OSglPF: Calculate portfolio weights for Garlappi model 1.2.3

In sstoeckl/uncertaintymeasures: Functions to create uncertainty measures using turbulence

Description

Calculate portfolio weights for Garlappi model 1.2.2-1.2.3: Uncertainty about expected returns estimated jointly for all assets and subgroups thereof.

Usage

OSglPF(
  factors,
  PFs,
  s.k = 1,
  imp = FALSE,
  rolling.PF = FALSE,
  rolling.eps = FALSE,
  roll.obs.PF = 120,
  roll.obs.eps = 120,
  rf = TRUE,
  gamma = 3
)

Arguments

factors,	list of factor premia xts
PFs,	list of portfolios (xts) to calculate PU for each factor premium
s.k	optional, lookback window for current observations that are related to the long-term mean
imp	optional, should missing values be imputed? (standard: FALSE)
rolling.PF	optional, should portfolio moments be calculated based on a rolling window?
rolling.eps	optional, should uncertainty moments be calculated based on a rolling window?
roll.obs.PF	optional, rolling.PF=TRUE: Length of rolling window; rolling.PF=FALSE: Initial estimation window size
roll.obs.eps	optional, rolling.eps=TRUE: Length of rolling window; rolling.eps=FALSE: Initial estimation window size
rf	optional, should the case with or without the risk-free rate be calculated (only for one PU parameter)
gamma	optional, coefficient of risk aversion (standard = 3)

Examples

data(factors)
data(X)
data(Y)
# out-of-sample exercise
factors <- list(fact1=factors[,1],fact2=factors[,2])
PFs <- list(PF1=X,PF2=Y)
w1 <- OSglPF(factors,PFs, s.k=12, imp=FALSE, rolling.PF=FALSE, rolling.eps=FALSE, roll.obs.PF=120, roll.obs.eps=120)
plot(w1$epsilon)
plot(w1$weights)
plot(w1$sturb)
w2 <- OSglPF(factors,PFs, s.k=12, imp=FALSE, rolling.PF=TRUE, rolling.eps=TRUE, roll.obs.PF=120, roll.obs.eps=120)
plot(w2$epsilon)
plot(w2$weights)
plot(w2$sturb)
w3 <- OSglPF(factors,PFs, s.k=12, imp=FALSE, rolling.PF=FALSE, rolling.eps=TRUE, roll.obs.PF=120, roll.obs.eps=120)
plot(w3$epsilon)
plot(w3$weights)
plot(w3$sturb)

sstoeckl/uncertaintymeasures documentation built on Nov. 7, 2021, 5:20 p.m.