backtestSelector: Selector of portfolio backtest results

In dppalomar/portfolioBacktest: Automated Backtesting of Portfolios over Multiple Datasets

Selector of portfolio backtest results

Description

Select the results from a portfolio backtest.

Usage

backtestSelector(
  bt,
  portfolio_index = NULL,
  portfolio_name = NULL,
  measures = NULL
)

Arguments

bt	Backtest results as produced by the function portfolioBacktest.
portfolio_index	Index number of a portfolio, e.g., 1 means to select the performance of the first portfolio recorded in bt.
portfolio_name	String name of a portfolio, e.g., "GMVP" means to select the performance of portfolio with name "GMVP" in bt. Only considered when portfolio_index is not passed.
measures	String vector to select performane measures (default is all) from "Sharpe ratio", "max drawdown", "annual return", "annual volatility", "Sterling ratio", "Omega ratio", and "ROT bps".

Value

List with the following elements:

performance	Performance measures selected by argument measures.
error	Error status (TRUE or FALSE) of portfolio over each dataset (TRUE is when the portfolio function generates an error or the maximum CPU time is exceeded).
error_message	Error messages generated by portfolio function over each dataset. Useful for debugging purposes.
cpu time	CPU usage by portfolio function over each dataset.
portfolio	Portfolio weights generated by portfolio function over each dataset.
return	Portfolio returns over each dataset.
wealth	Portfolio wealth (aka cumulative returns or cumulative P&L) over each dataset.

Author(s)

Rui Zhou and Daniel P. Palomar

Examples

library(portfolioBacktest)
data("dataset10")  # load dataset

# define your own portfolio function
EWP_portfolio <- function(dataset, ...) {
  N <- ncol(dataset$adjusted)
  return(rep(1/N, N))
}

# do backtest
bt <- portfolioBacktest(list("EWP" = EWP_portfolio), dataset10)

# extract your interested portfolio result
bt_sel <- backtestSelector(bt, portfolio_name = "EWP")
names(bt_sel)

dppalomar/portfolioBacktest documentation built on April 27, 2022, 3:27 a.m.