Backtests
EstefaniaUribe17 de Julio de 2015
404 Palabras (2 Páginas)285 Visitas
Backtests
Kyle Campbell, Jeff Enos, Daniel Gerlanc and David Kane
Introduction
The backtest package provides facilities for exploring
portfolio-based conjectures about financial instruments
(stocks, bonds, swaps, options, et cetera).
For example, consider a claim that stocks for which
analysts are raising their earnings estimates perform
better than stocks for which analysts are lowering estimates.
We want to examine if, on average, stocks
with raised estimates have higher future returns than
stocks with lowered estimates and whether this is
true over various time horizons and across different
categories of stocks. Colloquially, “backtest” is the
term used in finance for such tests.
Background
To demonstrate the capabilities of the backtest package
we will consider a series of examples based on a
single real-world data set. StarMine1 is a San Fransisco
research company which creates quantitative
equity models for stock selection. According to the
company:
StarMine Indicator is a 1-100 percentile ranking
of stocks that is predictive of future analyst
revisions. StarMine Indicator improves
upon basic earnings revisions models by:
• Explicitly considering management
guidance.
• Incorporating SmartEstimates,
StarMine’s superior estimates constructed
by putting more weight on the
most accurate analysts.
• Using a longer-term (forward 12-month)
forecast horizon (in addition to the current
quarter).
StarMine Indicator is positively correlated to
future stock price movements. Top-decile
stocks have annually outperformed bottomdecile
stocks by 27 percentage points over the
past ten years across all global regions.
These ranks and other attributes of stocks are in
the starmine data frame, available as part of the
backtest package.
> data(starmine)
> names(starmine)
[1] "date"
[2] "id"
[3] "symbol"
[4] "name"
[5] "country"
[6] "sector"
[7] "sec"
[8] "ind"
[9] "size"
[10] "smi"
[11] "liq"
[12] "ret.0.1.m"
[13] "ret.0.6.m"
[14] "ret.1.0.m"
[15] "ret.6.0.m"
[16] "ret.12.0.m"
[17] "mn.dollar.volume.20.d"
[18] "md.dollar.volume.120.d"
[19] "cap.usd"
[20] "cap"
[21] "sales"
[22] "net.income"
[23] "common.equity"
starmine contains selected attributes such as sector,
market capitalisation, country, and various measures
of return for a universe of approximately 6,000
securities. The data is on a monthly frequency from
January, 1995 through November, 1995. The number
of observations varies over time from a low of 4,528
in February to a high of 5,194 in November.
date count
1995-01-31 4593
1995-02-28 4528
1995-03-31 4569
1995-04-30 4708
1995-05-31 4724
1995-06-30 4748
1995-07-31 4878
1995-08-31 5092
1995-09-30 5185
1995-10-31 5109
1995-11-30 5194
The smi column contains the StarMine Indicator
score for each security and date if available. Here is
a sample of rows and columns from the data frame:
date name ret.0.1.m ret.0.6.m smi
1995-01-31 Lojack Corp 0.09 0.8 96
1995-02-28 Raymond Corp 0.05
...