ECON 413: Zachary Smitherman

fred <- read.csv('fred_qd.csv')
fred <- fred[-(1:2),]

fred_ts <- fred
fred_ts <- ts(fred[,-1],start=c(1959,1),frequency = 4)

# It gets rid of the first column "sasdate"

fred$NETEX <- (fred$EXPGSC1-fred$IMPGSC1)

install.packages(“stargazer”)

library(stargazer) library(graphics)



stargazer(subset(fred,select=c(GDPC1,PCECC96,GPDIC1,GCEC1,NETEX)),type='text')
#GDP CV
sd(fred$GDPC1, na.rm = TRUE)/mean(fred$GDPC1, na.rm = TRUE)
#Consumption CV
sd(fred$PCECC96, na.rm = TRUE)/mean(fred$PCECC96, na.rm = TRUE)
#Investment CV
sd(fred$GPDIC1, na.rm = TRUE)/mean(fred$GPDIC1, na.rm = TRUE)
#Governemtn Expenditure CV
sd(fred$GCEC1, na.rm = TRUE)/mean(fred$GCEC1, na.rm = TRUE)
#NX CV
sd(fred$NETEX, na.rm = TRUE)/mean(fred$NETEX, na.rm = TRUE)

Investment is the most volatile variable according to the CV. This does make sense economically because investment and net exports are considered to be the most volatile variables.

fred_ts <- ts(fred[,-1],start=c(1959,1),frequency = 4)

gdp_components <- fred_ts[, c("GDPC1", "PCECC96", "GPDIC1", "GCEC1", "NETEX")]

plot(gdp_components)

#All the graphs are trending upwards except net exports which is trending down.

ts.plot(gdp_components,
        main="Macroeconomic Aggregates",
        xlab="Quarters",
        ylab="Billions 2012 USD",
        col=c("red","green","blue","black","brown"))
        legend("topleft",
        legend = c("GDP (Red)","Consumption (Green)", "Investment(Blue)", "Government Spending (Black)", "Net Exports (Brown)"),
         col = c("red", "green", "blue", "black", "brown"))

sumcomponents <- fred$PCECC96+fred$GPDIC1+fred$GCEC1+fred$NETEX
differenceGDP <- fred$GDPC1 - sumcomponents
summary(differenceGDP)
##     Min.  1st Qu.   Median     Mean  3rd Qu.     Max. 
## -198.782 -111.661  -27.578  -56.635    1.121   51.296
t.test(differenceGDP)
## 
##  One Sample t-test
## 
## data:  differenceGDP
## t = -13.123, df = 262, p-value < 2.2e-16
## alternative hypothesis: true mean is not equal to 0
## 95 percent confidence interval:
##  -65.13214 -48.13695
## sample estimates:
## mean of x 
## -56.63455
Deviation <- c(fred$GDPC1,sumcomponents)
plot(Deviation,
xlab="Deviation",
ylab="GDP",
col=c("black","red"))