.38     2.19     2.44     2.44         2.44


Factor 6                      1        2        3        4           5      L-S       Benchmark
Fractile returns           13.73%   18.24%   16.04%    9.26%   11.76%         1.97%      16.30%
Std Dev                    30.89%   28.08%   31.31%   30.55%   30.40%        21.51%      13.68%
Avg Relative Performance     2.38     2.19     2.44     2.44         2.44




                                       Page 7 / 17
        Golden Toque Capital
        Carrington Bradley, Patrick Kane, Peter Rudnick, Dennis Wu


It appears that one month momentum is an attractive factor for a long/short strategy. The
results are flipped however, as the strategy should change to one of going long on the
bottom fractile and shorting the top fractile. One thought is that during the mid to late
1990’s, energy stocks enjoyed (at least on the upside) treatment very similar to technology
stocks. Specifically, companies such as Enron and Dynegy seemed to take the world by
storm with their impressive financial performance and unconventional styles. As a result,
their stocks were more volatile than comparable stocks (the table also shows relatively high
standard deviations of the returns) and that periods of relative calm (low momentum) were
followed by bursts. What is surprising however is that this factor looks good for energy yet
is not so for the communications or technology SIC codes. Perhaps the additional volatility
of the crude oil market creates an additional opportunity within this sector.
Reinvestment rate also showed some promise in this sector. Typically, we assume that a
high reinvestment rate is a favorable sign of future growth. As noted above, we feel that
this may have reflected a sentiment that high fliers had tremendous potential in this sector
compared to the relatively stodgy blue-chippers such as Mobil and Exxon that paid out
dividends regularly. This factor also showed some life with electronics for perhaps the same
reason, but telecom was not as strong.
When run using out of sample data, the momentum component lost luster while the
reinvestment element produces very impressive results. The out of sample data are few,
but this finding does give generate some concern over the usefulness of our first factor for
this sector.


        Industry: Food and tobacco products (SIC code = 20xx + 21xx)
Factor 1                      1        2        3        4           5      L-S       Benchmark
Fractile returns           18.02%   17.06%   18.77%   18.80%    16.35%        1.67%      16.30%
Std Dev                    20.69%   13.72%   14.01%   18.80%    24.68%       20.67%      13.68%
Avg Relative Performance     2.44     2.63     2.00      2.06        2.75


Factor 2                      1        2        3        4           5      L-S       Benchmark
Fractile returns            3.69%   17.86%   15.76%   21.80%    28.91%      -25.22%      16.30%
Std Dev                    23.38%   16.87%   18.54%   18.92%    25.09%       23.08%      13.68%
Avg Relative Performance     3.38     2.38     2.50      2.13        1.50


Factor 3                      1        2        3        4           5      L-S       Benchmark
Fractile returns           18.93%   15.23%    9.59%   12.29%    13.22%        5.71%      16.30%
Std Dev                    20.96%   19.11%   19.86%   30.19%    25.34%       21.27%      13.68%
Avg Relative Performance     1.88     2.19     2.63      2.63        2.56


Three month momentum appears to play a factor in this particular sector. Again, the long
position on the bottom fractile offset by shorting the top fractile creates the desired return.
This is probably the most surprising finding given the fact that many of these companies are
relatively low-growth CPG concerns. We believe that there might be two items in play here
however. The first is the drubbing that tobacco firms took in the 1990’s in the form of their
public relations nightmare, class action and state’s lawsuits and the introduction of smaller
firms unburdened by large settlements. This may have led investors to look for battered
firms (low 3 month returns) that later generated large returns. Likewise, firms that were
flying high for a period may have enjoyed a little “irrational exuberance,” making them


                                       Page 8 / 17
        Golden Toque Capital
        Carrington Bradley, Patrick Kane, Peter Rudnick, Dennis Wu


prime candidates for a price drop. The second is that this SIC code has the smallest number
of firms that we evaluated. Therefore, large swings by one or two large cap firms may have
influenced our results more than anticipated.


        Industry: Electronic & other electric equipment (SIC code = 36xx)
Factor 1                      1        2        3        4           5      L-S       Benchmark
Fractile returns           32.46%   21.03%   33.84%   20.04%    37.40%       -4.94%      16.30%
Std Dev                    39.85%   28.39%   33.82%   35.33%    36.79%       28.92%      13.68%
Avg Relative Performance     2.50     2.63     1.88      2.75        2.13


Factor 2                      1        2        3        4           5      L-S       Benchmark
Fractile returns           35.48%   31.55%   20.85%   29.69%    28.87%        6.61%      16.30%
Std Dev                    38.02%   32.63%   31.93%   32.32%    38.80%       31.05%      13.68%
Avg Relative Performance     2.13     2.19     2.63      2.44        2.50


Factor 3                      1        2        3        4           5      L-S       Benchmark
Fractile returns           26.77%   23.81%   30.45%   29.79%    33.02%       -6.26%      16.30%
Std Dev                    27.06%   39.75%   36.01%   40.71%    36.98%       19.76%      13.68%
Avg Relative Performance     2.13     2.75     2.50      2.38        2.13


Factor 4                      1        2        3        4           5      L-S       Benchmark
Fractile returns           37.00%   22.42%   21.72%   31.52%    16.78%       20.21%      16.30%
Std Dev                    34.97%   26.69%   31.03%   38.08%    42.56%       31.01%      13.68%
Avg Relative Performance     1.69     2.56     2.56      2.19        2.88


Factor 5                      1        2        3        4           5      L-S       Benchmark
Fractile returns           32.20%   31.40%   13.00%   19.31%    26.02%        6.17%      16.30%
Std Dev                    35.78%   32.76%   31.69%   34.14%    28.07%       24.87%      13.68%
Avg Relative Performance     1.81     2.06     2.81      2.75        2.44


Factor 6                      1        2        3        4           5      L-S       Benchmark
Fractile returns           31.18%   31.55%   21.25%   24.58%    31.01%        0.17%      16.30%
Std Dev                    39.64%   32.97%   25.25%   27.19%    35.77%       25.06%      13.68%
Avg Relative Performance     2.50     1.94     2.38      2.50        2.56


The only factor that gave a hint of hope was the reinvestment factor. As noted in our energy
discussion, we believe that this factor is a proxy for growth as companies with high growth
potential prefer to reinvest earnings rather than pay them out as dividends. As IT grew at
enormous clips during the 90’s it is reasonable to believe that the electronics firms pursued
this strategy and reaped the rewards in returns. Therefore, this factor seems to be
explained fairly well within industry. What will be interesting to learn is whether this factor
continues to be important during the 2000’s.




                                       Page 9 / 17
        Golden Toque Capital
        Carrington Bradley, Patrick Kane, Peter Rudnick, Dennis Wu



        Industry: Communication (SIC code = 48xx)
Factor 1                      1        2        3        4           5      L-S       Benchmark
Fractile returns           16.30%    9.95%   10.62%   18.29%    31.63%      -15.33%      16.30%
Std Dev                    25.93%   20.03%   24.36%   26.25%    47.16%       39.31%      13.68%
Avg Relative Performance     2.38     2.63     2.63      2.25        2.00


Factor 2                      1        2        3        4           5      L-S       Benchmark
Fractile returns           12.67%   18.91%   10.50%   24.59%    41.72%      -29.06%      16.30%
Std Dev                    27.78%   19.72%   24.91%   28.27%    50.83%       42.93%      13.68%
Avg Relative Performance     3.06     2.19     2.75      2.31        1.56


Factor 3                      1        2        3        4           5      L-S       Benchmark
Fractile returns           14.79%   18.41%   10.22%   20.14%    24.78%       -9.99%      16.30%
Std Dev                    16.67%   23.02%   31.88%   36.74%    36.22%       28.31%      13.68%
Avg Relative Performance     2.13     2.50     2.88      2.25        2.13


Factor 4                      1        2        3        4           5      L-S       Benchmark
Fractile returns           19.39%   13.45%   14.99%   22.54%    14.36%        5.04%      16.30%
Std Dev                    21.14%   20.25%   27.96%   36.16%    44.04%       34.47%      13.68%
Avg Relative Performance     1.88     2.31     2.56      2.38        2.75


Factor 5                      1        2        3        4           5      L-S       Benchmark
Fractile returns           19.45%   16.76%   14.62%   17.68%    15.92%        3.53%      16.30%
Std Dev                    24.33%   20.85%   18.87%   25.54%    26.30%       26.71%      13.68%
Avg Relative Performance     2.31     2.38     2.50      2.31        2.38


Factor 6                      1        2        3        4           5      L-S       Benchmark
Fractile returns           19.45%   16.76%   14.62%   17.68%    15.92%        3.53%      16.30%
Std Dev                    24.33%   20.85%   18.87%   25.54%    26.30%       26.71%      13.68%
Avg Relative Performance     2.31     2.38     2.50      2.31        2.38


As with food & tobacco, the telecom industry did respond to the 3 month momentum factor.
This is not entirely surprising given the discussion noted above in energy. What inspires
greater discussion however is why the 3 month momentum piece is effective for food &
tobacco and telecom, while energy showed life in both the 1 and 3 month momentum
swings (although to a lesser extent in 3 month). An examination of the levels of volatility
within each sector may give us some insight. The energy sector exhibits much higher
volatility in both 1 and 3 month momentum measurements than do food & tobacco and
telecom. Perhaps this extra volatility makes quicker strategies (1 month momentum)
effective, with effects lasting as long as 3 months. However, our next industry casts that
theory into some doubt.




                                       Page 10 / 17
        Golden Toque Capital
        Carrington Bradley, Patrick Kane, Peter Rudnick, Dennis Wu



        Industry: Depository institutions (SIC code = 60xx)
Factor 1                      1        2        3        4           5      L-S       Benchmark
Fractile returns            5.09%   21.22%   19.55%   29.70%   39.03%       -33.94%      16.30%
Std Dev                    20.40%   20.27%   21.42%   23.68%   22.48%        12.97%      13.68%
Avg Relative Performance     3.63     2.56     2.63     1.94         1.13


Factor 2                      1        2        3        4           5      L-S       Benchmark
Fractile returns            6.55%   18.08%   19.50%   21.38%   35.98%       -29.42%      16.30%
Std Dev                    21.17%   19.60%   20.59%   22.73%   26.07%        17.29%      13.68%
Avg Relative Performance     3.38     2.44     2.44     2.25         1.38


Factor 3                      1        2        3        4           5      L-S       Benchmark
Fractile returns           32.95%   22.54%   16.49%   13.45%   17.90%        15.05%      16.30%
Std Dev                    23.20%   23.69%   22.44%   20.91%   23.22%        13.28%      13.68%
Avg Relative Performance     1.25     2.13     2.69     3.06         2.75


Factor 4                      1        2        3        4           5      L-S       Benchmark
Fractile returns           22.95%   18.25%   19.15%   15.67%   19.16%         3.79%      16.30%
Std Dev                    23.28%   22.03%   21.24%   21.09%   23.23%        15.01%      13.68%
Avg Relative Performance     1.94     2.69     2.31     2.81         2.13


Factor 5                      1        2        3        4           5      L-S       Benchmark
Fractile returns           27.44%   20.05%   22.96%   19.52%   13.65%        13.79%      16.30%
Std Dev                    21.80%   20.04%   19.75%   23.07%   25.00%        12.34%      13.68%
Avg Relative Performance     1.88     2.19     2.00     2.56         3.25


Factor 6                      1        2        3        4           5      L-S       Benchmark
Fractile returns           24.00%   29.16%   17.79%   16.73%   18.76%         5.24%      16.30%
Std Dev                    22.86%   22.65%   22.57%   23.00%   25.85%        13.62%      13.68%
Avg Relative Performance     2.13     1.81     2.44     2.94         2.56


The banking sector showed a promising stretch for both 1 and 3 month momentum factors.
Again, going long on the bottom fractile and shorting the top brings great returns. It is not
entirely clear why this happened for the staid banking industry. We postulate that constant
consolidation may cause some pretty generous spreads, while large banking fees in the mid
to late 1990s may have also contributed to momentum swings. The consensus forecast
revision ratio also showed some promise, but the returns were very similar for long/short
hedge to the S&P 500.
Upon running out of sample data, the 3 month momentum factor also diminishes in
importance. We wonder whether this is a reflection of markets reacting quicker to
information (becoming more efficient in some ways) as a 3 month reaction period is simply
too slow, even for the less volatile banking sector.




                                       Page 11 / 17
       Golden Toque Capital
       Carrington Bradley, Patrick Kane, Peter Rudnick, Dennis Wu



       US Common Stocks
For a comparison reference, we ran these same factors for a universe of all US based
common stocks. While the dividend yield, forecast revision ratio and change in consensus FY
estimates showed good returns, they did not beat the S&P during that period of time. This
brings us to an important part of our evaluation.


   7. Analysis
                 Factor    Factor   Factor    Factor    Factor      Factor   Factor   Factor
SIC codes          1         2        3         4         5           6        7        8
13xx              good                         good
36xx
48xx
60xx              good      good
20xx + 21xx                 good


On the surface, it would appear that these factors are not effective in setting up a
long/short hedge fund upon examining the output for US common stocks. However, when
we dig a little deeper into sectors, it appears that some of these factors may be important
for certain types of businesses. This leads us to believe that there are still promising
searches within sectors, geographies or other assets that may offer solid returns.
We also have some misgivings about these findings however. To get those high returns
within a sector, the investor often has to take on much more risk. We believe that this a
reflection of the much smaller pool of companies within each SIC code. While this might
reduce the overall level of transactions costs, the volatility may not justify the larger returns.
Thus, we will continue our pursuit of higher returns with reduced volatility …


   8. Bi-variate Screens
Of the two industries where we found multiple interesting factors – Oil and gas extraction
(SIC code 13xx) and Depository institutions (SIC code 60xx) – we were intrigued by how
the factors would interplay. By using the FactSet bi-variate functionality, we were able to
generate sorting for each industry, and group them independently.




                                      Page 12 / 17
       Golden Toque Capital
       Carrington Bradley, Patrick Kane, Peter Rudnick, Dennis Wu


       Industry: Oil and gas extraction (SIC code = 13xx)



                                 4.00



                                 3.00


                                 2.00
         Value Weighted Return




                                 1.00


                                  0.00


                                 -1.00

                                                                                                    -5-
                                 -2.00
                                                                                                  -4-
                                                                                              -3-
                                 -3.00
                                                                                           -2-
                                         -1-
                                                    -2-                                 -1-
                                                                -3-
                                                                          -4-         Reinvestment Rate
                                               One Month Price Momentum         -5-


While there is no interaction between the two factors based on the FactSet bi-variate
independence postulate, it appears that by letting the one month price momentum factor
subdivide the original bucket formation on reinvestment rate, we lose coherence originally
found in the single variate sorting. This is a case where the aggregate of each bucket per
one factor provides more information in a predictive sense than in finer granularization. This
is true vice versa as well. So while we may still be able to trade off a spread by taking the
bucket-to-bucket corners, this will more than likely prove inconsistent across time.




                                                              Page 13 / 17
       Golden Toque Capital
       Carrington Bradley, Patrick Kane, Peter Rudnick, Dennis Wu


       Industry: Depository institutions (SIC code = 60xx)



                                  3.00



                                  2.50



                                  2.00
          Value Weighted Return




                                   1.50



                                   1.00



                                   0.50


                                                                                                             -5-
                                    0.00
                                                                                                       -4-

                                                                                                    -3- Three Month Price
                                   -0.50                                                                      Momentum
                                                                                              -2-
                                           -1-
                                                      -2-                               -1-
                                                                  -3-
                                                                            -4-
                                                 One Month Price Momentum         -5-



This bi-variate run on the banks provide a more workable learning experience. We recognize
that the two factors chosen are closely related, being both direct momentum predictor
variables. Hence, it is natural to observe such close correlation in the smooth transition
from the bucket-to-bucket corners. Nevertheless, we found this to be instructive in that
even granting correlation, this screening method of observing two close momentum
variables yields a tradable strategy. If an institution falls into bucket 5’s for both momentum
observations, then we gain confidence in a long-short position in it and it’s peers against a
portfolio in the bucket 1’s.




                                                               Page 14 / 17
        Golden Toque Capital
        Carrington Bradley, Patrick Kane, Peter Rudnick, Dennis Wu




   9. Optimizing Weights
Our results thus far have been intriguing. While the factors we chose provided no tradable
spread for the US market, we have isolated two industries where multiple factors seem to
provide significant insight. Our bi-variate screens yielded mix results, prompting us to
experiment with subjective score assignments to reflect relative importance of these factors.
In response to a more efficient scoring system, we took the buckets found under each
industry to be portfolios we would optimize under a mean variance paradigm (see MS Excel
file A1_GTC.xls). This was how we were aiming to gain a relative sense of importance and
direction between the factors and their respective buckets.


        Industry: Oil and gas extraction (SIC code = 13xx)
              Series                  Code          Weights       E          σ           σ2
 SIC   13   Factor 1 Bucket   1   SIC_13_F1_B1       -0.1725    0.0032      0.0925      0.0086
 SIC   13   Factor 1 Bucket   5   SIC_13_F1_B5        0.3738    0.0226      0.1125      0.0127
 SIC   13   Factor 4 Bucket   1   SIC_13_F4_B1        0.8408    0.0177      0.0952      0.0091
 SIC   13   Factor 4 Bucket   5   SIC_13_F4_B5       -0.0421   -0.0008      0.1105      0.0122

                                  Portfolio           1.0000   0.0228       0.1000      0.0100

                                                    Weights      E        σUS-equity
                                  Target             1.0000                 0.1000


Our annualized return is 27.3%. With no constraints on long or short positions, we were
trying to set the portfolio σ = σUS-equity = 0.0454. However we found that the solution would
not converge under the 0.1000 standard deviation we ended up with. We speculate that this
is in large part due to the large volatility with these particular portfolios to start with. This is
rationalized by the industry itself, which is very sensitive to economic factors. We are
comforted by the duality of the weights for each of the two factors between their factors.
From our discussion of the relative bucket merits, our long/short positions are as expected.


        Industry: Depository institutions (SIC code = 60xx)
              Series                  Code          Weights      E           Σ           σ2
 SIC   60   Factor 1 Bucket   1   SIC_60_F1_B1       -0.0923   0.0037       0.0580      0.0034
 SIC   60   Factor 1 Bucket   5   SIC_60_F1_B5        0.9038   0.0293       0.0627      0.0039
 SIC   60   Factor 2 Bucket   1   SIC_60_F2_B1        0.2438   0.0053       0.0572      0.0033
 SIC   60   Factor 2 Bucket   5   SIC_60_F2_B5       -0.0554   0.0253       0.0726      0.0053

                                  Portfolio           1.0000   0.0260       0.0600      0.0036

                                                    Weights      E        σUS-equity
                                  Target             1.0000                 0.0600




                                           Page 15 / 17
       Golden Toque Capital
       Carrington Bradley, Patrick Kane, Peter Rudnick, Dennis Wu


Our annualized return is 31.2%. With no constraints on long or short positions, we were
trying to set the portfolio σ = σUS-equity = 0.0454. However we found that the solution would
not converge under the 0.0600 standard deviation we ended up with. While these four
portfolios did not exhibit as high of volatility as in the oil & gas extraction industry, it was
still significant enough to put a floor on what the resulting mean variance frontier stopped.
Again, we are comforted by the duality of the weights for each of the two factors between
their factors. From our discussion of the relative bucket merits, our long/short positions are
as expected.


   10.         Closing Thoughts
This project focused on elaborating on what we developed as a screening exercise into areas
relevant to the team. Driven to the US market due to data availability, we were quick to
explore this methodology at the industry level. This would fit well into our top-down asset
allocation from country and global asset class to a more tactical industry and firm selection
and re-weighting.
The industry level exploration was interesting to us in comparison to how our factors
performed against 1) the US market as a whole, 2) the three country equities selected in
the paper that served as the basis for our project, and 3) each other.
The uni-variate screening allowed us to isolate industry specific relevant factors, while the
bi-variate screening allowed us to take our best results and see if we could enhance the
returns. We actually found that in certain situations, we actually lose the quality of
information in going to a bi-variate screening due to how the independent factors “split” the
other factors’ buckets. We also explored the optimization of scoring through the mean
variance paradigm against a subjective scoring assignment in combining factor results.
In studying this element of asset allocation, we have been prompted with more ideas than
we had time to process. Given resources and data, we would have liked to further explore:
              The multi-variate contrast between layering and a bi-variate screening, and
               how the systematic decoupling and re-coupling method compares with the
               independent.
              The predictive scope and range of the screening methodology with a multi-
               variate regression approach in achieving alphas, and within itself through
               bucket allocation methodologies.
              The emerging markets where efficiencies and regulation may derive returns
               (and risk) beyond that available within the US markets.
Our thanks to Prof. Harvey for his insight and feedback (and laptop), as well as Kevin Stoll
for sharing a time-saving intellectual asset, without which we would have spent more time
on data processing than on exploring new ideas.




                                      Page 16 / 17
       Golden Toque Capital
       Carrington Bradley, Patrick Kane, Peter Rudnick, Dennis Wu




   11.         Appendix A
Reference files:
              A1_GTC, Appendix A.PPS
              A1_GTC, Appendix A.MP3


   12.         Appendix B

       Mutual Fund Evaluation
One of our first attempts was with the mutual fund sector. We hypothesized two main points.
One, that we could create an optimizer that would allow individuals or firms to allocate an
employees’ funds in an optimal way among a number of funds to create maximum returns
based on a certain level of volatility. The second was that there may exist screens that
would allow us to identify high performing funds among the many funds available.
The first idea was dropped because we were having some difficulty in getting to fund
performance data quickly. Our unfamiliarity with Zephyr and our inability to create a
universe of specific funds (Vanguard or Fidelity for example) in FactSet was problematic. As
a result, we decided to attempt a general screen on all mutual funds within FactSet using a
variety of factors. Although the number of funds was truly robust, we discovered another
limiting factor. One of the elements that make screening equities so entertaining is that
there are a seemingly infinite number of screening options at your disposal. Mutual funds
however don’t have earnings reports, forward earnings estimates or other interesting
metrics. Therefore, screens related to price seemed more appropriate. Rather than limit
ourselves in this manor however, we decided to take a more stimulating run with equity
screens.


       Asian Markets Evaluation
Our second project idea involved constructing a long/short trading strategy for emerging
equities markets in Asia. Our universe included approximately 14,000 equities from Korea,
Taiwan, Singapore, Thailand, and six other high growth economies. We excluded the
Japanese and Hong Kong markets, believing they were too mature. Our hypothesis was that
by rebalancing our portfolio on a monthly basis we could exploit the inefficiencies and
volatility of these markets and capture very large long/short spreads (30%-40%).
We used FactSet Alpha Tester to sort the returns based on a series of uni-variate screens.
The screening variables included size, dividends, one month momentum, and E/P ratio as
listed in the COMPUSTAT databases. The initial runs for years 1998-2002 were immediately
disappointing. Due to lack of data, all but 40-80 companies were eliminated from the
analysis. We then re-ran this analysis using the Japan and Hong Kong markets, but
achieved no better results. We decided this small number of companies did not constitute a
large enough sample and abandoned the project.




                                      Page 17 / 17

				
DOCUMENT INFO