ARIMA Model

An ARIMA model is labelled as an ARIMA model (p, d, q), wherein:

_ p is the number of autoregressive terms;
_ d is the number of differences; and
_ q is the number of moving averages.
The autoregressive process. Autoregressive models assume that Yt is a linear
function of the preceding values and is given by equation (1) Yt ¼ α1Yt_1 þ εt
ð1Þ. Literally, each observation consists of a random component (random
shock, ε) and a linear combination of the previous observations. α1 in this
equation is the self-regression coefficient.

ACF and PCF

ACF is an (complete) auto-correlation function which gives us values of auto-
correlation of any series with its lagged values. It describes how well the
present value of the series is related with its past values. A time series can have
components like trend, seasonality, cyclic and residual. ACF considers all these
components while finding correlations hence it’s a ‘complete auto-correlation
plot’.
PACF is a partial auto-correlation function. Basically, instead of finding
correlations of present with lags like ACF, it finds correlation of the residuals
(which remains after removing the effects which are already explained by the
earlier lag(s)) with the next lag value hence ‘partial’ and not ‘complete’ as we
remove already found variations before we find the next correlation. So if there
is any hidden information in the residual which can be modelled by the next lag,
we might get a good correlation and we will keep that next lag as a feature
while modelling.
Methodology
1) Importing excel file based on UK inflation data from World Bank website
2) Converting data frame to time series data
3) Plotting yearly data on graph
4) Drawing acf graph which describes how well the present value of the
series is related with its past values.
5) Draw pcf graph which finds correlation of the residuals with the next lag
value.
6) Use ndiffs, which uses a unit root test to determine the number of
differences required for time series x to be made stationary.
7) Perform adf test to test whether given time series is stationary or not
8) Find the best ARIMA model
9) Plotting acf and pcf graph for residuals , making model for each ARIMA
values and forecasting data.