How to analyze Arima forecast

x<-File name$frequency

tsData = ts(x, start = c(start year time, 1), frequency = 12 )

plot(tsData)

plot(x)

components.ts = decompose(tsData)

plot(components.ts)

install.packages(“fUnitRoots”)

library(“fUnitRoots”)

urkpssTest(tsData, type = c(“tau”), lags = c(“short”),use.lag = NULL, doplot = TRUE)

tsstationary = diff(tsData, differences=1)

plot(tsstationary)

acf(tsData,lag.max=34)

timeseriesseasonallyadjusted <- tsData- components.ts$seasonal

tsstationary <- diff(timeseriesseasonallyadjusted, differences=1)

plot(tsstationary)

acf(tsstationary, lag.max=34)

pacf(tsstationary, lag.max=34)

fitARIMA <- arima(tsData, order=c(1,0,1),seasonal = list(order = c(0,1,0), period=12), method=”ML”)

install.packages(“lmtest”)

library(lmtest)

coeftest(fitARIMA)

confint(fitARIMA)

acf(fitARIMA$residuals)

qqnorm(fitARIMA$residuals)

qqline(fitARIMA$residuals)

install.packages(“forecast”)

library(forecast)

auto.arima(tsData, trace=TRUE)

predict(fitARIMA,n.ahead = Year number*12)

futurVal <- forecast(fitARIMA,h= Year number*12, level=c(99.5))

plot(futurVal)