# Load packages
# Core
library(tidyverse)
library(tidyquant)
Visualize and examine changes in the underlying trend in the downside risk of your portfolio in terms of kurtosis.
Choose your stocks.
four stocks: “BABA”, “LLY”, “JPM”, “UNH”
from 2012-12-31 to present
symbols <- c("BABA", "LLY", "JPM", "UNH")
prices <- tq_get(x = symbols,
get = "stock.prices",
from = "2012-12-31")
symbols
## [1] "BABA" "LLY" "JPM" "UNH"
prices
## # A tibble: 12,455 × 8
## symbol date open high low close volume adjusted
## <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 BABA 2014-09-19 92.7 99.7 89.9 93.9 271879400 89.2
## 2 BABA 2014-09-22 92.7 92.9 89.5 89.9 66657800 85.4
## 3 BABA 2014-09-23 88.9 90.5 86.6 87.2 39009800 82.8
## 4 BABA 2014-09-24 88.5 90.6 87.2 90.6 32088000 86.0
## 5 BABA 2014-09-25 91.1 91.5 88.5 88.9 28598000 84.4
## 6 BABA 2014-09-26 89.7 90.5 88.7 90.5 18340000 85.9
## 7 BABA 2014-09-29 89.6 89.7 88.0 88.8 25302000 84.3
## 8 BABA 2014-09-30 89 90.9 88.5 88.8 24419400 84.4
## 9 BABA 2014-10-01 88.7 88.9 86.0 86.1 24029600 81.8
## 10 BABA 2014-10-02 86.3 88.2 85.6 87.1 21469700 82.7
## # ℹ 12,445 more rows
asset_returns_tbl <- prices %>%
group_by(symbol) %>%
tq_transmute(select = adjusted,
mutate_fun = periodReturn,
period = "monthly",
type = "log") %>%
slice(-1) %>%
ungroup() %>%
set_names(c("asset", "date", "returns"))
asset_returns_tbl
## # A tibble: 595 × 3
## asset date returns
## <chr> <date> <dbl>
## 1 BABA 2014-10-31 0.104
## 2 BABA 2014-11-28 0.124
## 3 BABA 2014-12-31 -0.0715
## 4 BABA 2015-01-30 -0.154
## 5 BABA 2015-02-27 -0.0455
## 6 BABA 2015-03-31 -0.0223
## 7 BABA 2015-04-30 -0.0237
## 8 BABA 2015-05-29 0.0942
## 9 BABA 2015-06-30 -0.0822
## 10 BABA 2015-07-31 -0.0489
## # ℹ 585 more rows
# symbols
symbols <- asset_returns_tbl %>% distinct(asset) %>% pull()
symbols
## [1] "BABA" "JPM" "LLY" "UNH"
# weights
weights <- c(0.25, 0.25, 0.2, 0.3)
weights
## [1] 0.25 0.25 0.20 0.30
w_tbl <- tibble(symbols, weights)
w_tbl
## # A tibble: 4 × 2
## symbols weights
## <chr> <dbl>
## 1 BABA 0.25
## 2 JPM 0.25
## 3 LLY 0.2
## 4 UNH 0.3
# tq_portfolio()
portfolio_returns_tbl <- asset_returns_tbl %>%
tq_portfolio(assets_col = asset,
returns_col = returns,
weights = w_tbl,
rebalance_on = "months",
col_rename = "returns")
portfolio_returns_tbl
## # A tibble: 154 × 2
## date returns
## <date> <dbl>
## 1 2013-01-31 0.0409
## 2 2013-02-28 0.00544
## 3 2013-03-28 0.0216
## 4 2013-04-30 0.0185
## 5 2013-05-31 0.0337
## 6 2013-06-28 -0.00952
## 7 2013-07-31 0.0630
## 8 2013-08-30 -0.0338
## 9 2013-09-30 0.00205
## 10 2013-10-31 -0.0153
## # ℹ 144 more rows
portfolio_kurt_tidyquant_builtin_percent <- portfolio_returns_tbl %>%
tq_performance(Ra = returns,
performance_fun = table.Stats) %>%
select(Kurtosis)
portfolio_kurt_tidyquant_builtin_percent
## # A tibble: 1 × 1
## Kurtosis
## <dbl>
## 1 0.208
# Assing a value for window
window = 24
# Transform data: calculate 24 month rolling kurtosis
rolling_kurt_tbl <- portfolio_returns_tbl %>%
tq_mutate(select = returns,
mutate_fun = rollapply,
width = window,
FUN = kurtosis,
col_rename = "kurt") %>%
na.omit() %>%
select(-returns)
# Plot
rolling_kurt_tbl %>%
ggplot(aes(x = date,
y = kurt)) +
geom_line(color = "cornflowerblue") +
# Formatting
scale_y_continuous(breaks = seq(-1, 4, 0.5)) +
scale_x_date(breaks = scales::pretty_breaks(n = 7)) +
theme(plot.title = element_text(hjust = 0.5)) +
# Labeling
labs(x = NULL,
y = "Kurtosis",
title = paste0("Rolling" , window , "Month Kurtosis")) +
annotate(geom = "text",
x = as.Date("2016-07-01"),
y = 3,
size = 5,
color = "red",
label = str_glue("Downside risk skyrocketed
toward the beginning of 2017
and fell down significantly
in 2018"))
Has the downside risk of your portfolio increased or decreased over time? Explain using the plot you created. You may also refer to the skewness of the returns distribution you plotted in the previous assignment.
The down side risk has remained pretty stable except for a large spike between 2022 and 2025 on the graph. Since the spike the kurtosis has returned to pre 2022 levels.
The downside risk of the portfolio has occasionally small losses due to it having a negative skewness but a skewness with an absolute value of less than 1 meaning it is not far from normal distribution. The kurtosis of less than 3 tells us that this is only on occasion and not happening frequently.