Time Series Analysis and ARIMA model

Time series is a set of data points indexed in time order. Some typical example are annual s&p 500 index, daily temperature and website visit per second.

All time series can be decomposed as a multiplicative or additive function of three components.

1. S_t : seasonal factor

2. T_t: trend or cyclical patter

3. Error_t : random errors

Y_t = T_t + S_t + Error_t

For example, the air passenger data shows a very significant upward trend and seasonal…