library(lubridate)
##
## Attaching package: 'lubridate'
## The following objects are masked from 'package:base':
##
## date, intersect, setdiff, union
library(timetk)
library(purrr)
library(quantmod)
## Loading required package: xts
## Loading required package: zoo
##
## Attaching package: 'zoo'
## The following objects are masked from 'package:base':
##
## as.Date, as.Date.numeric
## Loading required package: TTR
## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo
library(dplyr)
##
## ######################### Warning from 'xts' package ##########################
## # #
## # The dplyr lag() function breaks how base R's lag() function is supposed to #
## # work, which breaks lag(my_xts). Calls to lag(my_xts) that you type or #
## # source() into this session won't work correctly. #
## # #
## # Use stats::lag() to make sure you're not using dplyr::lag(), or you can add #
## # conflictRules('dplyr', exclude = 'lag') to your .Rprofile to stop #
## # dplyr from breaking base R's lag() function. #
## # #
## # Code in packages is not affected. It's protected by R's namespace mechanism #
## # Set `options(xts.warn_dplyr_breaks_lag = FALSE)` to suppress this warning. #
## # #
## ###############################################################################
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:xts':
##
## first, last
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(tidyr)
# Define the ETF symbols
symbols <- c("SPY", "QQQ", "EEM", "IWM", "EFA", "TLT", "IYR", "GLD")
# Download the data from Yahoo Finance
prices <- getSymbols(symbols, src = 'yahoo', from = "2010-01-01", auto.assign = TRUE, warnings = FALSE) %>%
map(~ Ad(get(.))) %>%
reduce(merge) %>%
`colnames<-`(symbols)
# Convert xts to tibble
prices_tibble <- tk_tbl(prices, rename_index = "date")
# Ensure date column is in character format, then convert to Date type
prices_tibble <- prices_tibble %>%
mutate(date = as.character(date)) %>%
mutate(date = as.Date(date))
# Calculate weekly log returns
weekly_prices <- prices_tibble %>%
group_by(week = floor_date(date, "week")) %>%
summarize(across(all_of(symbols), last))
weekly_returns <- weekly_prices %>%
mutate(across(all_of(symbols), ~ log(. / lag(.)))) %>%
drop_na()
# Calculate monthly log returns
monthly_prices <- prices_tibble %>%
group_by(month = floor_date(date, "month")) %>%
summarize(across(all_of(symbols), last))
monthly_returns <- monthly_prices %>%
mutate(across(all_of(symbols), ~ log(. / lag(.)))) %>%
drop_na()
# Convert to tibble format
monthly_returns_tibble <- as_tibble(monthly_returns)
# Rename 'month' column to 'date'
monthly_returns_tibble <- monthly_returns_tibble %>%
rename(date = month)
# Load the Fama/French data from URL
FFdata <- read.csv("https://mba.tuck.dartmouth.edu/pages/faculty/ken.french/ftp/F-F_Research_Data_Factors.CSV", skip = 3)
# Clean and format the data, handling parsing errors
FFdata <- FFdata %>%
mutate(date = parse_date_time(X, orders = "Y%m", quiet = TRUE)) %>%
filter(!is.na(date)) %>%
select(date, Mkt.RF, SMB, HML, RF)
# Convert character columns to numeric
FFdata <- FFdata %>%
mutate(across(-date, ~ as.numeric(gsub(" ", "", .))))
# Ensure date columns are present and in Date format
FFdata <- FFdata %>%
mutate(date = as.Date(date))
# Merge the ETF returns with the FF factors data
merged_data <- left_join(monthly_returns_tibble, FFdata, by = 'date')
# Check the first few rows of the merged data
head(merged_data)
## # A tibble: 6 × 13
## date SPY QQQ EEM IWM EFA TLT IYR GLD
## <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 2010-02-01 0.0307 0.0450 0.0176 0.0438 0.00266 -0.00343 0.0531 0.0322
## 2 2010-03-01 0.0591 0.0743 0.0780 0.0791 0.0619 -0.0208 0.0930 -0.00440
## 3 2010-04-01 0.0154 0.0222 -0.00166 0.0552 -0.0284 0.0327 0.0619 0.0572
## 4 2010-05-01 -0.0828 -0.0768 -0.0986 -0.0784 -0.119 0.0498 -0.0585 0.0301
## 5 2010-06-01 -0.0531 -0.0616 -0.0141 -0.0806 -0.0208 0.0564 -0.0478 0.0233
## 6 2010-07-01 0.0661 0.0701 0.104 0.0651 0.110 -0.00951 0.0899 -0.0522
## # ℹ 4 more variables: Mkt.RF <dbl>, SMB <dbl>, HML <dbl>, RF <dbl>
# Extract the relevant returns for the CAPM model
capm_returns <- merged_data %>%
filter(date >= "2010-02-01" & date <= "2015-01-31") %>%
select(-date, -Mkt.RF, -SMB, -HML, -RF)
# Compute the covariance matrix
capm_cov_matrix <- cov(capm_returns)
print(capm_cov_matrix)
## SPY QQQ EEM IWM EFA
## SPY 0.0013789594 0.0014370256 0.0017213318 0.0017634429 0.0015961644
## QQQ 0.0014370256 0.0017632675 0.0017694604 0.0018116922 0.0016582450
## EEM 0.0017213318 0.0017694604 0.0033901741 0.0023127693 0.0024955614
## IWM 0.0017634429 0.0018116922 0.0023127693 0.0026629401 0.0019648710
## EFA 0.0015961644 0.0016582450 0.0024955614 0.0019648710 0.0024254035
## TLT -0.0009663043 -0.0009584946 -0.0011821316 -0.0013080783 -0.0011039468
## IYR 0.0011816464 0.0012041830 0.0017966302 0.0015876844 0.0015471659
## GLD 0.0002043546 0.0003904134 0.0009310435 0.0005394858 0.0004417087
## TLT IYR GLD
## SPY -0.0009663043 0.0011816464 0.0002043546
## QQQ -0.0009584946 0.0012041830 0.0003904134
## EEM -0.0011821316 0.0017966302 0.0009310435
## IWM -0.0013080783 0.0015876844 0.0005394858
## EFA -0.0011039468 0.0015471659 0.0004417087
## TLT 0.0015464578 -0.0003632190 0.0001797667
## IYR -0.0003632190 0.0019945636 0.0005353346
## GLD 0.0001797667 0.0005353346 0.0029025882
# Extract the relevant returns and FF factors for the FF model
ff_returns <- merged_data %>%
filter(date >= "2010-02-01" & date <= "2015-01-31")
# Compute the residuals for each ETF by regressing on the FF factors
residuals <- ff_returns %>%
select(all_of(symbols)) %>%
map_dfc(~ residuals(lm(. ~ Mkt.RF + SMB + HML, data = ff_returns)))
# Compute the covariance matrix of the residuals
ff_cov_matrix <- cov(residuals)
print(ff_cov_matrix)
## SPY QQQ EEM IWM EFA
## SPY 3.259790e-06 3.622713e-06 1.782016e-06 8.352482e-07 1.903099e-06
## QQQ 3.622713e-06 2.067142e-04 -5.274452e-05 -1.248230e-05 -3.609868e-05
## EEM 1.782016e-06 -5.274452e-05 1.213625e-03 4.639569e-05 5.052327e-04
## IWM 8.352482e-07 -1.248230e-05 4.639569e-05 1.656405e-05 3.183268e-05
## EFA 1.903099e-06 -3.609868e-05 5.052327e-04 3.183268e-05 5.327995e-04
## TLT 8.489302e-06 -4.926105e-06 1.964387e-05 2.785538e-05 -2.700992e-05
## IYR 2.136833e-05 -1.638189e-05 3.328145e-04 5.932435e-05 2.082008e-04
## GLD -8.118253e-06 5.140271e-05 5.668748e-04 5.844046e-05 1.954875e-04
## TLT IYR GLD
## SPY 8.489302e-06 2.136833e-05 -8.118253e-06
## QQQ -4.926105e-06 -1.638189e-05 5.140271e-05
## EEM 1.964387e-05 3.328145e-04 5.668748e-04
## IWM 2.785538e-05 5.932435e-05 5.844046e-05
## EFA -2.700992e-05 2.082008e-04 1.954875e-04
## TLT 7.800182e-04 4.560228e-04 2.593823e-04
## IYR 4.560228e-04 1.008802e-03 3.079648e-04
## GLD 2.593823e-04 3.079648e-04 2.510801e-03
# Function to compute GMV portfolio weights
compute_gmv_weights <- function(cov_matrix) {
inv_cov <- solve(cov_matrix)
ones <- rep(1, nrow(inv_cov))
weights <- inv_cov %*% ones / sum(inv_cov %*% ones)
return(weights)
}
# Compute the weights
gmv_weights_capm <- compute_gmv_weights(capm_cov_matrix)
gmv_weights_ff <- compute_gmv_weights(ff_cov_matrix)
print(gmv_weights_capm)
## [,1]
## SPY 0.94117848
## QQQ -0.18088616
## EEM -0.01436836
## IWM -0.05253496
## EFA -0.01342807
## TLT 0.48106086
## IYR -0.21174232
## GLD 0.05072053
print(gmv_weights_ff)
## [,1]
## SPY 0.8300023392
## QQQ 0.0052267851
## EEM 0.0001188313
## IWM 0.1868509941
## EFA 0.0009288447
## TLT 0.0032707168
## IYR -0.0286063610
## GLD 0.0022078499