plot(var()) displays two different plots, how do I merge them into one? Also having two y axis

Question

> dput(head(inputData))
structure(list(Date = c("2018:07:00", "2018:06:00", "2018:05:00", 
"2018:04:00", "2018:03:00", "2018:02:00"), IIP = c(125.8, 127.5, 
129.7, 122.6, 140.3, 127.4), CPI = c(139.8, 138.5, 137.8, 137.1, 
136.5, 136.4), `Term Spread` = c(1.580025, 1.89438, 2.020112, 
1.899074, 1.470544, 1.776862), RealMoney = c(142713.9916, 140728.6495, 
140032.2762, 139845.5215, 139816.4682, 139625.865), NSE50 = c(10991.15682, 
10742.97381, 10664.44773, 10472.93333, 10232.61842, 10533.10526
), CallMoneyRate = c(6.161175, 6.10112, 5.912088, 5.902226, 5.949956, 
5.925538), STCreditSpread = c(-0.4977, -0.3619, 0.4923, 0.1592, 
0.3819, -0.1363)), row.names = c(NA, -6L), class = c("tbl_df", 
"tbl", "data.frame"))

I want to make my autoregressive plot like this plot:

this plot(destination plot)

#------> importing all libraries
library(readr)
install.packages("lubridtae")
library("lubridate")
install.packages("forecast")
library('ggplot2')
library('fpp')
library('forecast')
library('tseries')

#--------->reading data
inputData <- read_csv("C:/Users/sanat/Downloads/exercise_1.csv")

#--------->calculating the lag=1 for NSE50

diff_NSE50<-(diff(inputData$NSE50, lag = 1, differences = 1)/lag(inputData$NSE50))
diff_RealM2<-(diff(inputData$RealMoney, lag = 1, differences = 1)/lag(inputData$RealMoney))


plot.ts(diff_NSE50)
#--------->
lm_fit = dynlm(IIP ~ CallMoneyRate + STCreditSpread + diff_NSE50 + diff_RealM2, data = inputData)
summary(lm_fit)
#--------->
inputData_ts = ts(inputData, frequency = 12, start = 2012)

#--------->area of my doubt is here 

VAR_data <- window(ts.union(ts(inputData$IIP), ts(inputData$CallMoneyRate)))
VAR_est <- VAR(y = VAR_data, p = 12)
plot(VAR_est)

I want to my plots to get plotted together in same plot. How do I serparate the var() plots to two separate ones.

Current plot:

My current plot(source)

My dataset : dataset

Please provide some sample data. Try adding the result from dput(head(VAR_est)) to the question. — Hector Haffenden, Mar 26 '19 at 22:04
I have added my whole dataset.and VAR function is from vars package — sana, Mar 26 '19 at 22:23
Could you add the data in a form we can just copy and paste it in? Please use dput(), see https://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example for more information — Hector Haffenden, Mar 26 '19 at 22:25

Hector Haffenden · Accepted Answer · 2019-03-26T23:04:33.633

Okay, so this still needs some work, but it should set the right framework for you. I would look more into working with the ggplot2 for future.

Few extra packages needed, namely library(vars) and library(dynlm).

Starting from,

VAR_est <- VAR(y = VAR_data, p = 12)

Now we extract the values we want from the VAR_est object.

y <- as.numeric(VAR_est$y[,1])
z <- as.numeric(VAR_est$y[,2])
x <- 1:length(y)


## second data set on a very different scale
par(mar = c(5, 4, 4, 4) + 0.3)  # Leave space for z axis
plot(x, y, type = "l") # first plot
par(new = TRUE)
plot(x, z, type = "l", axes = FALSE, bty = "n", xlab = "", ylab = "")
axis(side=4, at = pretty(range(z)))
mtext("z", side=4, line=3)

I will leave you to add the dotted lines on etc...

Hint: Decompose the VAR_est object, for example, VAR_est$datamat, then see which bit of data corresponds to the part of the plot you want.

Used some of this

The plots look different and normal ts plots have been plotted.I think `VAR_est` did not standardize and scale the plots.Will ggplot2 help? — sana, Mar 26 '19 at 23:08
I see, one solution could be to standardise and scale the y and z data yourself? Assuming this is just subtracting the mean and dividing by the sd of the data? For example, `a <- c(1,2,3,4); std.a <- (a-mean(a)) / sd(a)` — Hector Haffenden, Mar 26 '19 at 23:10

plot(var()) displays two different plots, how do I merge them into one? Also having two y axis

1 Answers1