【出版时间及名称】:2010年4月美国证券市场数量化投资策略
【作者】:德意志银行
【文件格式】:pdf
【页数】:50
【目录或简介】:
We are introducing our first factor research series, Signal Processing
Deutsche Bank Securities Inc.
Note to U.S. investors: US regulators have not approved most foreign listed stock index futures and options for US investors.
Eligible investors may be able to get exposure through over-the-counter products. Deutsche Bank does and seeks to do
business with companies covered in its research reports. Thus, investors should be aware that the firm may have a conflict of
interest that could affect the objectivity of this report. Investors should consider this report as only a single factor in making
their investment decision. DISCLOSURES AND ANALYST CERTIFICATIONS ARE LOCATED IN APPENDIX 1.MICA(P)
106/05/2009
Global Markets Research
Quantitative
Strategy
Team Contacts
Yin Luo, CFA
Strategist
(+1) 212 250-8983
yin.luo@db.com
Rochester Cahan, CFA
Strategist
(+1) 212 250 8983
rochester.cahan@db.com
Javed Jussa
Strategist
(+212) 250 8983
javed.jussa@db.com
Miguel-A Alvarez
Strategist
(+1) 212 250-8983
miguel-a.alvarez@db.com
We are launching our North American equity quantitative strategy piece. This is
the first in one of our four themes of research which we will continue publishing in
the coming weeks. In this series, we will address the issues of identifying new
alpha factors and investigating style rotation strategies. The other three series
cover portfolio construction, academic research, and our stock-selection model.
Three computationally intensive signals
The central theme of this month’s signal research is that most factors are
computationally intensive. First, we decompose traditional valuation ratios into a
trend (persistent) and a cyclical (mean-reversion) component. We not only find the
cyclical component has stronger predictive power, but also it is uncorrelated with
the underlying valuation ratios. Second, we study a few decompositions of
traditional accruals factors. A small change in the scaling factor makes a big
difference. Lastly, we find market frictions cause price delay in response to news.
Accounting delay can further be separated from non-accounting related delay.
Preview of style rotation strategies
We also provide a brief preview of our style rotation strategy. Full details will be
published in our upcoming research.
Factor performance review
In this section, we review recent factor performance, by the broad universe,
size/style breakdowns, and 10 GICS sectors.
Table of Contents
A letter to our readers....................................................................... 3
Introducing the factor research series............................................. 4
Factor backtesting methodology ..................................................... 6
Hedge portfolio........................................................................................................................6
Pearson information coefficient, i.e., IC ....................................................................................7
Spearman’s rank correlation, i.e., rank IC..................................................................................7
Risk adjusted factor and factor performance ..........................................................................12
Our approach ..........................................................................................................................12
Value factor decomposition ........................................................... 13
Previous research and what we have done differently ...........................................................13
Motivation – using IBM as an example ...................................................................................13
Model methodology................................................................................................................15
Results ...................................................................................................................................15
Composite value factors .........................................................................................................18
Future research.......................................................................................................................20
Earnings quality ............................................................................... 21
Review of traditional measures of earnings quality.................................................................21
FLOS accounting quality .........................................................................................................24
A small scale makes a big difference? ....................................................................................25
Conclusion ..............................................................................................................................28
Market frictions and price delay .................................................... 30
Preliminary delay measurement..............................................................................................30
Second-stage delay measure..................................................................................................30
Accounting delay and non-accounting delay ...........................................................................32
Preview of style rotation................................................................. 34
Factor performance, momentum or reversal? ........................................................................34
State space modeling of factor performance..........................................................................37
Factor performance review............................................................. 40
Broad US investable universe (Figure 69 and Figure 70).........................................................40
Size and style universe (Figure 71)..........................................................................................40
10 GICS sectors (Figure 72) ....................................................................................................40
Reference ......................................................................................... 45