Does stock market lead the economy?
Daniel Lee
10/1/2019
- Q1.
stock.pricesImport Dow Jones Industrial Average and NASDAQ indexes since 1999. - Q2. Prepare the imported stock prices for merge.
- Q3
economic.dataImport real U.S. GDP growth since 2000. - Q4. Prepare the imported economic data for merge.
- Q5. Merge the two data sets.
- Q6. Plot the relaionship between stock returns (of both indexes) and GDP growth?
- Q7. Describe the relationship between the two stock markets and economic growth. Which of the two indexes seems to have greater inflence on the economy?
- Q8 Hide the messages, the code and its results on the webpage.
- Q9 Display the title and your name correctly at the top of the webpage.
- Q10 Use the correct slug.
# Load packages
library(tidyquant)
library(tidyverse) stock.prices
# Import NASDAQ since 2010.
stocks <- tq_get(c("AAPL","MSFT"), get = "stock.prices", from = "1999-01-01")
stocks## # A tibble: 10,448 x 8
## symbol date open high low close volume adjusted
## <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 AAPL 1999-01-04 1.50 1.51 1.43 1.47 238221200 1.29
## 2 AAPL 1999-01-05 1.50 1.57 1.48 1.55 352528400 1.35
## 3 AAPL 1999-01-06 1.58 1.58 1.46 1.49 337142400 1.30
## 4 AAPL 1999-01-07 1.51 1.61 1.50 1.61 357254800 1.40
## 5 AAPL 1999-01-08 1.66 1.67 1.57 1.61 169708000 1.40
## 6 AAPL 1999-01-11 1.63 1.65 1.60 1.64 140243600 1.43
## 7 AAPL 1999-01-12 1.65 1.67 1.58 1.65 205184000 1.44
## 8 AAPL 1999-01-13 1.53 1.69 1.51 1.66 261954000 1.45
## 9 AAPL 1999-01-14 1.62 1.64 1.47 1.48 430964800 1.29
## 10 AAPL 1999-01-15 1.49 1.50 1.43 1.48 251501600 1.29
## # … with 10,438 more rowsstock_returns <-
stocks %>%
group_by(symbol) %>%
# Calculate yearly returns
tq_transmute(select = adjusted, mutate_fun = periodReturn, period = "yearly") %>%
# Create a new variable, year
mutate(year = year(date)+1) %>%
# Drop date
select(-date)
stock_returns## # A tibble: 42 x 3
## # Groups: symbol [2]
## symbol yearly.returns year
## <chr> <dbl> <dbl>
## 1 AAPL 1.49 2000
## 2 AAPL -0.711 2001
## 3 AAPL 0.472 2002
## 4 AAPL -0.346 2003
## 5 AAPL 0.491 2004
## 6 AAPL 2.01 2005
## 7 AAPL 1.23 2006
## 8 AAPL 0.180 2007
## 9 AAPL 1.33 2008
## 10 AAPL -0.569 2009
## # … with 32 more rowseconomic.data
# Import real U.S. GDP growth since 2010.
econ <- tq_get("A191RL1A225NBEA", get = "economic.data", from = "2000-01-01")
econ## # A tibble: 19 x 2
## date price
## <date> <dbl>
## 1 2000-01-01 4.1
## 2 2001-01-01 1
## 3 2002-01-01 1.7
## 4 2003-01-01 2.9
## 5 2004-01-01 3.8
## 6 2005-01-01 3.5
## 7 2006-01-01 2.9
## 8 2007-01-01 1.9
## 9 2008-01-01 -0.1
## 10 2009-01-01 -2.5
## 11 2010-01-01 2.6
## 12 2011-01-01 1.6
## 13 2012-01-01 2.2
## 14 2013-01-01 1.8
## 15 2014-01-01 2.5
## 16 2015-01-01 2.9
## 17 2016-01-01 1.6
## 18 2017-01-01 2.4
## 19 2018-01-01 2.9econ_decimal <-
econ %>%
mutate(year = year(date), # Create a new variable, year
GDPgrowth = price/100) %>% # Convert price to decimal number
# Drop date
select(-date)
econ_decimal## # A tibble: 19 x 3
## price year GDPgrowth
## <dbl> <dbl> <dbl>
## 1 4.1 2000 0.0410
## 2 1 2001 0.01
## 3 1.7 2002 0.017
## 4 2.9 2003 0.0290
## 5 3.8 2004 0.038
## 6 3.5 2005 0.035
## 7 2.9 2006 0.0290
## 8 1.9 2007 0.019
## 9 -0.1 2008 -0.001
## 10 -2.5 2009 -0.025
## 11 2.6 2010 0.026
## 12 1.6 2011 0.016
## 13 2.2 2012 0.022
## 14 1.8 2013 0.018
## 15 2.5 2014 0.025
## 16 2.9 2015 0.0290
## 17 1.6 2016 0.016
## 18 2.4 2017 0.024
## 19 2.9 2018 0.0290Merge
# Merge the two data sets.
data_merged <-
econ_decimal %>%
left_join(stock_returns)
data_merged## # A tibble: 38 x 5
## price year GDPgrowth symbol yearly.returns
## <dbl> <dbl> <dbl> <chr> <dbl>
## 1 4.1 2000 0.0410 AAPL 1.49
## 2 4.1 2000 0.0410 MSFT 0.656
## 3 1 2001 0.01 AAPL -0.711
## 4 1 2001 0.01 MSFT -0.628
## 5 1.7 2002 0.017 AAPL 0.472
## 6 1.7 2002 0.017 MSFT 0.527
## 7 2.9 2003 0.0290 AAPL -0.346
## 8 2.9 2003 0.0290 MSFT -0.220
## 9 3.8 2004 0.038 AAPL 0.491
## 10 3.8 2004 0.038 MSFT 0.0682
## # … with 28 more rowsPlot
# Visualize the relaionship between stock returns and GDP growth
data_merged %>%
ggplot(aes(yearly.returns, GDPgrowth)) +
geom_point() +
scale_x_continuous(label = scales::percent) +
scale_y_continuous(label = scales::percent) +
geom_smooth(method = "lm") +
facet_wrap(~symbol)
Q1. stock.prices Import Dow Jones Industrial Average and NASDAQ indexes since 1999.
stocks <- tq_get(c("^DJI","^IXIC"), get = "stock.prices", from = "1999-01-01")
stocks## # A tibble: 10,448 x 8
## symbol date open high low close volume adjusted
## <chr> <date> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 ^DJI 1999-01-04 9184. 9350. 9122. 9184. 89410000 9184.
## 2 ^DJI 1999-01-05 9185. 9339. 9183. 9311. 79860000 9311.
## 3 ^DJI 1999-01-06 9315. 9562. 9315. 9545. 103340000 9545.
## 4 ^DJI 1999-01-07 9542. 9542. 9426. 9538. 88290000 9538.
## 5 ^DJI 1999-01-08 9538. 9648. 9525. 9643. 103250000 9643.
## 6 ^DJI 1999-01-11 9643. 9643. 9533. 9620. 98720000 9620.
## 7 ^DJI 1999-01-12 9619. 9620. 9452. 9475. 95680000 9475.
## 8 ^DJI 1999-01-13 9471. 9471. 9213. 9350. 109060000 9350.
## 9 ^DJI 1999-01-14 9350. 9359. 9088. 9121. 90510000 9121.
## 10 ^DJI 1999-01-15 9127. 9343. 9127. 9341. 79440000 9341.
## # … with 10,438 more rowsQ2. Prepare the imported stock prices for merge.
stock_returns <-
stocks %>%
group_by(symbol) %>%
# Calculate yearly returns
tq_transmute(select = adjusted, mutate_fun = periodReturn, period = "yearly") %>%
# Create a new variable, year
mutate(year = year(date)+1) %>%
# Drop date
select(-date)
stock_returns## # A tibble: 42 x 3
## # Groups: symbol [2]
## symbol yearly.returns year
## <chr> <dbl> <dbl>
## 1 ^DJI 0.252 2000
## 2 ^DJI -0.0617 2001
## 3 ^DJI -0.0710 2002
## 4 ^DJI -0.168 2003
## 5 ^DJI 0.253 2004
## 6 ^DJI 0.0315 2005
## 7 ^DJI -0.00608 2006
## 8 ^DJI 0.163 2007
## 9 ^DJI 0.0643 2008
## 10 ^DJI -0.338 2009
## # … with 32 more rowsQ3 economic.data Import real U.S. GDP growth since 2000.
econ <- tq_get("A191RL1A225NBEA", get = "economic.data", from = "2000-01-01")
econ## # A tibble: 19 x 2
## date price
## <date> <dbl>
## 1 2000-01-01 4.1
## 2 2001-01-01 1
## 3 2002-01-01 1.7
## 4 2003-01-01 2.9
## 5 2004-01-01 3.8
## 6 2005-01-01 3.5
## 7 2006-01-01 2.9
## 8 2007-01-01 1.9
## 9 2008-01-01 -0.1
## 10 2009-01-01 -2.5
## 11 2010-01-01 2.6
## 12 2011-01-01 1.6
## 13 2012-01-01 2.2
## 14 2013-01-01 1.8
## 15 2014-01-01 2.5
## 16 2015-01-01 2.9
## 17 2016-01-01 1.6
## 18 2017-01-01 2.4
## 19 2018-01-01 2.9Hint: Find the symbol in FRED. Select in the list of related variables, Percent Change from Preceding Period, Annual, Not Seasonally Adjusted.
Q4. Prepare the imported economic data for merge.
econ_decimal <-
econ %>%
mutate(year = year(date), # Create a new variable, year
GDPgrowth = price/100) %>% # Convert price to decimal number
# Drop date
select(-date)
econ_decimal## # A tibble: 19 x 3
## price year GDPgrowth
## <dbl> <dbl> <dbl>
## 1 4.1 2000 0.0410
## 2 1 2001 0.01
## 3 1.7 2002 0.017
## 4 2.9 2003 0.0290
## 5 3.8 2004 0.038
## 6 3.5 2005 0.035
## 7 2.9 2006 0.0290
## 8 1.9 2007 0.019
## 9 -0.1 2008 -0.001
## 10 -2.5 2009 -0.025
## 11 2.6 2010 0.026
## 12 1.6 2011 0.016
## 13 2.2 2012 0.022
## 14 1.8 2013 0.018
## 15 2.5 2014 0.025
## 16 2.9 2015 0.0290
## 17 1.6 2016 0.016
## 18 2.4 2017 0.024
## 19 2.9 2018 0.0290Q5. Merge the two data sets.
data_merged <-
econ_decimal %>%
left_join(stock_returns)
data_merged## # A tibble: 38 x 5
## price year GDPgrowth symbol yearly.returns
## <dbl> <dbl> <dbl> <chr> <dbl>
## 1 4.1 2000 0.0410 ^DJI 0.252
## 2 4.1 2000 0.0410 ^IXIC 0.843
## 3 1 2001 0.01 ^DJI -0.0617
## 4 1 2001 0.01 ^IXIC -0.393
## 5 1.7 2002 0.017 ^DJI -0.0710
## 6 1.7 2002 0.017 ^IXIC -0.211
## 7 2.9 2003 0.0290 ^DJI -0.168
## 8 2.9 2003 0.0290 ^IXIC -0.315
## 9 3.8 2004 0.038 ^DJI 0.253
## 10 3.8 2004 0.038 ^IXIC 0.500
## # … with 28 more rowsQ6. Plot the relaionship between stock returns (of both indexes) and GDP growth?
data_merged %>%
ggplot(aes(yearly.returns, GDPgrowth)) +
geom_point() +
scale_x_continuous(label = scales::percent) +
scale_y_continuous(label = scales::percent) +
geom_smooth(method = "lm") +
facet_wrap(~symbol)
Hint: See the code in 4.2.1 Scatterplot in the textbook.
Q7. Describe the relationship between the two stock markets and economic growth. Which of the two indexes seems to have greater inflence on the economy?
Q8 Hide the messages, the code and its results on the webpage.
Hint: Use message, echo and results in the chunk options. Refer to the RMarkdown Reference Guide.