E5a — AQA GCSE Statistics
Test yourself on E5a with AQA GCSE practice questions.
Start free
7 days Premium · Then free forever · No card, no charge
Your focus
- Interpret a distribution of data in terms of skewness identified from inspection.
E5a exam tips
Quick Revision Summary (Key Takeaway)
AQA GCSE Statistics specification E5a covers time series data, focusing on calculating moving averages, plotting trend lines, and evaluating seasonal variations. Students learn to smooth out short-term fluctuations to identify underlying trends and make reliable contextual forecasts for real-world scenarios.
Topic Overview
E5a Time Series and Moving Averages teaches students how to process sequential data recorded over regular intervals of time, such as days, months, or quarters. By smoothing out seasonal peaks and troughs, students can identify underlying long-term trends.
This module equips learners with core quantitative forecasting techniques essential for economics, business forecasting, and meteorological modeling. Mastery of this topic connects directly into correlation, trend estimation, and critical evaluation of statistical predictions.
Key Concepts
- →Time series data consists of pairs of values where the independent variable is sequential time periods (days, quarters, years).
- →Moving averages smooth out short-term seasonal and irregular fluctuations to reveal the long-term underlying trend.
- →Centred moving averages are required whenever an even number of data points (e.g. 4-point quarterly data) is averaged, placing the smoothed point precisely on an observed time coordinate.
- →Seasonal variation measures the deviation of an actual value from the trend line (Additive Model: Actual = Trend + Seasonal Variation + Random Variation).
- →Extrapolation using trend lines allows for forecasting, but uncertainty increases the further into the future predictions are made.
Examiner Tips
- 💡Always draw moving average trend lines with a sharp pencil and ruler, ensuring the line passes centrally through the scatter of moving average points.
- 💡When asked to calculate mean seasonal variation, always check whether any values are negative; sum them carefully using signed arithmetic.
- 💡In commentary questions, always contextualise your answer: mention the specific variables (e.g. sales, rainfall, visitor numbers) rather than speaking in abstract statistical terms.
Common Mistakes
- Plotting moving averages at the wrong time coordinates: students frequently plot odd-period moving averages offset between points, or plot uncentred even-period averages directly on whole intervals.
- Confusing the additive model with the multiplicative model: students often multiply when they should add/subtract the seasonal variation.
- Assuming trend lines can be reliably projected indefinitely into the future, ignoring economic or environmental structural changes.
Revision Plan
- 1Day 1-2: Review time series graphs, practice calculating 3-point and 5-point moving averages, and plot trend lines correctly.
- 2Day 3-4: Master 4-point centred moving averages, ensuring accurate alignment with middle quarters.
- 3Day 5-6: Practise calculating seasonal variations and mean seasonal variations using the additive model.
- 4Day 7: Complete past paper exam questions involving future forecasts and writing contextual evaluations of reliability.
Exam Question Types
- 📋Table completion: Calculating missing values in a moving average table (including centred values).
- 📋Graph plotting: Plotting moving averages onto an existing time series graph and ruling a trend line.
- 📋Calculation and forecasting: Working out the mean seasonal effect and producing a numeric forecast for a given future period.
- 📋Evaluation and critique: Assessing the validity or reliability of an extrapolated prediction in context.
Command Word Expectations (AQA)
Calculate
Show all working clearly, including addition of raw values and division by the period count, followed by the exact numerical answer.
Plot
Mark coordinates with small crosses accurately within half a small square on the grid at the correct time positions.
Predict / Estimate
Read the trend value from your trend line at the requested time period, add/subtract the seasonal variation, and state the final value with units.
How Students Lose Marks (Examiner Pitfalls)
Pitfall: Failing to centre moving averages when dealing with an even number of data points (such as quarterly data).
❌ Weak Answer (Loses Marks):The student calculates 4-point moving averages and plots each point directly on Quarter 2 or Quarter 3 without centring.
Example improved answer:Calculate consecutive 4-point moving totals, take pairs of these totals to find 8-point sums, and divide by 8 to obtain centred moving averages aligned precisely with each corresponding quarter.
Examiner Tip: For quarterly data, examiners insist on centred moving averages; ensure your points are plotted directly on the time period mark, not between gridlines.
Pitfall: Ignoring the additive or multiplicative model structure when calculating seasonal variation and future predictions.
❌ Weak Answer (Loses Marks):The student extends the trend line to estimate a future value but forgets to add or subtract the mean seasonal variation.
Example improved answer:Predicted value = Trend line value + Mean seasonal effect (using the additive model: Y = T + S + I). Identify the trend value at the target period from the line of best fit, then add the calculated mean seasonal variation for that specific season.
Examiner Tip: Always check whether the question specifies an additive model or multiplicative model before applying the seasonal adjustment to your trend estimate.
Step-by-Step Worked Solutions
Question: The quarterly sales (in thousands of pounds) of an ice cream parlour over two years are: Year 1: Q1 = 12, Q2 = 28, Q3 = 44, Q4 = 16. Year 2: Q1 = 14, Q2 = 32, Q3 = 50, Q4 = 20. Calculate the first centred 4-point moving average.
- 1.Step 1: Calculate the first two 4-point moving totals. Total 1 (Y1 Q1-Q4) = 12 + 28 + 44 + 16 = 100. Total 2 (Y1 Q2 to Y2 Q1) = 28 + 44 + 16 + 14 = 102.
- 2.Step 2: Add the two consecutive 4-point moving totals to produce an 8-point total: 100 + 102 = 202.
- 3.Step 3: Divide the combined total by 8 (or average the two 4-point means of 25 and 25.5): Centred Moving Average = 202 / 8 = 25.25.
- 4.Step 4: State the alignment: This centred moving average corresponds exactly to Year 1, Quarter 3.
Final Answer: 25.25 thousand pounds (aligned at Year 1, Quarter 3)
Question: A company uses an additive time series model. For Quarter 4, the trend line equation gives an estimated value of 84 units. The seasonal variations for Quarter 4 over the past three years are -14, -18, and -16. Predict the actual sales for Quarter 4 and comment on its reliability.
- 1.Step 1: Calculate the mean seasonal variation for Quarter 4: (-14 + -18 + -16) / 3 = -48 / 3 = -16 units.
- 2.Step 2: Apply the additive model formula: Predicted Value = Trend Value + Mean Seasonal Variation = 84 + (-16) = 68 units.
- 3.Step 3: Evaluate reliability: The prediction is reasonably reliable if it is within or close to the given data range, but reliability reduces if extrapolating far into the future or if random variation is large.
Final Answer: Predicted sales = 68 units. The forecast is reliable for near-term estimation assuming past seasonal patterns continue consistently.
Active Recall Memory Test
Why are moving averages calculated in time series analysis?
Key Fact: To smooth out regular seasonal fluctuations and random noise, exposing the true underlying trend.
Why must 4-point moving averages be centred before plotting?
Key Fact: Because the average of four values falls between time periods (at 2.5); centring pairs of averages realigns points with actual time periods.
What is the formula for seasonal variation in an additive time series model?
Key Fact: Seasonal Variation = Actual Value - Trend Value.
What two values must be combined to forecast a future time series value using an additive model?
Key Fact: The trend line value at that time period and the mean seasonal variation for that specific season.
Frequently Asked Questions
When should I use a 4-point moving average versus a 3-point moving average?
The number of points in a moving average should match the natural periodicity of the data. For quarterly data with four seasons in a year, use a 4-point moving average. For data with cyclical patterns every three days or three months, use a 3-point moving average.
Why do moving average points stop before the end of the time series graph?
A moving average requires surrounding data points to compute. For example, an n-point moving average loses points at the start and end of the series because complete groups of n consecutive values cannot be formed without past or future data.
What is the difference between an additive and a multiplicative time series model?
In an additive model, seasonal effects are assumed to have a constant absolute size added to or subtracted from the trend (Actual = Trend + Seasonal). In a multiplicative model, seasonal variations are proportional to the trend and expressed as percentages or factors (Actual = Trend x Seasonal factor).
Why is extrapolation risky when using a time series trend line?
Extrapolation assumes past patterns will continue unchanged into the future. External shocks, changes in customer behaviour, or market saturation can invalidate the trend, making long-term forecasts unreliable.
Do I plot the trend line through the raw data or the moving average points?
You should always draw the trend line through the plotted moving average points, not the raw data points. The moving averages represent the smoothed trend, whereas raw points contain seasonal and random fluctuations.