library(tidyquant)
library(tidyverse)Hint: Add group_by(symbol) at the end of the code so that calculations below will be done per stock.
# Import stock prices
from = today() - years(10)
Stocks <-
tq_get(c("AAPL", "AMZN", "MSFT"), get = "stock.prices", from = from) %>%
group_by(symbol)
Stocks
## # A tibble: 7,551 x 8
## # Groups: symbol [3]
## symbol date open high low close volume adjusted
## <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 AAPL 2010-05-06 36.3 36.9 28.5 35.2 321465200 30.5
## 2 AAPL 2010-05-07 34.8 35.2 32.2 33.7 419004600 29.2
## 3 AAPL 2010-05-10 35.8 36.4 35.5 36.3 246076600 31.5
## 4 AAPL 2010-05-11 36.0 37.1 35.8 36.6 212226700 31.8
## 5 AAPL 2010-05-12 37.0 37.6 37.0 37.4 163594900 32.5
## 6 AAPL 2010-05-13 37.6 37.9 36.6 36.9 149928100 32.0
## 7 AAPL 2010-05-14 36.5 36.6 35.6 36.3 189840700 31.5
## 8 AAPL 2010-05-17 36.4 36.6 35.4 36.3 190708700 31.5
## 9 AAPL 2010-05-18 36.7 36.9 35.8 36.1 195669600 31.3
## 10 AAPL 2010-05-19 35.6 36.1 35.0 35.5 256431700 30.8
## # … with 7,541 more rowsHint: Take the adjusted variable from Stocks, and calculate yearly returns using ***tq_transmute().
returns_yearly <-
Stocks %>%
tq_transmute(select = adjusted, mutate_fun = periodReturn, period = "yearly")
returns_yearly
## # A tibble: 33 x 3
## # Groups: symbol [3]
## symbol date yearly.returns
## <chr> <date> <dbl>
## 1 AAPL 2010-12-31 0.310
## 2 AAPL 2011-12-30 0.256
## 3 AAPL 2012-12-31 0.326
## 4 AAPL 2013-12-31 0.0807
## 5 AAPL 2014-12-31 0.406
## 6 AAPL 2015-12-31 -0.0301
## 7 AAPL 2016-12-30 0.125
## 8 AAPL 2017-12-29 0.485
## 9 AAPL 2018-12-31 -0.0539
## 10 AAPL 2019-12-31 0.890
## # … with 23 more rowsHint: Take returns_yearly and pipe it to summarise. Calculate the mean yearly returns.
returns_yearly %>%
summarise(returns_avg = mean(yearly.returns))
## # A tibble: 3 x 2
## symbol returns_avg
## <chr> <dbl>
## 1 AAPL 0.255
## 2 AMZN 0.345
## 3 MSFT 0.221Amazon has the highest expected yearly return at 0.345.
Hint: Take returns_yearly and pipe it to tidyquant::tq_performance. Use the performance_fun argument to compute sd (standard deviation).
returns_yearly %>%
tq_performance(Ra = yearly.returns,
Rb = NULL, #Calculating downside risk
performance_fun = sd)
## # A tibble: 3 x 2
## # Groups: symbol [3]
## symbol sd.1
## <chr> <dbl>
## 1 AAPL 0.277
## 2 AMZN 0.369
## 3 MSFT 0.195Out of the three stocks Amazon is the riskiest in terms of standard deviation becuase it is higher than the other two stocks. Amazon’s SD is 0.369.
Hint: when the return distribution is not normal, the standard deviation is not an appropriate measure of risk. One can use skewness and kurtosis to detect non-normal returns. Take returns_yearly and pipe it to tidyquant::tq_performance. Use the performance_fun argument to compute skewness. Do the same for kurtosis.
returns_yearly %>%
tq_performance(Ra = yearly.returns,
Rb = NULL, #Calculating downside risk
performance_fun = skewness)
## # A tibble: 3 x 2
## # Groups: symbol [3]
## symbol skewness.1
## <chr> <dbl>
## 1 AAPL 0.971
## 2 AMZN 0.731
## 3 MSFT 0.345
returns_yearly %>%
tq_performance(Ra = yearly.returns,
Rb = NULL, #Calculating downside risk
performance_fun = kurtosis)
## # A tibble: 3 x 2
## # Groups: symbol [3]
## symbol kurtosis.1
## <chr> <dbl>
## 1 AAPL 0.462
## 2 AMZN 0.649
## 3 MSFT -0.804Standard deviation is not an appropriate way to measure stocks.
Hint: Take returns_yearly and pipe it to tidyquant::tq_performance. Use the performance_fun argument to compute table.DownsideRisk. Fully interpret downside risk measures in at least 100 words.
returns_yearly %>%
tq_performance(Ra = yearly.returns,
Rb = NULL, #Calculating downside risk
performance_fun = table.DownsideRisk) %>%
t()
## [,1] [,2] [,3]
## symbol "AAPL" "AMZN" "MSFT"
## DownsideDeviation(0%) "0.0186" "0.0679" "0.0151"
## DownsideDeviation(MAR=0.833333333333333%) "0.0221" "0.0708" "0.0185"
## DownsideDeviation(Rf=0%) "0.0186" "0.0679" "0.0151"
## GainDeviation "0.2625" "0.3150" "0.1663"
## HistoricalES(95%) "-0.0539" "-0.2218" "-0.0452"
## HistoricalVaR(95%) "-0.0420" "-0.1301" "-0.0333"
## LossDeviation "0.0168" "0.1297" "0.0168"
## MaximumDrawdown "0.0539" "0.2218" "0.0656"
## ModifiedES(95%) "-0.1977" "-0.2510" "-0.1106"
## ModifiedVaR(95%) "-0.0991" "-0.1527" "-0.0690"
## SemiDeviation "0.1601" "0.2232" "0.1228"Amazon demonstrates the greatest risk. Nasdaq’s highest VaR is recorded at -0.13. Amazon’s historical ES is -0.22, which is significanlty higher than the other two stocks. This represents a much higher chance of risk.
Hint: Make your argument based on the three Sharpe Ratios. Fully interpret Sharpe Ratios in at least 100 words.
returns_yearly %>%
tq_performance(Ra = yearly.returns,
Rb = NULL,
performance_fun = SharpeRatio,
Rf = 0.03)
## # A tibble: 3 x 4
## # Groups: symbol [3]
## symbol `ESSharpe(Rf=3%,p=95%… `StdDevSharpe(Rf=3%,p=95… `VaRSharpe(Rf=3%,p=95…
## <chr> <dbl> <dbl> <dbl>
## 1 AAPL 1.14 0.813 2.27
## 2 AMZN 1.25 0.853 2.06
## 3 MSFT 1.72 0.979 2.76Based off of the chart showing the numbers above. I would chose to invest my money in Microsoft.
Hint: Make your argument based on the three Sharpe Ratios. Fully interpret Sharpe Ratios in at least 100 words.
returns_yearly %>%
tq_performance(Ra = yearly.returns,
Rb = NULL,
performance_fun = SharpeRatio,
p = 0.99, Rf = 0.03)
## # A tibble: 3 x 4
## # Groups: symbol [3]
## symbol `ESSharpe(Rf=3%,p=99%… `StdDevSharpe(Rf=3%,p=99… `VaRSharpe(Rf=3%,p=99…
## <chr> <dbl> <dbl> <dbl>
## 1 AAPL 0.225 0.813 2.14
## 2 AMZN 0.831 0.853 1.18
## 3 MSFT 0.458 0.979 1.58Yes, this changes my answer because now I would rather invest my money in Amazon.
Hint: Use message, echo and results in the chunk options. Refer to the RMarkdown Reference Guide.