QCE General Mathematics - Unit 3 - Time series analysis
Describing Patterns in Time Series Data | QCE General Mathematics
Learn trend, seasonality and irregular fluctuations in QCE General Mathematics time series plots.
Updated 2026-05-18 - 5 min read
QCAA official coverage - General Mathematics 2025 v1.3
Exact syllabus points covered
- Construct and use time series plots.
- Describe time series plots by identifying features, including trend (long-term direction, e.g. increasing/decreasing), seasonality (systematic, calendar-related movements) and irregular fluctuations (unsystematic, short-term fluctuations).
A time series records data in time order. The time variable might be months, quarters, years, days or hours. The graph is different from an ordinary scatterplot because the order matters: adjacent points are connected to show movement over time.
Original Sylligence diagram for general time series components.
The main features
| Feature | Meaning | Example | |---|---|---| | Trend | long-term direction | yearly sales gradually increase | | Seasonality | repeated calendar-related pattern | electricity use rises each summer | | Irregular fluctuations | short-term unpredictable movement | a sudden drop after a storm |
Trend can be increasing, decreasing or roughly stable. Seasonality repeats over a known period such as each week, month, quarter or year. Irregular fluctuations do not follow the regular seasonal pattern.
Reading a time series plot
A strong response should refer to direction, timing and context. Instead of saying "it goes up and down", say "sales peak each December and fall each February, suggesting a seasonal pattern linked to holiday demand."
If there is a sudden unusual value, call it an outlier or irregular fluctuation only if it sits away from the usual pattern. A single high point during the same month every year is probably seasonal, not irregular.
Worked example
Common traps
Also avoid giving a conclusion without evidence. Refer to dates, months, years or relative size when the graph allows it.
Extra descriptive features
The current syllabus names trend, seasonality and irregular fluctuations. The source notes also discuss related language that can help you interpret graphs:
| Feature | Meaning | How to use it carefully | |---|---|---| | Outlier | an unusually high or low time point | identify the time and explain how it differs | | Structural change | a lasting shift in level or pattern | look for a change after a policy, event or disruption | | Cycle | repeated movement not tied to a fixed calendar period | useful context, but do not confuse it with seasonality |
These are useful descriptive ideas, but keep official syllabus wording at the centre of your answer.
Evidence-based descriptions
Weak description: "The graph goes up and down."
Stronger description: "The series has an overall increasing trend from 2021 to 2025, with repeated peaks in the December quarter and one unusually low value in March 2024."
Mentioning time points makes the interpretation more mathematical and less like a visual guess.
Depth: separating trend, seasonality and irregular variation
Time series data is ordered by time, so the sequence matters. The same values in a different order could show a different story. When describing a time series, separate the major features rather than writing one vague sentence.
| Feature | Meaning | Example wording | |---|---|---| | Trend | long-term movement | sales show an overall upward trend | | Seasonality | repeated pattern at fixed intervals | demand peaks each summer | | Cyclical movement | longer wave-like changes not fixed to one year | building approvals rise and fall across several years | | Irregular variation | random short-term changes | one month is unusually low | | Structural change | pattern shifts after an event | the level increases after a new policy |
The 2025 syllabus emphasises trend, seasonality and irregular fluctuations. It is still useful to recognise cycles and structural breaks when explaining real data.
Describing trend shape
Trend may be increasing, decreasing, approximately constant or changing direction. It can also be linear or non-linear.
Reading from a graph
When interpreting a time-series graph:
- Start with the overall direction across the full time span.
- Look for repeated peaks and troughs.
- Identify unusually high or low observations.
- Mention approximate values or dates to support the description.
- Avoid explaining causes unless the graph or context provides evidence.
Forecasting cautions
Forecasts are more reliable when the past pattern is stable and the prediction is close to the observed time range. They are less reliable when:
- the trend is changing rapidly
- there is a structural break
- the seasonal pattern is inconsistent
- the forecast is far into the future
- external conditions have changed
This is similar to extrapolation in regression: extending a pattern is a modelling assumption, not a guarantee.