[R-SIG-Finance] Extract Fama and French coefficients at each t point in time on one asset

[Alex Badoi]

Hello,

My name is Alex B, Financial Economics student. I am using R to write my
thesis i am in need of a bit of programming help. I have been using the
program for just over a month so i'm still not familiar with all the
functions and packages. I am trying to extract Fama and French coefficient
data to CSV for further analysis and factor portfolio formation.

I am using the package nlme with the following regression equation:

fund.xcess ~ rmrf + smb + hml + rmw + cma

What i am trying to do:
I have a time series of daily asset prices from 2009 to 2015 and i am
trying to estimate the regression coefficients at each period in time
starting with 2010 and using the last year for my first estimate such that
i have a time series of regression coefficients. The end result would
ideally be a .csv file with coefficient estimates  rmrf , smb , hml, rmw
and cma as columns and dates ranging from 2010 to 2015 as rows.

Here is what i have so far:

# Load data into R
setwd("/Users/alexbadoi/Desktop/College/Postgrad/Master/Seminar Pc/R")
ff_data = read.csv("ff5_bab_qmj.csv", header = TRUE, sep=",")
library(nlme)

# Assign Fama-French Factor Data

rmrf <- ff_data[,2]/100
rf <- ff_data[,7]/100
smb <- ff_data[,3]/100
hml <- ff_data[,4]/100
rmw <- ff_data[,5]/100
cma <- ff_data[,6]/100

#perform regression

i = nrow(ff_data)

for(i in 58){
fund <- ff_data[11,i+1]/100
fund.xcess <- fund - rf
ffgls <- gls(fund.xcess ~ rmrf + smb + hml + rmw + cma,
             correlation=corARMA(p=1, q=1), method='ML')

output <- data.frame(ffgls$coefficients)

write.table(output, file="test123.csv", sep=",", dec=".", col.names=FALSE,
append=TRUE)
print(summary(ffgls))
}


My asset returns are at [,11].
the ff5_bab_qmj.csv file contains Fama and French factor data, rf and
returns of asset a

Any help would be very much appreciated.
Thank you in advance.

	[[alternative HTML version deleted]]