📈 Retail sales and advertising spend
Research question: How strongly are sales related to advertising, and how much extra sales does each RM 1,000 of advertising bring? Answer: Advertising spend (RM thousand) and sales (RM thousand) were strongly positively correlated, r(34) = .83, p < .001. A simple linear regression showed that advertising spend (RM thousand) explained 69.2% of the variance in sales (RM thousand), F(1, 34) = 76.26, p < .001. Each additional unit of advertising spend (RM thousand) was associated with 4.29 more units of sales (RM thousand), B = 4.29, 95% CI [3.29, 5.29].
Open this example in StatLab Dataset and codebook (CSV, Excel, .sav)
What is the situation?
A fictional electronics retailer recorded monthly advertising spend and sales (both in RM thousand) for 36 months. The data are synthetic — produced by a seeded random process for teaching; they describe no real people or organisations.
What is in the dataset?
36 cases.
| Variable | Label | Measure | Value labels |
|---|---|---|---|
month | Month number | scale | |
ad_spend | Advertising spend (RM thousand) | scale | |
sales | Sales (RM thousand) | scale |
How is it analysed, step by step?
- Scatterplot — Always look at the relationship before fitting a line. (guide)
The points rise from left to right in a roughly straight band; fit line: Sales (RM thousand) = 112.78 + 4.29 × Advertising spend (RM thousand). - Correlations — Strength and direction of the linear relationship. (guide)
Advertising spend (RM thousand) – Sales (RM thousand): r = .83, p < .001 - Linear regression — Estimate the slope (extra sales per RM 1,000 of advertising). (guide)
R² = .692, adjusted R² = .683, F(1, 34) = 76.26, p < .001, Durbin-Watson = 2.07.
(Constant): B = 112.781, SE = 12.628, t = 8.93, p < .001
Advertising spend (RM thousand): B = 4.291, SE = .491, β = .83, t = 8.73, p < .001, VIF = 1.00
How would I write it up (APA style)?
Advertising spend (RM thousand) and sales (RM thousand) were strongly positively correlated, r(34) = .83, p < .001. A simple linear regression showed that advertising spend (RM thousand) explained 69.2% of the variance in sales (RM thousand), F(1, 34) = 76.26, p < .001. Each additional unit of advertising spend (RM thousand) was associated with 4.29 more units of sales (RM thousand), B = 4.29, 95% CI [3.29, 5.29].
Every number on this page was computed by StatLab's statistics engine from this dataset when the page was built, and the same analyses are part of the reference validation against scipy/statsmodels (433 reference test cases, 36,554 values checked against scipy/statsmodels/numpy, 0 failures). “Open this example” loads the data and runs these steps live in your browser.