fit.attribution: fit.attribution

In rogerjbos/fit.factor.models: Factor models for attribution and risk

Description

Function to calculate factor returns for portfolio attribution analysis. The code has been adapted from the factorAnalyticsAddons package (Uthaisaad, 2017).

Usage

fit.attribution(fitdata, date.var, id.var, return.var, exposure.vars,
  weight.var = NULL, rob.stats = FALSE, full.resid.cov = FALSE,
  z.score = FALSE, stdReturn = FALSE, resid.EWMA = FALSE,
  lambda = 0.9, ...)

Arguments

date.var	string name of the date column
id.var	string name of the id column
return.var	string name of the return column
weight.var	string name of the weight column
rob.stats	logical
full.resid.cov	logical
z.score	logical
resid.EWMA	logical
exposures.var	vector of string name(s) of the column(s) to use as exposures (attributes)
strReturns	logical

Value

An object with S3 class "fir.factor.models" containing:

beta a matrix of security exposures for the last time period

factor.returns a matrix of factor returns by date

residuals a list of regression residuals by date

r2 a vector of regression R-squared values

factor.cov a matrix of factor variances / covariances

resid.cov a matrix of residual variances / covariances

return.cov a matrix of return variances / covariances

resid.var a vector of residual variances

call the function call

fitdata a data.table of data to use for attribution

exposure.vars a vector of string names of factors to use for attribution

weight.var = weight.var,

date.var a string name of the column with dates

return.var a string name of the column with returns

id.var a string name of the column with IDs

id.names a vector of security names or IDs

factor.names a vector of factor names

exposures.char the name of the grouping column, if applicable

time.periods a vector of the dates

Author(s)

Roger J. Bos, [e-mail]

References

https://github.com/chindhanai/factorAnalyticsAddons

Examples

fit <- fit.attribution(fitdata = stock, date.var = 'DATE', id.var = 'TICKER', return.var = 'RETURN',
  weight.var = 'LOG.MARKETCAP', exposure.vars = c('NET.SALES','BOOK2MARKET','GICS.SECTOR'),
  rob.stats = TRUE, full.resid.cov = FALSE, z.score = FALSE,
  stdReturn = TRUE, resid.EWMA = TRUE)

rogerjbos/fit.factor.models documentation built on July 23, 2020, 3:44 p.m.