Lesson 6: Fitting a trend line
Fit a trend line to deseasonalised data
SkillsFitting a trend lineDeseasonalising data
Worked example
The deseasonalised guest nights (thousands) at the holiday park, from Q1 2022 () to Q4 2024 (), are:
| 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | 12 | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Deseasonalised | 30.11 | 30.09 | 30.08 | 29.74 | 32.49 | 32.95 | 32.16 | 32.53 | 34.87 | 34.38 | 35.27 | 35.32 |
a) Fit a least-squares trend line to the deseasonalised data, with coefficients correct to three decimal places.
b) Interpret the slope, and comment on the strength of the trend.
Step 1: Enter the data
values in the list, deseasonalised values in the list.
The trend line is fitted to deseasonalised values so the seasonal zigzag doesn't distort it.
Step 2: Run the regression
Technology gives , and .
Step 3: Write the line
Step 4: Interpret
Deseasonalised guest nights are increasing by about 0.556 thousand, or 556 guest nights, per quarter. shows a strong, increasing linear trend.
Answer
(thousands, is Q1 2022). Deseasonalised guest nights increase by about 556 per quarter; indicates a strong increasing trend.
Try a similar one
A fresh question of the same kind, checked as you answer, with hints and a full solution.
Method
Deseasonalise first (or use the deseasonalised values given).
Fit the least-squares line of deseasonalised value against .
Interpret the slope per period, and use to describe the strength of the trend.
Watch out for
Fitting the line to the raw guest nights, which gives with .
Saying "per year" when counts quarters.