# Load packages

# Core
library(tidyverse)
library(tidyquant)

Goal

Visualize and compare skewness of your portfolio and its assets.

Choose your stocks.

from 2012-12-31 to 2017-12-31

1 Import stock prices

symbols <- c("WMT", "AAPL", "NFLX", "GOOGL")

prices <- tq_get(x   = symbols,
                get  = "stock,prices",
                from = "2012-12-31",
                to   = "2017-12-31")
prices
## # A tibble: 5,040 × 8
##    symbol date        open  high   low close   volume adjusted
##    <chr>  <date>     <dbl> <dbl> <dbl> <dbl>    <dbl>    <dbl>
##  1 WMT    2012-12-31  22.5  22.8  22.5  22.7 21037500     17.4
##  2 WMT    2013-01-02  23.0  23.1  22.8  23.1 31172400     17.7
##  3 WMT    2013-01-03  23.1  23.1  22.8  22.9 26730300     17.6
##  4 WMT    2013-01-04  22.9  23.1  22.8  23.0 19314000     17.7
##  5 WMT    2013-01-07  22.9  23.0  22.7  22.8 18604200     17.5
##  6 WMT    2013-01-08  22.8  23.0  22.7  22.9 17600700     17.5
##  7 WMT    2013-01-09  22.9  22.9  22.7  22.9 15165600     17.5
##  8 WMT    2013-01-10  22.9  23.0  22.6  22.8 34361400     17.5
##  9 WMT    2013-01-11  22.9  22.9  22.7  22.9 18673500     17.6
## 10 WMT    2013-01-14  22.8  22.9  22.7  22.8 16471200     17.5
## # ℹ 5,030 more rows

2 Convert prices to returns (monthly)

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: 240 × 3
##    asset date         returns
##    <chr> <date>         <dbl>
##  1 AAPL  2013-01-31 -0.156   
##  2 AAPL  2013-02-28 -0.0256  
##  3 AAPL  2013-03-28  0.00285 
##  4 AAPL  2013-04-30  0.000271
##  5 AAPL  2013-05-31  0.0222  
##  6 AAPL  2013-06-28 -0.126   
##  7 AAPL  2013-07-31  0.132   
##  8 AAPL  2013-08-30  0.0804  
##  9 AAPL  2013-09-30 -0.0217  
## 10 AAPL  2013-10-31  0.0920  
## # ℹ 230 more rows

3 Assign a weight to each asset (change the weigting scheme)

# symbols
symbols <- asset_returns_tbl %>% distinct(asset) %>% pull()
symbols
## [1] "AAPL"  "GOOGL" "NFLX"  "WMT"
# weights
weights <- c(0.35, 0.30, 0.20, 0.15)
weights
## [1] 0.35 0.30 0.20 0.15
w_tbl <- tibble(symbols, weights)
w_tbl
## # A tibble: 4 × 2
##   symbols weights
##   <chr>     <dbl>
## 1 AAPL       0.35
## 2 GOOGL      0.3 
## 3 NFLX       0.2 
## 4 WMT        0.15

4 Build a 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: 60 × 2
##    date        returns
##    <date>        <dbl>
##  1 2013-01-31  0.0849 
##  2 2013-02-28  0.0362 
##  3 2013-03-28  0.00894
##  4 2013-04-30  0.0435 
##  5 2013-05-31  0.0287 
##  6 2013-06-28 -0.0555 
##  7 2013-07-31  0.0849 
##  8 2013-08-30  0.0350 
##  9 2013-09-30  0.0216 
## 10 2013-10-31  0.0949 
## # ℹ 50 more rows

5 Compute Skewness

portfolio_skew_tidyquant_builtin_percent <- portfolio_returns_tbl %>%
    
    tq_performance(Ra              = returns,
                   performance_fun = table.Stats) %>%
    
    select(Skewness)

portfolio_skew_tidyquant_builtin_percent
## # A tibble: 1 × 1
##   Skewness
##      <dbl>
## 1   -0.474

6 Plot: Skewness Comparison

# Data transformation: calculate skewness
asset_skewness_tbl <- asset_returns_tbl %>%
    
    group_by(asset) %>%
    summarise(skew = skewness(returns)) %>%
    ungroup() %>%
    
    # Add portfolio units
    add_row(tibble(asset = "Portfolio",
                   skew  = skewness(portfolio_returns_tbl$returns)))

asset_skewness_tbl
## # A tibble: 5 × 2
##   asset        skew
##   <chr>       <dbl>
## 1 AAPL      -0.555 
## 2 GOOGL      0.867 
## 3 NFLX       0.909 
## 4 WMT        0.0723
## 5 Portfolio -0.474
# Plot skewness
asset_skewness_tbl %>%
    
    ggplot(aes(x = asset, y = skew, color = asset)) + 
    geom_point() + 
    
    ggrepel::geom_text_repel(aes(label = asset),
                 data = asset_skewness_tbl %>%
                 filter(asset == "Portfolio")) +     
                
    labs(y = "skewness")

Is any asset in your portfolio more likely to return extreme positive returns than your portfolio collectively? Discuss in terms of skewness. You may also refer to the distribution of returns you plotted in Code along 4.

Based on the skewness comparison in my scatterplot graph, both Netflix and Google are moderately right skewed but very close to being highly right skewed. Each line is a 0.25 margin and since they are both right at the top, more than halfway above a positive 0.75 skewness rate, I can only assume they are rated at about 0.9 with Netflix being slightly higher. A skewness rating of 0.5-1.0 is considered “moderate” but these 2 stocks are on the verge of returning extreme positive returns (>1.0 skewness). Compared to the portfolio as a whole, they have more frequent surges in stock price and are more likely to deliver extreme returns on a monthly basis, but that doesn’t necessarily mean they outperform the Portfolio as a whole.

The portfolio is rated at about a -0.5 skewness rating so it is considered moderately left skewed. In terms of extreme positive returns, the portfolio has a whole has a lot lower of a chance doing this but skewness isn’t the only factor that should come into play when determining whether or not to invest in this particular portfolio. Moderately left skewed investments tend to deliver small, yet steady and consistent returns while the moderately right skewed stocks, as mentioned above, typically ride on the rare surges they have to make the mean return look greater than it really is.