Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.

Today I want to show how to use Volatility Position Sizing to improve strategy’s Risk Adjusted Performance. I will use the Average True Range (ATR) as a measure of Volatility and will increase allocation during low Volatility periods and will decrease allocation during high Volatility periods. Following are two good references that explain these strategy in detail:

First, let’s load prices for SPY and compute Buy & Hold performance using the Systematic Investor Toolbox:

###############################################################################
# Load Systematic Investor Toolbox (SIT)
# http://systematicinvestor.wordpress.com/systematic-investor-toolbox/
###############################################################################
con = gzcon(url('http://www.systematicportfolio.com/sit.gz', 'rb'))
source(con)
close(con)

#*****************************************************************
#******************************************************************
tickers = spl('SPY')

data <- new.env()
getSymbols(tickers, src = 'yahoo', from = '1970-01-01', env = data, auto.assign = T)
bt.prep(data, align='keep.all', dates='1970::')

#*****************************************************************
# Code Strategies
#******************************************************************
prices = data$prices nperiods = nrow(prices) models = list() #***************************************************************** # Buy & Hold #****************************************************************** data$weight[] = 0
data$weight[] = 1 models$buy.hold = bt.run.share(data, clean.signal=T)


Next, let’s modify Buy & Hold strategy to vary it’s allocation according to the Average True Range (ATR).

	#*****************************************************************
# Volatility Position Sizing - ATR
#******************************************************************
atr = bt.apply(data, function(x) ATR(HLC(x),20)[,'atr'])

# position size in units = ((porfolio size * % of capital to risk)/(ATR*2))
data$weight[] = NA capital = 100000 # risk 2% of capital data$weight[] = (capital * 2/100) / (2 * atr)

# make sure you are not committing more than 100%
max.allocation = capital / prices
data$weight[] = iif(data$weight > max.allocation, max.allocation,data$weight) models$buy.hold.2atr = bt.run(data, type='share', capital=capital)

#*****************************************************************
# Create Report
#******************************************************************
models = rev(models)

plotbt.custom.report.part1(models)

plotbt.custom.report.part2(models)


The Sharpe and DVR are both higher for new strategy and draw-downs are lower.

To view the complete source code for this example, please have a look at the bt.position.sizing.test() function in factor.model.test.r at github.