Time adds order and dependence. Treating monthly observations as an unordered sample discards information needed for forecasting and uncertainty.

Base stats; tsibble, fable, and feasts are optional modern extensions.

yt = trend_t + seasonal_t + remainder_t

1. Step 1Define every variable and unit.
2. Step 2Check assumptions and information timing.
3. Step 3Calculate, verify, and interpret in context.

Variable

Five years of simulated monthly values with known seasonality.

Model choice

STL components depend on smoothing choices and are not uniquely observed causal quantities.

Calculation

Frequency = 12; STL returns data, seasonal, trend, and remainder components.

Interpretation

The periodic seasonal pattern repeats by month while trend rises; remainder captures what this decomposition leaves.

Reasonableness check

Full-sample decomposition is descriptive and uses future values near earlier dates; forecast evaluation must refit on training data.

The periodic seasonal pattern repeats by month while trend rises; remainder captures what this decomposition leaves. Limitation: Full-sample decomposition is descriptive and uses future values near earlier dates; forecast evaluation must refit on training data.

A simulated monthly series combines a rising trend and repeating seasonal movement.

Run the self-contained starter code in the protected STATLAB R runner. The code prints an auditable result and avoids network or unrestricted file access.

Compare your result with the definition, units, and model assumptions—not only with a target number.

Complete these without looking at the selected solutions. More than one defensible program may exist.

These are compact solution routes. Confirm dimensions, units, and any changed modelling choices.

Represent ordered data correctly and separate levels, changes, trend, seasonality, and remainder.

Name the assumption, evidence you would seek, and how the recommendation might change.

Reach 70% to complete the chapter. Explanations appear after submission.