Introduction to Time Series Analysis

This part introduces the core concepts needed before formal ARIMA modeling. The focus is on understanding observed dynamics in time-indexed data: trend, seasonality, irregular variation, and short-term dependence.

It is intentionally case-driven. The same business context is reused so you can compare decomposition and ad hoc forecasting approaches on one coherent dataset.

How This Part Is Structured

Block	Purpose	Main chapters
Case context	Frame the applied forecasting problem and data characteristics	Case: HPC
Decomposition	Separate trend, seasonal, and irregular components	Decomposition of Time Series
Ad hoc forecasting	Build baseline forecasts and diagnose residual behavior	Ad Hoc Models for Time Series

How To Use It

Start here if you are new to time series or if you need an interpretable baseline before ARIMA.
After completing this part, continue with 148  Introduction to Box-Jenkins Analysis for systematic ARIMA identification, estimation, diagnostics, and forecasting.